\u4e8c\u3001\u73af\u5883\u51c6\u5907<\/h3>\n1. \u6838\u5fc3\u4f9d\u8d56\u5b89\u88c5<\/h4>\n
\u672c\u6b21\u5b9e\u6218\u4ec5\u9700\u5b89\u88c5DrissionPage\u6846\u67b6（\u96c6\u6210\u6d4f\u89c8\u5668\u81ea\u52a8\u5316 + \u63a5\u53e3\u76d1\u542c，\u65e0\u9700\u989d\u5916\u5b89\u88c5 Selenium\/Requests）：<\/p>\n
pip install DrissionPage<\/p>\n
2. \u73af\u5883\u8bf4\u660e<\/h4>\n\n- Python \u7248\u672c：3.8 \u53ca\u4ee5\u4e0a（\u63a8\u8350 3.9~3.11，\u517c\u5bb9 DrissionPage）；<\/li>\n
- \u64cd\u4f5c\u7cfb\u7edf：Windows\/macOS\/Linux \u5747\u652f\u6301；<\/li>\n
- \u6d4f\u89c8\u5668：\u81ea\u52a8\u9002\u914d\u672c\u5730 Chrome \u6d4f\u89c8\u5668，\u65e0\u9700\u624b\u52a8\u914d\u7f6e\u9a71\u52a8（DrissionPage \u5df2\u5185\u7f6e\u9002\u914d\u903b\u8f91）\u3002<\/li>\n<\/ul>\n
\u4e09\u3001\u5b8c\u6574\u5b9e\u6218\u4ee3\u7801<\/h3>\n
\u76f4\u63a5\u590d\u5236\u4ee5\u4e0b\u4ee3\u7801，\u4fee\u6539\u5c11\u91cf\u914d\u7f6e（\u5982\u5730\u533a\u7f16\u7801\u3001\u5c97\u4f4d\u5927\u7c7b）\u5373\u53ef\u8fd0\u884c：<\/p>\n
import time
\nimport json
\nimport logging
\nfrom DrissionPage import ChromiumPage<\/p>\n
# ===================== \u81ea\u5b9a\u4e49\u914d\u7f6e（\u6839\u636e\u9700\u6c42\u4fee\u6539） =====================
\n# 1. \u5c97\u4f4d\u5927\u7c7b\u4e0e\u7ec6\u5206\u5c97\u4f4d\u914d\u7f6e（\u53ef\u81ea\u884c\u6269\u5c55）
\nJOB_BIG_TYPE = {
\n "\u6280\u672f\u5f00\u53d1": ["Python", "Java", "\u524d\u7aef", "\u540e\u7aef", "\u6d4b\u8bd5", "\u8fd0\u7ef4"],
\n "\u4ea7\u54c1\u8fd0\u8425": ["\u4ea7\u54c1\u7ecf\u7406", "\u8fd0\u8425", "\u65b0\u5a92\u4f53", "\u7535\u5546\u8fd0\u8425"],
\n "\u8bbe\u8ba1": ["UI\u8bbe\u8ba1", "\u5e73\u9762\u8bbe\u8ba1", "\u4ea4\u4e92\u8bbe\u8ba1", "\u89c6\u89c9\u8bbe\u8ba1"]
\n}<\/p>\n
# 2. \u722c\u53d6\u5730\u533a\u7f16\u7801（040000=\u4e0a\u6d77，\u53ef\u66ff\u6362\u4e3a\u5176\u4ed6\u57ce\u5e02：101010100=\u5317\u4eac，101280600=\u6df1\u5733）
\nCITY_CODE = "040000"<\/p>\n
# 3. \u6700\u5927\u7ffb\u9875\u6570（\u907f\u514d\u722c\u53d6\u8fc7\u591a\u89e6\u53d1\u53cd\u722c）
\nMAX_PAGE_PER_KEYWORD = 3<\/p>\n
# ===================== \u6570\u636e\u6a21\u578b\u4e0e\u5de5\u5177\u51fd\u6570 =====================
\ndef BossItem():
\n """\u5b9a\u4e49\u5c97\u4f4d\u6570\u636e\u6a21\u578b（\u66ff\u4ee3Scrapy Item，\u7528\u5b57\u5178\u6807\u51c6\u5316\u5b57\u6bb5）"""
\n return {
\n "job_id": "", # \u5c97\u4f4d\u552f\u4e00ID
\n "\u5c97\u4f4d\u540d\u79f0": "", # \u539f\u59cb\u5c97\u4f4d\u540d
\n "\u6807\u51c6\u5c97\u4f4d": "", # \u6807\u51c6\u5316\u540e\u7684\u5c97\u4f4d\u540d
\n "\u5c97\u4f4d\u5927\u7c7b": "", # \u5c97\u4f4d\u6240\u5c5e\u5927\u7c7b
\n "\u516c\u53f8": "", # \u516c\u53f8\u5168\u79f0
\n "\u516c\u53f8\u9886\u57df": "", # \u516c\u53f8\u6240\u5c5e\u884c\u4e1a
\n "\u89c4\u6a21": "", # \u516c\u53f8\u89c4\u6a21
\n "\u85aa\u8d44": "", # \u85aa\u8d44\u8303\u56f4
\n "\u5b66\u5386\u8981\u6c42": "", # \u5b66\u5386\u8981\u6c42
\n "\u7ecf\u9a8c\u8981\u6c42": "", # \u5de5\u4f5c\u7ecf\u9a8c\u8981\u6c42
\n "\u6280\u80fd\u9700\u6c42": "", # \u5c97\u4f4d\u6280\u80fd\u6807\u7b7e
\n "\u5e02": "", # \u57ce\u5e02
\n "\u533a": "", # \u884c\u653f\u533a
\n "\u5546\u5708": "", # \u5546\u5708
\n "\u7ecf\u5ea6": "", # \u7ecf\u5ea6
\n "\u7eac\u5ea6": "", # \u7eac\u5ea6
\n "\u641c\u7d22\u5173\u952e\u8bcd": "", # \u722c\u53d6\u8be5\u5c97\u4f4d\u7684\u641c\u7d22\u5173\u952e\u8bcd
\n "\u6765\u6e90\u6e20\u9053": "51job", # \u6570\u636e\u6765\u6e90
\n "\u8bbf\u95ee\u5730\u5740": "" # \u5c97\u4f4d\u8be6\u60c5\u9875\u94fe\u63a5
\n }<\/p>\n
def normalize_job(job_name):
\n """\u6807\u51c6\u5316\u5c97\u4f4d\u540d\u79f0，\u5339\u914d\u5927\u7c7b\u548c\u6807\u51c6\u5c97\u4f4d"""
\n for big_type, jobs in JOB_BIG_TYPE.items():
\n for j in jobs:
\n if j in job_name:
\n return big_type, j
\n return "\u5176\u4ed6", "\u5176\u4ed6"<\/p>\n
def build_search_keywords():
\n """\u57fa\u4e8eJOB_BIG_TYPE\u6784\u5efa\u53bb\u91cd\u540e\u7684\u641c\u7d22\u5173\u952e\u8bcd\u5217\u8868"""
\n keywords = []
\n for jobs in JOB_BIG_TYPE.values():
\n keywords.extend(jobs)
\n return list(set(keywords)) # \u53bb\u91cd<\/p>\n
# ===================== \u6838\u5fc3\u722c\u866b\u7c7b =====================
\nclass Job51Spider:
\n def __init__(self):
\n # 1. \u914d\u7f6e\u65e5\u5fd7（\u66ff\u4ee3Scrapy logger，\u5b9e\u65f6\u8f93\u51fa\u722c\u53d6\u8fdb\u5ea6）
\n logging.basicConfig(
\n level=logging.INFO,
\n format='%(asctime)s – %(levelname)s – %(message)s',
\n handlers=[logging.StreamHandler()] # \u8f93\u51fa\u5230\u63a7\u5236\u53f0
\n )
\n self.logger = logging.getLogger(__name__)<\/p>\n
# 2. \u521d\u59cb\u5316\u6d4f\u89c8\u5668（headless=True \u542f\u7528\u65e0\u5934\u6a21\u5f0f，\u65e0\u754c\u9762\u8fd0\u884c）
\n self.dp = ChromiumPage(headless=False) # \u8c03\u8bd5\u65f6\u8bbe\u4e3aFalse，\u4e0a\u7ebf\u8bbe\u4e3aTrue
\n # 3. \u5f00\u542f\u63a5\u53e3\u76d1\u542c，\u76d1\u542c51job\u641c\u7d22\u63a5\u53e3\u6807\u8bc6（search-pc）
\n self.dp.listen.start("search-pc")
\n self.logger.info("\u2705 \u6d4f\u89c8\u5668\u521d\u59cb\u5316\u5b8c\u6210，\u63a5\u53e3\u76d1\u542c\u5df2\u5f00\u542f")<\/p>\n
def parse_jobs(self, job_list, keyword):
\n """
\n \u89e3\u6790\u5355\u9875\u804c\u4f4d\u5217\u8868\u6570\u636e
\n :param job_list: \u63a5\u53e3\u8fd4\u56de\u7684\u5c97\u4f4d\u5217\u8868
\n :param keyword: \u5f53\u524d\u641c\u7d22\u5173\u952e\u8bcd
\n :return: \u7ed3\u6784\u5316\u7684\u5c97\u4f4d\u5b57\u5178\u5217\u8868
\n """
\n job_items = []
\n for job in job_list:
\n try:
\n item = BossItem()
\n job_name = job.get("jobName", "")
\n # \u6807\u51c6\u5316\u5c97\u4f4d\u540d\u79f0
\n big_type, std_job = normalize_job(job_name)
\n # \u89e3\u6790\u5730\u533a\u4fe1\u606f（\u5d4c\u5957\u5b57\u5178\u5bb9\u9519）
\n area = job.get("jobAreaLevelDetail", {})<\/p>\n
# \u586b\u5145\u5c97\u4f4d\u6570\u636e（\u5168\u91cf\u5bb9\u9519，\u907f\u514d\u5b57\u6bb5\u7f3a\u5931\u62a5\u9519）
\n item["job_id"] = job.get("jobId", "")
\n item["\u5c97\u4f4d\u540d\u79f0"] = job_name
\n item["\u6807\u51c6\u5c97\u4f4d"] = std_job
\n item["\u5c97\u4f4d\u5927\u7c7b"] = big_type
\n item["\u516c\u53f8"] = job.get("fullCompanyName", "")
\n item["\u516c\u53f8\u9886\u57df"] = job.get("industryType1Str", "")
\n item["\u89c4\u6a21"] = job.get("companySizeString", "")
\n item["\u85aa\u8d44"] = job.get("provideSalaryString", "")
\n item["\u5b66\u5386\u8981\u6c42"] = job.get("degreeString", "")
\n item["\u7ecf\u9a8c\u8981\u6c42"] = job.get("workYearString", "")
\n # \u63d0\u53d6\u6280\u80fd\u6807\u7b7e（\u8df3\u8fc7\u524d2\u4e2a\u65e0\u5173\u6807\u7b7e）
\n job_tags_slice = job.get("jobTags", [])[2:]
\n item["\u6280\u80fd\u9700\u6c42"] = ",".join(job_tags_slice) if job_tags_slice else "\u6682\u65e0"
\n item["\u5e02"] = area.get("cityString", "")
\n item["\u533a"] = area.get("districtString", "")
\n item["\u5546\u5708"] = job.get("landmarkString", "")
\n item["\u7ecf\u5ea6"] = job.get("lon", "")
\n item["\u7eac\u5ea6"] = job.get("lat", "")
\n item["\u641c\u7d22\u5173\u952e\u8bcd"] = keyword
\n item["\u8bbf\u95ee\u5730\u5740"] = job.get("jobHref", "")<\/p>\n
job_items.append(item)
\n self.logger.info(f"📌 \u89e3\u6790\u5230\u804c\u4f4d：{job_name} – {item['\u516c\u53f8']} – {item['\u85aa\u8d44']}")<\/p>\n
except Exception as e:
\n self.logger.warning(f"\u26a0\ufe0f \u5355\u4e2a\u5c97\u4f4d\u89e3\u6790\u5931\u8d25，\u8df3\u8fc7：{str(e)}")
\n continue<\/p>\n
# \u89e3\u6790\u5b8c\u4e00\u9875\u540e\u4f11\u7720，\u964d\u4f4e\u53cd\u722c\u98ce\u9669
\n time.sleep(5)
\n return job_items<\/p>\n
def crawl(self):
\n """\u6838\u5fc3\u722c\u53d6\u903b\u8f91：\u904d\u5386\u5173\u952e\u8bcd\u2192\u63a5\u53e3\u76d1\u542c\u2192\u7ffb\u9875\u2192\u89e3\u6790\u6570\u636e"""
\n # 1. \u6784\u5efa\u6240\u6709\u641c\u7d22\u5173\u952e\u8bcd
\n keywords = build_search_keywords()
\n self.logger.info(f"📋 \u5171\u751f\u6210 {len(keywords)} \u4e2a\u641c\u7d22\u5173\u952e\u8bcd：{keywords}")<\/p>\n
# 2. \u5b58\u50a8\u6240\u6709\u722c\u53d6\u7684\u804c\u4f4d\u6570\u636e
\n all_jobs = []<\/p>\n
# 3. \u904d\u5386\u6bcf\u4e2a\u5173\u952e\u8bcd\u722c\u53d6
\n for keyword in keywords:
\n self.logger.info(f"\\\\n🚀 \u5f00\u59cb\u91c7\u96c6\u5173\u952e\u8bcd：{keyword}")<\/p>\n
# \u6784\u9020\u641c\u7d22URL（\u62fc\u63a5\u5730\u533a\u7f16\u7801\u548c\u5173\u952e\u8bcd）
\n search_url = (
\n f"https:\/\/we.51job.com\/pc\/search"
\n f"?jobArea={CITY_CODE}&keyword={keyword}"
\n )
\n self.dp.get(search_url)<\/p>\n
# 4. \u83b7\u53d6\u7b2c\u4e00\u9875\u63a5\u53e3\u6570\u636e（\u5bb9\u9519\u5904\u7406）
\n try:
\n # \u7b49\u5f85\u63a5\u53e3\u54cd\u5e94，\u8d85\u65f610\u79d2
\n resp = self.dp.listen.wait(timeout=10)
\n first_data = resp.response.body
\n # \u517c\u5bb9\u63a5\u53e3\u8fd4\u56de\u5b57\u7b26\u4e32\u7684\u60c5\u51b5，\u8f6c\u4e3a\u5b57\u5178
\n if isinstance(first_data, str):
\n first_data = json.loads(first_data)
\n except Exception as e:
\n self.logger.error(f"\u274c \u83b7\u53d6{keyword}\u7b2c\u4e00\u9875\u63a5\u53e3\u6570\u636e\u5931\u8d25：{e}")
\n continue<\/p>\n
# 5. \u63d0\u53d6\u603b\u9875\u6570（\u591a\u5c42\u5bb9\u9519，\u907f\u514d\u6570\u636e\u683c\u5f0f\u5f02\u5e38）
\n total_page = first_data.get("resultbody", {}).get("job", {}).get("totalcount", 1)
\n try:
\n total_page = int(total_page)
\n total_page = max(total_page, 1) # \u786e\u4fdd\u9875\u6570\u22651
\n except (ValueError, TypeError):
\n total_page = 1
\n # \u9650\u5236\u6700\u5927\u7ffb\u9875\u6570
\n actual_max_page = min(total_page, MAX_PAGE_PER_KEYWORD)
\n self.logger.info(f"📖 {keyword} \u5171 {total_page} \u9875\u6570\u636e（\u672c\u6b21\u6700\u591a\u722c\u53d6 {actual_max_page} \u9875）")<\/p>\n
# 6. \u89e3\u6790\u7b2c\u4e00\u9875\u6570\u636e
\n job_list = first_data.get("resultbody", {}).get("job", {}).get("items", [])
\n if not job_list:
\n self.logger.info(f"📭 {keyword} \u65e0\u6570\u636e，\u8df3\u8fc7")
\n continue
\n # \u89e3\u6790\u5e76\u6536\u96c6\u7b2c\u4e00\u9875\u804c\u4f4d
\n page1_jobs = self.parse_jobs(job_list, keyword)
\n all_jobs.extend(page1_jobs)<\/p>\n
# 7. \u7ffb\u9875\u722c\u53d6（\u4ece\u7b2c2\u9875\u5230\u5b9e\u9645\u6700\u5927\u9875）
\n for page in range(2, actual_max_page + 1):
\n try:
\n # \u6eda\u52a8\u5230\u9875\u9762\u5e95\u90e8，\u52a0\u8f7d\u4e0b\u4e00\u9875\u6309\u94ae
\n self.dp.scroll.to_bottom()
\n # \u67e5\u627e\u4e0b\u4e00\u9875\u6309\u94ae（CSS\u9009\u62e9\u5668\u5b9a\u4f4d）
\n next_btn = self.dp.ele('css:button.btn-next', timeout=5)
\n if not next_btn:
\n self.logger.info(f"📄 {keyword} \u5df2\u65e0\u4e0b\u4e00\u9875（\u9884\u671f{total_page}\u9875，\u5b9e\u9645\u722c\u53d6\u5230{page – 1}\u9875）")
\n break<\/p>\n
# \u70b9\u51fb\u4e0b\u4e00\u9875\u6309\u94ae
\n next_btn.click()
\n self.logger.info(f"🔍 \u6b63\u5728\u91c7\u96c6{keyword} \u7b2c{page}\u9875\u7684\u6570\u636e…")
\n # \u7b49\u5f85\u4e0b\u4e00\u9875\u63a5\u53e3\u54cd\u5e94
\n resp = self.dp.listen.wait(timeout=10)
\n data = resp.response.body
\n if isinstance(data, str):
\n data = json.loads(data)<\/p>\n
# \u89e3\u6790\u5f53\u524d\u9875\u804c\u4f4d\u5217\u8868
\n job_list = data.get("resultbody", {}).get("job", {}).get("items", [])
\n if not job_list:
\n self.logger.info(f"📭 {keyword} \u7b2c{page}\u9875\u65e0\u6570\u636e，\u505c\u6b62\u7ffb\u9875")
\n break<\/p>\n
# \u89e3\u6790\u5e76\u6536\u96c6\u5f53\u524d\u9875\u804c\u4f4d
\n page_jobs = self.parse_jobs(job_list, keyword)
\n all_jobs.extend(page_jobs)
\n # \u7ffb\u9875\u540e\u77ed\u4f11\u7720，\u907f\u514d\u8bf7\u6c42\u8fc7\u5feb
\n time.sleep(1.5)<\/p>\n
except Exception as e:
\n self.logger.warning(f"\u26a0\ufe0f {keyword} \u7b2c {page} \u9875\u722c\u53d6\u5f02\u5e38: {e}，\u505c\u6b62\u7ffb\u9875")
\n break<\/p>\n
# 8. \u722c\u53d6\u5b8c\u6210，\u4fdd\u5b58\u6570\u636e\u5230JSON\u6587\u4ef6
\n self.save_data(all_jobs)
\n self.logger.info(f"\\\\n🎉 \u722c\u53d6\u5b8c\u6210！\u5171\u91c7\u96c6\u5230 {len(all_jobs)} \u4e2a\u6709\u6548\u804c\u4f4d\u6570\u636e")<\/p>\n
def save_data(self, all_jobs):
\n """\u5c06\u7ed3\u6784\u5316\u5c97\u4f4d\u6570\u636e\u4fdd\u5b58\u4e3aJSON\u6587\u4ef6（UTF-8\u7f16\u7801，\u683c\u5f0f\u5316\u8f93\u51fa）"""
\n with open("51job_crawled_data.json", "w", encoding="utf-8") as f:
\n json.dump(all_jobs, f, ensure_ascii=False, indent=4)
\n self.logger.info(f"💾 \u6570\u636e\u5df2\u4fdd\u5b58\u5230：51job_crawled_data.json")<\/p>\n
def close(self):
\n """\u722c\u866b\u7ed3\u675f\u540e，\u91ca\u653e\u6d4f\u89c8\u5668\u8d44\u6e90（\u5fc5\u987b\u6267\u884c）"""
\n self.logger.info("🔌 \u5f00\u59cb\u5173\u95ed\u6d4f\u89c8\u5668，\u91ca\u653e\u8d44\u6e90…")
\n self.dp.listen.stop() # \u505c\u6b62\u63a5\u53e3\u76d1\u542c
\n self.dp.quit() # \u5173\u95ed\u6d4f\u89c8\u5668
\n self.logger.info("\u2705 \u6d4f\u89c8\u5668\u5df2\u5173\u95ed，\u8d44\u6e90\u91ca\u653e\u5b8c\u6210")<\/p>\n
# ===================== \u8fd0\u884c\u722c\u866b =====================
\nif __name__ == "__main__":
\n # \u521d\u59cb\u5316\u722c\u866b\u5b9e\u4f8b
\n spider = Job51Spider()
\n try:
\n # \u6267\u884c\u6838\u5fc3\u722c\u53d6\u903b\u8f91
\n spider.crawl()
\n except Exception as e:
\n spider.logger.error(f"\u274c \u722c\u866b\u8fd0\u884c\u5f02\u5e38：{e}")
\n finally:
\n # \u65e0\u8bba\u662f\u5426\u5f02\u5e38，\u90fd\u786e\u4fdd\u6d4f\u89c8\u5668\u5173\u95ed
\n spider.close()<\/p>\n
\u56db\u3001\u6838\u5fc3\u4ee3\u7801\u89e3\u6790<\/h3>\n1. \u81ea\u5b9a\u4e49\u914d\u7f6e\u6a21\u5757（\u53ef\u5feb\u901f\u8c03\u6574）<\/h4>\n\n- JOB_BIG_TYPE：\u5b9a\u4e49\u5c97\u4f4d\u5927\u7c7b\u548c\u7ec6\u5206\u5c97\u4f4d，\u722c\u53d6\u65f6\u4f1a\u81ea\u52a8\u751f\u6210\u6240\u6709\u7ec6\u5206\u5c97\u4f4d\u7684\u641c\u7d22\u5173\u952e\u8bcd，\u65e0\u9700\u624b\u52a8\u7ef4\u62a4；<\/li>\n
- CITY_CODE：\u722c\u53d6\u5730\u533a\u7f16\u7801（040000 = \u4e0a\u6d77，\u53ef\u66ff\u6362\u4e3a\u5317\u4eac \/ \u6df1\u5733\u7b49），\u53ef\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u4ece URL \u4e2d\u63d0\u53d6\u7f16\u7801；<\/li>\n
- MAX_PAGE_PER_KEYWORD：\u9650\u5236\u6bcf\u4e2a\u5173\u952e\u8bcd\u7684\u6700\u5927\u7ffb\u9875\u6570，\u907f\u514d\u722c\u53d6\u8fc7\u591a\u89e6\u53d1\u53cd\u722c\u673a\u5236\u3002<\/li>\n<\/ul>\n
2. \u6570\u636e\u6a21\u578b\u4e0e\u5de5\u5177\u51fd\u6570<\/h4>\n\n- BossItem()：\u7528\u5b57\u5178\u6807\u51c6\u5316\u5c97\u4f4d\u5b57\u6bb5，\u7edf\u4e00\u8f93\u51fa\u683c\u5f0f，\u540e\u7eed\u53ef\u76f4\u63a5\u5bf9\u63a5\u6570\u636e\u5e93 \/ Kafka，\u65e0\u9700\u989d\u5916\u8f6c\u6362；<\/li>\n
- normalize_job()：\u5c06\u539f\u59cb\u5c97\u4f4d\u540d\u79f0\u6807\u51c6\u5316（\u5982 \u201cPython \u5f00\u53d1\u5de5\u7a0b\u5e08\u201d\u2192\u6807\u51c6\u5c97\u4f4d \u201cPython\u201d，\u5927\u7c7b \u201c\u6280\u672f\u5f00\u53d1\u201d），\u4fbf\u4e8e\u540e\u7eed\u5206\u7c7b\u5206\u6790；<\/li>\n
- build_search_keywords()：\u4eceJOB_BIG_TYPE\u4e2d\u63d0\u53d6\u6240\u6709\u7ec6\u5206\u5c97\u4f4d，\u53bb\u91cd\u540e\u751f\u6210\u641c\u7d22\u5173\u952e\u8bcd\u5217\u8868，\u5b9e\u73b0\u81ea\u52a8\u5316\u6279\u91cf\u722c\u53d6\u3002<\/li>\n<\/ul>\n
3. \u722c\u866b\u7c7b\u6838\u5fc3\u903b\u8f91<\/h4>\n（1）\u521d\u59cb\u5316（init）<\/h5>\n\n- \u914d\u7f6e\u65e5\u5fd7：\u5b9e\u65f6\u8f93\u51fa\u722c\u53d6\u8fdb\u5ea6\u3001\u5f02\u5e38\u4fe1\u606f，\u4fbf\u4e8e\u8c03\u8bd5\u548c\u76d1\u63a7；<\/li>\n
- \u521d\u59cb\u5316\u6d4f\u89c8\u5668：ChromiumPage(headless=False) \u542f\u52a8\u5e26\u754c\u9762\u6d4f\u89c8\u5668（\u8c03\u8bd5\u7528），\u4e0a\u7ebf\u53ef\u6539\u4e3aTrue\u542f\u7528\u65e0\u5934\u6a21\u5f0f；<\/li>\n
- \u5f00\u542f\u63a5\u53e3\u76d1\u542c：dp.listen.start("search-pc") \u76d1\u542c 51job \u641c\u7d22\u63a5\u53e3，\u65e0\u9700\u5206\u6790\u5b8c\u6574\u63a5\u53e3 URL，\u6846\u67b6\u81ea\u52a8\u5339\u914d\u5173\u952e\u8bcd\u3002<\/li>\n<\/ul>\n
（2）\u6570\u636e\u89e3\u6790（parse_jobs）<\/h5>\n\n- \u5168\u91cf\u5bb9\u9519：\u4f7f\u7528job.get(key, \u9ed8\u8ba4\u503c)\u66ff\u4ee3\u76f4\u63a5\u53d6\u503c，\u907f\u514d\u5b57\u6bb5\u7f3a\u5931\u5bfc\u81f4\u7a0b\u5e8f\u5d29\u6e83；<\/li>\n
- \u6280\u80fd\u6807\u7b7e\u5904\u7406：\u8df3\u8fc7\u524d 2 \u4e2a\u65e0\u5173\u6807\u7b7e，\u53ea\u4fdd\u7559\u6838\u5fc3\u6280\u80fd\u9700\u6c42；<\/li>\n
- \u53cd\u722c\u4f11\u7720：\u89e3\u6790\u5b8c\u4e00\u9875\u540e\u4f11\u7720 5 \u79d2，\u964d\u4f4e\u88ab\u68c0\u6d4b\u98ce\u9669\u3002<\/li>\n<\/ul>\n
（3）\u6838\u5fc3\u722c\u53d6（crawl）<\/h5>\n\n- \u5173\u952e\u8bcd\u904d\u5386：\u9010\u4e2a\u722c\u53d6\u6240\u6709\u6807\u51c6\u5316\u5173\u952e\u8bcd\u7684\u5c97\u4f4d\u6570\u636e；<\/li>\n
- \u63a5\u53e3\u6570\u636e\u83b7\u53d6：dp.listen.wait(timeout=10) \u7b49\u5f85\u63a5\u53e3\u54cd\u5e94，\u8d85\u65f6 10 \u79d2\u907f\u514d\u65e0\u9650\u7b49\u5f85；<\/li>\n
- \u9875\u6570\u5bb9\u9519：\u63d0\u53d6\u603b\u9875\u6570\u65f6\u505a\u7c7b\u578b\u8f6c\u6362\u548c\u6700\u5c0f\u503c\u9650\u5236，\u907f\u514d\u6570\u636e\u683c\u5f0f\u5f02\u5e38；<\/li>\n
- \u7ffb\u9875\u903b\u8f91：\u901a\u8fc7\u70b9\u51fb \u201c\u4e0b\u4e00\u9875\u201d \u6309\u94ae\u5b9e\u73b0\u7ffb\u9875，\u7ed3\u5408\u6eda\u52a8\u5230\u5e95\u90e8\u786e\u4fdd\u6309\u94ae\u52a0\u8f7d，\u517c\u5bb9 51job \u7684\u61d2\u52a0\u8f7d\u673a\u5236\u3002<\/li>\n<\/ul>\n
（4）\u6570\u636e\u4fdd\u5b58\u4e0e\u8d44\u6e90\u91ca\u653e<\/h5>\n\n- save_data()：\u5c06\u6240\u6709\u5c97\u4f4d\u6570\u636e\u4fdd\u5b58\u4e3a JSON \u6587\u4ef6，ensure_ascii=False \u907f\u514d\u4e2d\u6587\u4e71\u7801，indent=4 \u683c\u5f0f\u5316\u8f93\u51fa\u4fbf\u4e8e\u9605\u8bfb；<\/li>\n
- close()：\u722c\u866b\u7ed3\u675f\u540e\u505c\u6b62\u63a5\u53e3\u76d1\u542c\u3001\u5173\u95ed\u6d4f\u89c8\u5668，\u907f\u514d\u8d44\u6e90\u6cc4\u9732\u3002<\/li>\n<\/ul>\n
\u4e94\u3001\u8fd0\u884c\u8bf4\u660e\u4e0e\u7ed3\u679c\u5c55\u793a<\/h3>\n1. \u8fd0\u884c\u6b65\u9aa4<\/h4>\n
- \u590d\u5236\u4ee3\u7801\u5230\u672c\u5730，\u4fdd\u5b58\u4e3a51job_spider.py；<\/li>\n
- \u4fee\u6539JOB_BIG_TYPE（\u6269\u5c55\u5c97\u4f4d\u7c7b\u578b）\u3001CITY_CODE（\u5207\u6362\u722c\u53d6\u57ce\u5e02）\u3001MAX_PAGE_PER_KEYWORD（\u8c03\u6574\u7ffb\u9875\u6570）；<\/li>\n
- \u7ec8\u7aef\u6267\u884c\u547d\u4ee4： python 51job_spider.py\n <\/li>\n
2. \u8fd0\u884c\u65e5\u5fd7\u793a\u4f8b![\"\"](\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png\")
<\/h4>\n3. \u8f93\u51fa\u6587\u4ef6\u793a\u4f8b（51job_crawled_data.json）<\/h4>\n
![\"\"](\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043523-6989640b0bd26.png\")
<\/p>\n
\u516d\u3001\u6ce8\u610f\u4e8b\u9879\u4e0e\u4f18\u5316\u5efa\u8bae<\/h3>\n1. \u6838\u5fc3\u6ce8\u610f\u4e8b\u9879<\/h4>\n\n- \u53cd\u722c\u673a\u5236\u89c4\u907f：\n
\n- \u5207\u52ff\u5c06MAX_PAGE_PER_KEYWORD\u8bbe\u7f6e\u8fc7\u5927（\u5efa\u8bae\u22645），\u4e14\u4f11\u7720\u65f6\u95f4\u4e0d\u53ef\u5220\u9664 \/ \u51cf\u5c0f；<\/li>\n
- \u907f\u514d\u77ed\u65f6\u95f4\u5185\u91cd\u590d\u8fd0\u884c，\u5efa\u8bae\u95f4\u9694\u226530 \u5206\u949f；<\/li>\n
- \u4e0a\u7ebf\u8fd0\u884c\u65f6\u542f\u7528headless=True，\u51cf\u5c11\u6d4f\u89c8\u5668\u7279\u5f81\u66b4\u9732\u3002<\/li>\n<\/ul>\n<\/li>\n
- \u63a5\u53e3\u76d1\u542c\u5931\u6548：\u82e5search-pc\u5173\u952e\u8bcd\u65e0\u6cd5\u5339\u914d\u63a5\u53e3，\u53ef\u6253\u5f00\u6d4f\u89c8\u5668 F12\u2192\u7f51\u7edc\u2192\u7b5b\u9009 XHR，\u627e\u5230 51job \u641c\u7d22\u63a5\u53e3\u7684 URL \/ \u54cd\u5e94，\u4fee\u6539\u76d1\u542c\u5173\u952e\u8bcd\u3002<\/li>\n
- \u5730\u533a\u7f16\u7801\u83b7\u53d6：\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u590d\u5236 URL \u4e2d\u7684jobArea\u53c2\u6570\u503c（\u5982\u5317\u4eac = 101010100）\u3002<\/li>\n<\/ul>\n
2. \u8fdb\u9636\u4f18\u5316\u5efa\u8bae<\/h4>\n\n- \u96c6\u6210 Kafka：\u5728parse_jobs\u65b9\u6cd5\u4e2d\u6dfb\u52a0 Kafka \u751f\u4ea7\u8005，\u5c06\u89e3\u6790\u540e\u7684\u5c97\u4f4d\u6570\u636e\u6295\u9012\u5230 Kafka \u4e3b\u9898，\u5b9e\u73b0 \u201c\u722c\u53d6\u2192\u6d88\u606f\u7f13\u51b2\u2192\u6d88\u8d39\u5b58\u50a8\u201d \u89e3\u8026；<\/li>\n
- \u6570\u636e\u5165\u5e93：\u7f16\u5199 JSON \u6587\u4ef6\u89e3\u6790\u811a\u672c，\u5c06\u6570\u636e\u5b58\u5165 MySQL\/MongoDB\/Elasticsearch，\u4fbf\u4e8e\u540e\u7eed\u67e5\u8be2\u5206\u6790；<\/li>\n
- \u591a\u7ebf\u7a0b\u722c\u53d6：\u6309\u5173\u952e\u8bcd\u5206\u7ebf\u7a0b\u722c\u53d6（\u9700\u63a7\u5236\u5e76\u53d1\u6570\u22643），\u63d0\u5347\u722c\u53d6\u6548\u7387；<\/li>\n
- \u6570\u636e\u53bb\u91cd：\u57fa\u4e8ejob_id\u6216 \u201c\u5c97\u4f4d\u540d\u79f0 + \u516c\u53f8 + \u85aa\u8d44\u201d \u53bb\u91cd，\u907f\u514d\u91cd\u590d\u6570\u636e；<\/li>\n
- \u90ae\u4ef6\u544a\u8b66：\u6dfb\u52a0\u5f02\u5e38\u90ae\u4ef6\u901a\u77e5，\u722c\u53d6\u5931\u8d25\u65f6\u53ca\u65f6\u63d0\u9192\u3002<\/li>\n<\/ul>\n
\u4e03\u3001\u603b\u7ed3<\/h3>\n
- \u672c\u6b21\u5b9e\u6218\u57fa\u4e8eDrissionPage\u7684\u63a5\u53e3\u76d1\u542c\u7279\u6027，\u907f\u5f00\u4e86 51job \u590d\u6742\u7684\u9875\u9762\u7ed3\u6784，\u76f4\u63a5\u83b7\u53d6\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7a33\u5b9a\u6027\u8fdc\u9ad8\u4e8e\u4f20\u7edf\u9875\u9762\u89e3\u6790\u722c\u866b；<\/li>\n
- \u4ee3\u7801\u8bbe\u8ba1\u4e0a\u517c\u987e \u201c\u6613\u7528\u6027\u201d \u548c \u201c\u5065\u58ee\u6027\u201d：\u81ea\u5b9a\u4e49\u914d\u7f6e\u6a21\u5757\u53ef\u5feb\u901f\u8c03\u6574\u722c\u53d6\u89c4\u5219，\u5168\u91cf\u5bb9\u9519\u5904\u7406\u907f\u514d\u7a0b\u5e8f\u5d29\u6e83，\u5b8c\u5584\u7684\u65e5\u5fd7\u4fbf\u4e8e\u8c03\u8bd5；<\/li>\n
- \u6838\u5fc3\u6d41\u7a0b（\u5173\u952e\u8bcd\u751f\u6210\u2192\u63a5\u53e3\u76d1\u542c\u2192\u6570\u636e\u89e3\u6790\u2192\u7ffb\u9875\u2192\u4fdd\u5b58）\u53ef\u590d\u7528\u81f3\u5176\u4ed6\u62db\u8058\u5e73\u53f0（\u5982 BOSS \u76f4\u8058\u3001\u667a\u8054\u62db\u8058），\u4ec5\u9700\u4fee\u6539\u63a5\u53e3\u5173\u952e\u8bcd\u548c\u6570\u636e\u89e3\u6790\u903b\u8f91；<\/li>\n
- \u6269\u5c55\u65b9\u5411\u4e0a，\u53ef\u96c6\u6210 Kafka\u3001\u6570\u636e\u5e93\u3001\u591a\u7ebf\u7a0b\u7b49，\u9002\u914d\u4f01\u4e1a\u7ea7\u6570\u636e\u722c\u53d6\u573a\u666f\u3002<\/li>\n
\u5982\u679c\u672c\u6587\u5bf9\u4f60\u6709\u5e2e\u52a9，\u6b22\u8fce\u70b9\u8d5e + \u6536\u85cf + \u5173\u6ce8！\u8fd0\u884c\u8fc7\u7a0b\u4e2d\u9047\u5230\u95ee\u9898，\u53ef\u5728\u8bc4\u8bba\u533a\u7559\u8a00，\u6211\u4f1a\u7b2c\u4e00\u65f6\u95f4\u89e3\u7b54～<\/p>\n","protected":false},"excerpt":{"rendered":"
\u4e00\u3001\u524d\u8a00
\n51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO<\/p>\n","protected":false},"author":2,"featured_media":74211,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,190,677],"topic":[],"class_list":["post-74213","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-python","tag-190","tag-677"],"yoast_head":"\n
\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-02-09T04:35:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-02-09T04:35:25+00:00\",\"dateModified\":\"2026-02-09T04:35:25+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/74213.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/74213.html","og_locale":"zh_CN","og_type":"article","og_title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO","og_url":"https:\/\/www.wsisp.com\/helps\/74213.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-02-09T04:35:25+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"6 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/74213.html","url":"https:\/\/www.wsisp.com\/helps\/74213.html","name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-02-09T04:35:25+00:00","dateModified":"2026-02-09T04:35:25+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/74213.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=74213"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/74211"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=74213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=74213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=74213"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=74213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\u4e09\u3001\u5b8c\u6574\u5b9e\u6218\u4ee3\u7801<\/h3>\n
\u76f4\u63a5\u590d\u5236\u4ee5\u4e0b\u4ee3\u7801，\u4fee\u6539\u5c11\u91cf\u914d\u7f6e（\u5982\u5730\u533a\u7f16\u7801\u3001\u5c97\u4f4d\u5927\u7c7b）\u5373\u53ef\u8fd0\u884c：<\/p>\n
import time
\nimport json
\nimport logging
\nfrom DrissionPage import ChromiumPage<\/p>\n
# ===================== \u81ea\u5b9a\u4e49\u914d\u7f6e（\u6839\u636e\u9700\u6c42\u4fee\u6539） =====================
\n# 1. \u5c97\u4f4d\u5927\u7c7b\u4e0e\u7ec6\u5206\u5c97\u4f4d\u914d\u7f6e（\u53ef\u81ea\u884c\u6269\u5c55）
\nJOB_BIG_TYPE = {
\n "\u6280\u672f\u5f00\u53d1": ["Python", "Java", "\u524d\u7aef", "\u540e\u7aef", "\u6d4b\u8bd5", "\u8fd0\u7ef4"],
\n "\u4ea7\u54c1\u8fd0\u8425": ["\u4ea7\u54c1\u7ecf\u7406", "\u8fd0\u8425", "\u65b0\u5a92\u4f53", "\u7535\u5546\u8fd0\u8425"],
\n "\u8bbe\u8ba1": ["UI\u8bbe\u8ba1", "\u5e73\u9762\u8bbe\u8ba1", "\u4ea4\u4e92\u8bbe\u8ba1", "\u89c6\u89c9\u8bbe\u8ba1"]
\n}<\/p>\n
# 2. \u722c\u53d6\u5730\u533a\u7f16\u7801（040000=\u4e0a\u6d77，\u53ef\u66ff\u6362\u4e3a\u5176\u4ed6\u57ce\u5e02：101010100=\u5317\u4eac，101280600=\u6df1\u5733）
\nCITY_CODE = "040000"<\/p>\n
# 3. \u6700\u5927\u7ffb\u9875\u6570（\u907f\u514d\u722c\u53d6\u8fc7\u591a\u89e6\u53d1\u53cd\u722c）
\nMAX_PAGE_PER_KEYWORD = 3<\/p>\n
# ===================== \u6570\u636e\u6a21\u578b\u4e0e\u5de5\u5177\u51fd\u6570 =====================
\ndef BossItem():
\n """\u5b9a\u4e49\u5c97\u4f4d\u6570\u636e\u6a21\u578b（\u66ff\u4ee3Scrapy Item，\u7528\u5b57\u5178\u6807\u51c6\u5316\u5b57\u6bb5）"""
\n return {
\n "job_id": "", # \u5c97\u4f4d\u552f\u4e00ID
\n "\u5c97\u4f4d\u540d\u79f0": "", # \u539f\u59cb\u5c97\u4f4d\u540d
\n "\u6807\u51c6\u5c97\u4f4d": "", # \u6807\u51c6\u5316\u540e\u7684\u5c97\u4f4d\u540d
\n "\u5c97\u4f4d\u5927\u7c7b": "", # \u5c97\u4f4d\u6240\u5c5e\u5927\u7c7b
\n "\u516c\u53f8": "", # \u516c\u53f8\u5168\u79f0
\n "\u516c\u53f8\u9886\u57df": "", # \u516c\u53f8\u6240\u5c5e\u884c\u4e1a
\n "\u89c4\u6a21": "", # \u516c\u53f8\u89c4\u6a21
\n "\u85aa\u8d44": "", # \u85aa\u8d44\u8303\u56f4
\n "\u5b66\u5386\u8981\u6c42": "", # \u5b66\u5386\u8981\u6c42
\n "\u7ecf\u9a8c\u8981\u6c42": "", # \u5de5\u4f5c\u7ecf\u9a8c\u8981\u6c42
\n "\u6280\u80fd\u9700\u6c42": "", # \u5c97\u4f4d\u6280\u80fd\u6807\u7b7e
\n "\u5e02": "", # \u57ce\u5e02
\n "\u533a": "", # \u884c\u653f\u533a
\n "\u5546\u5708": "", # \u5546\u5708
\n "\u7ecf\u5ea6": "", # \u7ecf\u5ea6
\n "\u7eac\u5ea6": "", # \u7eac\u5ea6
\n "\u641c\u7d22\u5173\u952e\u8bcd": "", # \u722c\u53d6\u8be5\u5c97\u4f4d\u7684\u641c\u7d22\u5173\u952e\u8bcd
\n "\u6765\u6e90\u6e20\u9053": "51job", # \u6570\u636e\u6765\u6e90
\n "\u8bbf\u95ee\u5730\u5740": "" # \u5c97\u4f4d\u8be6\u60c5\u9875\u94fe\u63a5
\n }<\/p>\n
def normalize_job(job_name):
\n """\u6807\u51c6\u5316\u5c97\u4f4d\u540d\u79f0，\u5339\u914d\u5927\u7c7b\u548c\u6807\u51c6\u5c97\u4f4d"""
\n for big_type, jobs in JOB_BIG_TYPE.items():
\n for j in jobs:
\n if j in job_name:
\n return big_type, j
\n return "\u5176\u4ed6", "\u5176\u4ed6"<\/p>\n
def build_search_keywords():
\n """\u57fa\u4e8eJOB_BIG_TYPE\u6784\u5efa\u53bb\u91cd\u540e\u7684\u641c\u7d22\u5173\u952e\u8bcd\u5217\u8868"""
\n keywords = []
\n for jobs in JOB_BIG_TYPE.values():
\n keywords.extend(jobs)
\n return list(set(keywords)) # \u53bb\u91cd<\/p>\n
# ===================== \u6838\u5fc3\u722c\u866b\u7c7b =====================
\nclass Job51Spider:
\n def __init__(self):
\n # 1. \u914d\u7f6e\u65e5\u5fd7（\u66ff\u4ee3Scrapy logger，\u5b9e\u65f6\u8f93\u51fa\u722c\u53d6\u8fdb\u5ea6）
\n logging.basicConfig(
\n level=logging.INFO,
\n format='%(asctime)s – %(levelname)s – %(message)s',
\n handlers=[logging.StreamHandler()] # \u8f93\u51fa\u5230\u63a7\u5236\u53f0
\n )
\n self.logger = logging.getLogger(__name__)<\/p>\n
# 2. \u521d\u59cb\u5316\u6d4f\u89c8\u5668（headless=True \u542f\u7528\u65e0\u5934\u6a21\u5f0f，\u65e0\u754c\u9762\u8fd0\u884c）
\n self.dp = ChromiumPage(headless=False) # \u8c03\u8bd5\u65f6\u8bbe\u4e3aFalse，\u4e0a\u7ebf\u8bbe\u4e3aTrue
\n # 3. \u5f00\u542f\u63a5\u53e3\u76d1\u542c，\u76d1\u542c51job\u641c\u7d22\u63a5\u53e3\u6807\u8bc6（search-pc）
\n self.dp.listen.start("search-pc")
\n self.logger.info("\u2705 \u6d4f\u89c8\u5668\u521d\u59cb\u5316\u5b8c\u6210，\u63a5\u53e3\u76d1\u542c\u5df2\u5f00\u542f")<\/p>\n
def parse_jobs(self, job_list, keyword):
\n """
\n \u89e3\u6790\u5355\u9875\u804c\u4f4d\u5217\u8868\u6570\u636e
\n :param job_list: \u63a5\u53e3\u8fd4\u56de\u7684\u5c97\u4f4d\u5217\u8868
\n :param keyword: \u5f53\u524d\u641c\u7d22\u5173\u952e\u8bcd
\n :return: \u7ed3\u6784\u5316\u7684\u5c97\u4f4d\u5b57\u5178\u5217\u8868
\n """
\n job_items = []
\n for job in job_list:
\n try:
\n item = BossItem()
\n job_name = job.get("jobName", "")
\n # \u6807\u51c6\u5316\u5c97\u4f4d\u540d\u79f0
\n big_type, std_job = normalize_job(job_name)
\n # \u89e3\u6790\u5730\u533a\u4fe1\u606f（\u5d4c\u5957\u5b57\u5178\u5bb9\u9519）
\n area = job.get("jobAreaLevelDetail", {})<\/p>\n
# \u586b\u5145\u5c97\u4f4d\u6570\u636e（\u5168\u91cf\u5bb9\u9519，\u907f\u514d\u5b57\u6bb5\u7f3a\u5931\u62a5\u9519）
\n item["job_id"] = job.get("jobId", "")
\n item["\u5c97\u4f4d\u540d\u79f0"] = job_name
\n item["\u6807\u51c6\u5c97\u4f4d"] = std_job
\n item["\u5c97\u4f4d\u5927\u7c7b"] = big_type
\n item["\u516c\u53f8"] = job.get("fullCompanyName", "")
\n item["\u516c\u53f8\u9886\u57df"] = job.get("industryType1Str", "")
\n item["\u89c4\u6a21"] = job.get("companySizeString", "")
\n item["\u85aa\u8d44"] = job.get("provideSalaryString", "")
\n item["\u5b66\u5386\u8981\u6c42"] = job.get("degreeString", "")
\n item["\u7ecf\u9a8c\u8981\u6c42"] = job.get("workYearString", "")
\n # \u63d0\u53d6\u6280\u80fd\u6807\u7b7e（\u8df3\u8fc7\u524d2\u4e2a\u65e0\u5173\u6807\u7b7e）
\n job_tags_slice = job.get("jobTags", [])[2:]
\n item["\u6280\u80fd\u9700\u6c42"] = ",".join(job_tags_slice) if job_tags_slice else "\u6682\u65e0"
\n item["\u5e02"] = area.get("cityString", "")
\n item["\u533a"] = area.get("districtString", "")
\n item["\u5546\u5708"] = job.get("landmarkString", "")
\n item["\u7ecf\u5ea6"] = job.get("lon", "")
\n item["\u7eac\u5ea6"] = job.get("lat", "")
\n item["\u641c\u7d22\u5173\u952e\u8bcd"] = keyword
\n item["\u8bbf\u95ee\u5730\u5740"] = job.get("jobHref", "")<\/p>\n
job_items.append(item)
\n self.logger.info(f"📌 \u89e3\u6790\u5230\u804c\u4f4d：{job_name} – {item['\u516c\u53f8']} – {item['\u85aa\u8d44']}")<\/p>\n
except Exception as e:
\n self.logger.warning(f"\u26a0\ufe0f \u5355\u4e2a\u5c97\u4f4d\u89e3\u6790\u5931\u8d25，\u8df3\u8fc7：{str(e)}")
\n continue<\/p>\n
# \u89e3\u6790\u5b8c\u4e00\u9875\u540e\u4f11\u7720，\u964d\u4f4e\u53cd\u722c\u98ce\u9669
\n time.sleep(5)
\n return job_items<\/p>\n
def crawl(self):
\n """\u6838\u5fc3\u722c\u53d6\u903b\u8f91：\u904d\u5386\u5173\u952e\u8bcd\u2192\u63a5\u53e3\u76d1\u542c\u2192\u7ffb\u9875\u2192\u89e3\u6790\u6570\u636e"""
\n # 1. \u6784\u5efa\u6240\u6709\u641c\u7d22\u5173\u952e\u8bcd
\n keywords = build_search_keywords()
\n self.logger.info(f"📋 \u5171\u751f\u6210 {len(keywords)} \u4e2a\u641c\u7d22\u5173\u952e\u8bcd：{keywords}")<\/p>\n
# 2. \u5b58\u50a8\u6240\u6709\u722c\u53d6\u7684\u804c\u4f4d\u6570\u636e
\n all_jobs = []<\/p>\n
# 3. \u904d\u5386\u6bcf\u4e2a\u5173\u952e\u8bcd\u722c\u53d6
\n for keyword in keywords:
\n self.logger.info(f"\\\\n🚀 \u5f00\u59cb\u91c7\u96c6\u5173\u952e\u8bcd：{keyword}")<\/p>\n
# \u6784\u9020\u641c\u7d22URL（\u62fc\u63a5\u5730\u533a\u7f16\u7801\u548c\u5173\u952e\u8bcd）
\n search_url = (
\n f"https:\/\/we.51job.com\/pc\/search"
\n f"?jobArea={CITY_CODE}&keyword={keyword}"
\n )
\n self.dp.get(search_url)<\/p>\n
# 4. \u83b7\u53d6\u7b2c\u4e00\u9875\u63a5\u53e3\u6570\u636e（\u5bb9\u9519\u5904\u7406）
\n try:
\n # \u7b49\u5f85\u63a5\u53e3\u54cd\u5e94，\u8d85\u65f610\u79d2
\n resp = self.dp.listen.wait(timeout=10)
\n first_data = resp.response.body
\n # \u517c\u5bb9\u63a5\u53e3\u8fd4\u56de\u5b57\u7b26\u4e32\u7684\u60c5\u51b5，\u8f6c\u4e3a\u5b57\u5178
\n if isinstance(first_data, str):
\n first_data = json.loads(first_data)
\n except Exception as e:
\n self.logger.error(f"\u274c \u83b7\u53d6{keyword}\u7b2c\u4e00\u9875\u63a5\u53e3\u6570\u636e\u5931\u8d25：{e}")
\n continue<\/p>\n
# 5. \u63d0\u53d6\u603b\u9875\u6570（\u591a\u5c42\u5bb9\u9519，\u907f\u514d\u6570\u636e\u683c\u5f0f\u5f02\u5e38）
\n total_page = first_data.get("resultbody", {}).get("job", {}).get("totalcount", 1)
\n try:
\n total_page = int(total_page)
\n total_page = max(total_page, 1) # \u786e\u4fdd\u9875\u6570\u22651
\n except (ValueError, TypeError):
\n total_page = 1
\n # \u9650\u5236\u6700\u5927\u7ffb\u9875\u6570
\n actual_max_page = min(total_page, MAX_PAGE_PER_KEYWORD)
\n self.logger.info(f"📖 {keyword} \u5171 {total_page} \u9875\u6570\u636e（\u672c\u6b21\u6700\u591a\u722c\u53d6 {actual_max_page} \u9875）")<\/p>\n
# 6. \u89e3\u6790\u7b2c\u4e00\u9875\u6570\u636e
\n job_list = first_data.get("resultbody", {}).get("job", {}).get("items", [])
\n if not job_list:
\n self.logger.info(f"📭 {keyword} \u65e0\u6570\u636e，\u8df3\u8fc7")
\n continue
\n # \u89e3\u6790\u5e76\u6536\u96c6\u7b2c\u4e00\u9875\u804c\u4f4d
\n page1_jobs = self.parse_jobs(job_list, keyword)
\n all_jobs.extend(page1_jobs)<\/p>\n
# 7. \u7ffb\u9875\u722c\u53d6（\u4ece\u7b2c2\u9875\u5230\u5b9e\u9645\u6700\u5927\u9875）
\n for page in range(2, actual_max_page + 1):
\n try:
\n # \u6eda\u52a8\u5230\u9875\u9762\u5e95\u90e8，\u52a0\u8f7d\u4e0b\u4e00\u9875\u6309\u94ae
\n self.dp.scroll.to_bottom()
\n # \u67e5\u627e\u4e0b\u4e00\u9875\u6309\u94ae（CSS\u9009\u62e9\u5668\u5b9a\u4f4d）
\n next_btn = self.dp.ele('css:button.btn-next', timeout=5)
\n if not next_btn:
\n self.logger.info(f"📄 {keyword} \u5df2\u65e0\u4e0b\u4e00\u9875（\u9884\u671f{total_page}\u9875，\u5b9e\u9645\u722c\u53d6\u5230{page – 1}\u9875）")
\n break<\/p>\n
# \u70b9\u51fb\u4e0b\u4e00\u9875\u6309\u94ae
\n next_btn.click()
\n self.logger.info(f"🔍 \u6b63\u5728\u91c7\u96c6{keyword} \u7b2c{page}\u9875\u7684\u6570\u636e…")
\n # \u7b49\u5f85\u4e0b\u4e00\u9875\u63a5\u53e3\u54cd\u5e94
\n resp = self.dp.listen.wait(timeout=10)
\n data = resp.response.body
\n if isinstance(data, str):
\n data = json.loads(data)<\/p>\n
# \u89e3\u6790\u5f53\u524d\u9875\u804c\u4f4d\u5217\u8868
\n job_list = data.get("resultbody", {}).get("job", {}).get("items", [])
\n if not job_list:
\n self.logger.info(f"📭 {keyword} \u7b2c{page}\u9875\u65e0\u6570\u636e，\u505c\u6b62\u7ffb\u9875")
\n break<\/p>\n
# \u89e3\u6790\u5e76\u6536\u96c6\u5f53\u524d\u9875\u804c\u4f4d
\n page_jobs = self.parse_jobs(job_list, keyword)
\n all_jobs.extend(page_jobs)
\n # \u7ffb\u9875\u540e\u77ed\u4f11\u7720，\u907f\u514d\u8bf7\u6c42\u8fc7\u5feb
\n time.sleep(1.5)<\/p>\n
except Exception as e:
\n self.logger.warning(f"\u26a0\ufe0f {keyword} \u7b2c {page} \u9875\u722c\u53d6\u5f02\u5e38: {e}，\u505c\u6b62\u7ffb\u9875")
\n break<\/p>\n
# 8. \u722c\u53d6\u5b8c\u6210，\u4fdd\u5b58\u6570\u636e\u5230JSON\u6587\u4ef6
\n self.save_data(all_jobs)
\n self.logger.info(f"\\\\n🎉 \u722c\u53d6\u5b8c\u6210！\u5171\u91c7\u96c6\u5230 {len(all_jobs)} \u4e2a\u6709\u6548\u804c\u4f4d\u6570\u636e")<\/p>\n
def save_data(self, all_jobs):
\n """\u5c06\u7ed3\u6784\u5316\u5c97\u4f4d\u6570\u636e\u4fdd\u5b58\u4e3aJSON\u6587\u4ef6（UTF-8\u7f16\u7801，\u683c\u5f0f\u5316\u8f93\u51fa）"""
\n with open("51job_crawled_data.json", "w", encoding="utf-8") as f:
\n json.dump(all_jobs, f, ensure_ascii=False, indent=4)
\n self.logger.info(f"💾 \u6570\u636e\u5df2\u4fdd\u5b58\u5230：51job_crawled_data.json")<\/p>\n
def close(self):
\n """\u722c\u866b\u7ed3\u675f\u540e，\u91ca\u653e\u6d4f\u89c8\u5668\u8d44\u6e90（\u5fc5\u987b\u6267\u884c）"""
\n self.logger.info("🔌 \u5f00\u59cb\u5173\u95ed\u6d4f\u89c8\u5668，\u91ca\u653e\u8d44\u6e90…")
\n self.dp.listen.stop() # \u505c\u6b62\u63a5\u53e3\u76d1\u542c
\n self.dp.quit() # \u5173\u95ed\u6d4f\u89c8\u5668
\n self.logger.info("\u2705 \u6d4f\u89c8\u5668\u5df2\u5173\u95ed，\u8d44\u6e90\u91ca\u653e\u5b8c\u6210")<\/p>\n
# ===================== \u8fd0\u884c\u722c\u866b =====================
\nif __name__ == "__main__":
\n # \u521d\u59cb\u5316\u722c\u866b\u5b9e\u4f8b
\n spider = Job51Spider()
\n try:
\n # \u6267\u884c\u6838\u5fc3\u722c\u53d6\u903b\u8f91
\n spider.crawl()
\n except Exception as e:
\n spider.logger.error(f"\u274c \u722c\u866b\u8fd0\u884c\u5f02\u5e38：{e}")
\n finally:
\n # \u65e0\u8bba\u662f\u5426\u5f02\u5e38，\u90fd\u786e\u4fdd\u6d4f\u89c8\u5668\u5173\u95ed
\n spider.close()<\/p>\n
\u56db\u3001\u6838\u5fc3\u4ee3\u7801\u89e3\u6790<\/h3>\n1. \u81ea\u5b9a\u4e49\u914d\u7f6e\u6a21\u5757（\u53ef\u5feb\u901f\u8c03\u6574）<\/h4>\n\n- JOB_BIG_TYPE：\u5b9a\u4e49\u5c97\u4f4d\u5927\u7c7b\u548c\u7ec6\u5206\u5c97\u4f4d，\u722c\u53d6\u65f6\u4f1a\u81ea\u52a8\u751f\u6210\u6240\u6709\u7ec6\u5206\u5c97\u4f4d\u7684\u641c\u7d22\u5173\u952e\u8bcd，\u65e0\u9700\u624b\u52a8\u7ef4\u62a4；<\/li>\n
- CITY_CODE：\u722c\u53d6\u5730\u533a\u7f16\u7801（040000 = \u4e0a\u6d77，\u53ef\u66ff\u6362\u4e3a\u5317\u4eac \/ \u6df1\u5733\u7b49），\u53ef\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u4ece URL \u4e2d\u63d0\u53d6\u7f16\u7801；<\/li>\n
- MAX_PAGE_PER_KEYWORD：\u9650\u5236\u6bcf\u4e2a\u5173\u952e\u8bcd\u7684\u6700\u5927\u7ffb\u9875\u6570，\u907f\u514d\u722c\u53d6\u8fc7\u591a\u89e6\u53d1\u53cd\u722c\u673a\u5236\u3002<\/li>\n<\/ul>\n
2. \u6570\u636e\u6a21\u578b\u4e0e\u5de5\u5177\u51fd\u6570<\/h4>\n\n- BossItem()：\u7528\u5b57\u5178\u6807\u51c6\u5316\u5c97\u4f4d\u5b57\u6bb5，\u7edf\u4e00\u8f93\u51fa\u683c\u5f0f，\u540e\u7eed\u53ef\u76f4\u63a5\u5bf9\u63a5\u6570\u636e\u5e93 \/ Kafka，\u65e0\u9700\u989d\u5916\u8f6c\u6362；<\/li>\n
- normalize_job()：\u5c06\u539f\u59cb\u5c97\u4f4d\u540d\u79f0\u6807\u51c6\u5316（\u5982 \u201cPython \u5f00\u53d1\u5de5\u7a0b\u5e08\u201d\u2192\u6807\u51c6\u5c97\u4f4d \u201cPython\u201d，\u5927\u7c7b \u201c\u6280\u672f\u5f00\u53d1\u201d），\u4fbf\u4e8e\u540e\u7eed\u5206\u7c7b\u5206\u6790；<\/li>\n
- build_search_keywords()：\u4eceJOB_BIG_TYPE\u4e2d\u63d0\u53d6\u6240\u6709\u7ec6\u5206\u5c97\u4f4d，\u53bb\u91cd\u540e\u751f\u6210\u641c\u7d22\u5173\u952e\u8bcd\u5217\u8868，\u5b9e\u73b0\u81ea\u52a8\u5316\u6279\u91cf\u722c\u53d6\u3002<\/li>\n<\/ul>\n
3. \u722c\u866b\u7c7b\u6838\u5fc3\u903b\u8f91<\/h4>\n（1）\u521d\u59cb\u5316（init）<\/h5>\n\n- \u914d\u7f6e\u65e5\u5fd7：\u5b9e\u65f6\u8f93\u51fa\u722c\u53d6\u8fdb\u5ea6\u3001\u5f02\u5e38\u4fe1\u606f，\u4fbf\u4e8e\u8c03\u8bd5\u548c\u76d1\u63a7；<\/li>\n
- \u521d\u59cb\u5316\u6d4f\u89c8\u5668：ChromiumPage(headless=False) \u542f\u52a8\u5e26\u754c\u9762\u6d4f\u89c8\u5668（\u8c03\u8bd5\u7528），\u4e0a\u7ebf\u53ef\u6539\u4e3aTrue\u542f\u7528\u65e0\u5934\u6a21\u5f0f；<\/li>\n
- \u5f00\u542f\u63a5\u53e3\u76d1\u542c：dp.listen.start("search-pc") \u76d1\u542c 51job \u641c\u7d22\u63a5\u53e3，\u65e0\u9700\u5206\u6790\u5b8c\u6574\u63a5\u53e3 URL，\u6846\u67b6\u81ea\u52a8\u5339\u914d\u5173\u952e\u8bcd\u3002<\/li>\n<\/ul>\n
（2）\u6570\u636e\u89e3\u6790（parse_jobs）<\/h5>\n\n- \u5168\u91cf\u5bb9\u9519：\u4f7f\u7528job.get(key, \u9ed8\u8ba4\u503c)\u66ff\u4ee3\u76f4\u63a5\u53d6\u503c，\u907f\u514d\u5b57\u6bb5\u7f3a\u5931\u5bfc\u81f4\u7a0b\u5e8f\u5d29\u6e83；<\/li>\n
- \u6280\u80fd\u6807\u7b7e\u5904\u7406：\u8df3\u8fc7\u524d 2 \u4e2a\u65e0\u5173\u6807\u7b7e，\u53ea\u4fdd\u7559\u6838\u5fc3\u6280\u80fd\u9700\u6c42；<\/li>\n
- \u53cd\u722c\u4f11\u7720：\u89e3\u6790\u5b8c\u4e00\u9875\u540e\u4f11\u7720 5 \u79d2，\u964d\u4f4e\u88ab\u68c0\u6d4b\u98ce\u9669\u3002<\/li>\n<\/ul>\n
（3）\u6838\u5fc3\u722c\u53d6（crawl）<\/h5>\n\n- \u5173\u952e\u8bcd\u904d\u5386：\u9010\u4e2a\u722c\u53d6\u6240\u6709\u6807\u51c6\u5316\u5173\u952e\u8bcd\u7684\u5c97\u4f4d\u6570\u636e；<\/li>\n
- \u63a5\u53e3\u6570\u636e\u83b7\u53d6：dp.listen.wait(timeout=10) \u7b49\u5f85\u63a5\u53e3\u54cd\u5e94，\u8d85\u65f6 10 \u79d2\u907f\u514d\u65e0\u9650\u7b49\u5f85；<\/li>\n
- \u9875\u6570\u5bb9\u9519：\u63d0\u53d6\u603b\u9875\u6570\u65f6\u505a\u7c7b\u578b\u8f6c\u6362\u548c\u6700\u5c0f\u503c\u9650\u5236，\u907f\u514d\u6570\u636e\u683c\u5f0f\u5f02\u5e38；<\/li>\n
- \u7ffb\u9875\u903b\u8f91：\u901a\u8fc7\u70b9\u51fb \u201c\u4e0b\u4e00\u9875\u201d \u6309\u94ae\u5b9e\u73b0\u7ffb\u9875，\u7ed3\u5408\u6eda\u52a8\u5230\u5e95\u90e8\u786e\u4fdd\u6309\u94ae\u52a0\u8f7d，\u517c\u5bb9 51job \u7684\u61d2\u52a0\u8f7d\u673a\u5236\u3002<\/li>\n<\/ul>\n
（4）\u6570\u636e\u4fdd\u5b58\u4e0e\u8d44\u6e90\u91ca\u653e<\/h5>\n\n- save_data()：\u5c06\u6240\u6709\u5c97\u4f4d\u6570\u636e\u4fdd\u5b58\u4e3a JSON \u6587\u4ef6，ensure_ascii=False \u907f\u514d\u4e2d\u6587\u4e71\u7801，indent=4 \u683c\u5f0f\u5316\u8f93\u51fa\u4fbf\u4e8e\u9605\u8bfb；<\/li>\n
- close()：\u722c\u866b\u7ed3\u675f\u540e\u505c\u6b62\u63a5\u53e3\u76d1\u542c\u3001\u5173\u95ed\u6d4f\u89c8\u5668，\u907f\u514d\u8d44\u6e90\u6cc4\u9732\u3002<\/li>\n<\/ul>\n
\u4e94\u3001\u8fd0\u884c\u8bf4\u660e\u4e0e\u7ed3\u679c\u5c55\u793a<\/h3>\n1. \u8fd0\u884c\u6b65\u9aa4<\/h4>\n
- \u590d\u5236\u4ee3\u7801\u5230\u672c\u5730，\u4fdd\u5b58\u4e3a51job_spider.py；<\/li>\n
- \u4fee\u6539JOB_BIG_TYPE（\u6269\u5c55\u5c97\u4f4d\u7c7b\u578b）\u3001CITY_CODE（\u5207\u6362\u722c\u53d6\u57ce\u5e02）\u3001MAX_PAGE_PER_KEYWORD（\u8c03\u6574\u7ffb\u9875\u6570）；<\/li>\n
- \u7ec8\u7aef\u6267\u884c\u547d\u4ee4： python 51job_spider.py\n <\/li>\n
2. \u8fd0\u884c\u65e5\u5fd7\u793a\u4f8b<\/h4>\n3. \u8f93\u51fa\u6587\u4ef6\u793a\u4f8b（51job_crawled_data.json）<\/h4>\n
<\/p>\n
\u516d\u3001\u6ce8\u610f\u4e8b\u9879\u4e0e\u4f18\u5316\u5efa\u8bae<\/h3>\n1. \u6838\u5fc3\u6ce8\u610f\u4e8b\u9879<\/h4>\n\n- \u53cd\u722c\u673a\u5236\u89c4\u907f：\n
\n- \u5207\u52ff\u5c06MAX_PAGE_PER_KEYWORD\u8bbe\u7f6e\u8fc7\u5927（\u5efa\u8bae\u22645），\u4e14\u4f11\u7720\u65f6\u95f4\u4e0d\u53ef\u5220\u9664 \/ \u51cf\u5c0f；<\/li>\n
- \u907f\u514d\u77ed\u65f6\u95f4\u5185\u91cd\u590d\u8fd0\u884c，\u5efa\u8bae\u95f4\u9694\u226530 \u5206\u949f；<\/li>\n
- \u4e0a\u7ebf\u8fd0\u884c\u65f6\u542f\u7528headless=True，\u51cf\u5c11\u6d4f\u89c8\u5668\u7279\u5f81\u66b4\u9732\u3002<\/li>\n<\/ul>\n<\/li>\n
- \u63a5\u53e3\u76d1\u542c\u5931\u6548：\u82e5search-pc\u5173\u952e\u8bcd\u65e0\u6cd5\u5339\u914d\u63a5\u53e3，\u53ef\u6253\u5f00\u6d4f\u89c8\u5668 F12\u2192\u7f51\u7edc\u2192\u7b5b\u9009 XHR，\u627e\u5230 51job \u641c\u7d22\u63a5\u53e3\u7684 URL \/ \u54cd\u5e94，\u4fee\u6539\u76d1\u542c\u5173\u952e\u8bcd\u3002<\/li>\n
- \u5730\u533a\u7f16\u7801\u83b7\u53d6：\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u590d\u5236 URL \u4e2d\u7684jobArea\u53c2\u6570\u503c（\u5982\u5317\u4eac = 101010100）\u3002<\/li>\n<\/ul>\n
2. \u8fdb\u9636\u4f18\u5316\u5efa\u8bae<\/h4>\n\n- \u96c6\u6210 Kafka：\u5728parse_jobs\u65b9\u6cd5\u4e2d\u6dfb\u52a0 Kafka \u751f\u4ea7\u8005，\u5c06\u89e3\u6790\u540e\u7684\u5c97\u4f4d\u6570\u636e\u6295\u9012\u5230 Kafka \u4e3b\u9898，\u5b9e\u73b0 \u201c\u722c\u53d6\u2192\u6d88\u606f\u7f13\u51b2\u2192\u6d88\u8d39\u5b58\u50a8\u201d \u89e3\u8026；<\/li>\n
- \u6570\u636e\u5165\u5e93：\u7f16\u5199 JSON \u6587\u4ef6\u89e3\u6790\u811a\u672c，\u5c06\u6570\u636e\u5b58\u5165 MySQL\/MongoDB\/Elasticsearch，\u4fbf\u4e8e\u540e\u7eed\u67e5\u8be2\u5206\u6790；<\/li>\n
- \u591a\u7ebf\u7a0b\u722c\u53d6：\u6309\u5173\u952e\u8bcd\u5206\u7ebf\u7a0b\u722c\u53d6（\u9700\u63a7\u5236\u5e76\u53d1\u6570\u22643），\u63d0\u5347\u722c\u53d6\u6548\u7387；<\/li>\n
- \u6570\u636e\u53bb\u91cd：\u57fa\u4e8ejob_id\u6216 \u201c\u5c97\u4f4d\u540d\u79f0 + \u516c\u53f8 + \u85aa\u8d44\u201d \u53bb\u91cd，\u907f\u514d\u91cd\u590d\u6570\u636e；<\/li>\n
- \u90ae\u4ef6\u544a\u8b66：\u6dfb\u52a0\u5f02\u5e38\u90ae\u4ef6\u901a\u77e5，\u722c\u53d6\u5931\u8d25\u65f6\u53ca\u65f6\u63d0\u9192\u3002<\/li>\n<\/ul>\n
\u4e03\u3001\u603b\u7ed3<\/h3>\n
- \u672c\u6b21\u5b9e\u6218\u57fa\u4e8eDrissionPage\u7684\u63a5\u53e3\u76d1\u542c\u7279\u6027，\u907f\u5f00\u4e86 51job \u590d\u6742\u7684\u9875\u9762\u7ed3\u6784，\u76f4\u63a5\u83b7\u53d6\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7a33\u5b9a\u6027\u8fdc\u9ad8\u4e8e\u4f20\u7edf\u9875\u9762\u89e3\u6790\u722c\u866b；<\/li>\n
- \u4ee3\u7801\u8bbe\u8ba1\u4e0a\u517c\u987e \u201c\u6613\u7528\u6027\u201d \u548c \u201c\u5065\u58ee\u6027\u201d：\u81ea\u5b9a\u4e49\u914d\u7f6e\u6a21\u5757\u53ef\u5feb\u901f\u8c03\u6574\u722c\u53d6\u89c4\u5219，\u5168\u91cf\u5bb9\u9519\u5904\u7406\u907f\u514d\u7a0b\u5e8f\u5d29\u6e83，\u5b8c\u5584\u7684\u65e5\u5fd7\u4fbf\u4e8e\u8c03\u8bd5；<\/li>\n
- \u6838\u5fc3\u6d41\u7a0b（\u5173\u952e\u8bcd\u751f\u6210\u2192\u63a5\u53e3\u76d1\u542c\u2192\u6570\u636e\u89e3\u6790\u2192\u7ffb\u9875\u2192\u4fdd\u5b58）\u53ef\u590d\u7528\u81f3\u5176\u4ed6\u62db\u8058\u5e73\u53f0（\u5982 BOSS \u76f4\u8058\u3001\u667a\u8054\u62db\u8058），\u4ec5\u9700\u4fee\u6539\u63a5\u53e3\u5173\u952e\u8bcd\u548c\u6570\u636e\u89e3\u6790\u903b\u8f91；<\/li>\n
- \u6269\u5c55\u65b9\u5411\u4e0a，\u53ef\u96c6\u6210 Kafka\u3001\u6570\u636e\u5e93\u3001\u591a\u7ebf\u7a0b\u7b49，\u9002\u914d\u4f01\u4e1a\u7ea7\u6570\u636e\u722c\u53d6\u573a\u666f\u3002<\/li>\n
\u5982\u679c\u672c\u6587\u5bf9\u4f60\u6709\u5e2e\u52a9，\u6b22\u8fce\u70b9\u8d5e + \u6536\u85cf + \u5173\u6ce8！\u8fd0\u884c\u8fc7\u7a0b\u4e2d\u9047\u5230\u95ee\u9898，\u53ef\u5728\u8bc4\u8bba\u533a\u7559\u8a00，\u6211\u4f1a\u7b2c\u4e00\u65f6\u95f4\u89e3\u7b54～<\/p>\n","protected":false},"excerpt":{"rendered":"
\u4e00\u3001\u524d\u8a00
\n51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO<\/p>\n","protected":false},"author":2,"featured_media":74211,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,190,677],"topic":[],"class_list":["post-74213","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-python","tag-190","tag-677"],"yoast_head":"\n
\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-02-09T04:35:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-02-09T04:35:25+00:00\",\"dateModified\":\"2026-02-09T04:35:25+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/74213.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/74213.html","og_locale":"zh_CN","og_type":"article","og_title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO","og_url":"https:\/\/www.wsisp.com\/helps\/74213.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-02-09T04:35:25+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"6 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/74213.html","url":"https:\/\/www.wsisp.com\/helps\/74213.html","name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-02-09T04:35:25+00:00","dateModified":"2026-02-09T04:35:25+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/74213.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=74213"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/74211"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=74213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=74213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=74213"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=74213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
- \n
- JOB_BIG_TYPE：\u5b9a\u4e49\u5c97\u4f4d\u5927\u7c7b\u548c\u7ec6\u5206\u5c97\u4f4d，\u722c\u53d6\u65f6\u4f1a\u81ea\u52a8\u751f\u6210\u6240\u6709\u7ec6\u5206\u5c97\u4f4d\u7684\u641c\u7d22\u5173\u952e\u8bcd，\u65e0\u9700\u624b\u52a8\u7ef4\u62a4；<\/li>\n
- CITY_CODE：\u722c\u53d6\u5730\u533a\u7f16\u7801（040000 = \u4e0a\u6d77，\u53ef\u66ff\u6362\u4e3a\u5317\u4eac \/ \u6df1\u5733\u7b49），\u53ef\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u4ece URL \u4e2d\u63d0\u53d6\u7f16\u7801；<\/li>\n
- MAX_PAGE_PER_KEYWORD：\u9650\u5236\u6bcf\u4e2a\u5173\u952e\u8bcd\u7684\u6700\u5927\u7ffb\u9875\u6570，\u907f\u514d\u722c\u53d6\u8fc7\u591a\u89e6\u53d1\u53cd\u722c\u673a\u5236\u3002<\/li>\n<\/ul>\n
2. \u6570\u636e\u6a21\u578b\u4e0e\u5de5\u5177\u51fd\u6570<\/h4>\n
- \n
- BossItem()：\u7528\u5b57\u5178\u6807\u51c6\u5316\u5c97\u4f4d\u5b57\u6bb5，\u7edf\u4e00\u8f93\u51fa\u683c\u5f0f，\u540e\u7eed\u53ef\u76f4\u63a5\u5bf9\u63a5\u6570\u636e\u5e93 \/ Kafka，\u65e0\u9700\u989d\u5916\u8f6c\u6362；<\/li>\n
- normalize_job()：\u5c06\u539f\u59cb\u5c97\u4f4d\u540d\u79f0\u6807\u51c6\u5316（\u5982 \u201cPython \u5f00\u53d1\u5de5\u7a0b\u5e08\u201d\u2192\u6807\u51c6\u5c97\u4f4d \u201cPython\u201d，\u5927\u7c7b \u201c\u6280\u672f\u5f00\u53d1\u201d），\u4fbf\u4e8e\u540e\u7eed\u5206\u7c7b\u5206\u6790；<\/li>\n
- build_search_keywords()：\u4eceJOB_BIG_TYPE\u4e2d\u63d0\u53d6\u6240\u6709\u7ec6\u5206\u5c97\u4f4d，\u53bb\u91cd\u540e\u751f\u6210\u641c\u7d22\u5173\u952e\u8bcd\u5217\u8868，\u5b9e\u73b0\u81ea\u52a8\u5316\u6279\u91cf\u722c\u53d6\u3002<\/li>\n<\/ul>\n
3. \u722c\u866b\u7c7b\u6838\u5fc3\u903b\u8f91<\/h4>\n
（1）\u521d\u59cb\u5316（init）<\/h5>\n
- \n
- \u914d\u7f6e\u65e5\u5fd7：\u5b9e\u65f6\u8f93\u51fa\u722c\u53d6\u8fdb\u5ea6\u3001\u5f02\u5e38\u4fe1\u606f，\u4fbf\u4e8e\u8c03\u8bd5\u548c\u76d1\u63a7；<\/li>\n
- \u521d\u59cb\u5316\u6d4f\u89c8\u5668：ChromiumPage(headless=False) \u542f\u52a8\u5e26\u754c\u9762\u6d4f\u89c8\u5668（\u8c03\u8bd5\u7528），\u4e0a\u7ebf\u53ef\u6539\u4e3aTrue\u542f\u7528\u65e0\u5934\u6a21\u5f0f；<\/li>\n
- \u5f00\u542f\u63a5\u53e3\u76d1\u542c：dp.listen.start("search-pc") \u76d1\u542c 51job \u641c\u7d22\u63a5\u53e3，\u65e0\u9700\u5206\u6790\u5b8c\u6574\u63a5\u53e3 URL，\u6846\u67b6\u81ea\u52a8\u5339\u914d\u5173\u952e\u8bcd\u3002<\/li>\n<\/ul>\n
（2）\u6570\u636e\u89e3\u6790（parse_jobs）<\/h5>\n
- \n
- \u5168\u91cf\u5bb9\u9519：\u4f7f\u7528job.get(key, \u9ed8\u8ba4\u503c)\u66ff\u4ee3\u76f4\u63a5\u53d6\u503c，\u907f\u514d\u5b57\u6bb5\u7f3a\u5931\u5bfc\u81f4\u7a0b\u5e8f\u5d29\u6e83；<\/li>\n
- \u6280\u80fd\u6807\u7b7e\u5904\u7406：\u8df3\u8fc7\u524d 2 \u4e2a\u65e0\u5173\u6807\u7b7e，\u53ea\u4fdd\u7559\u6838\u5fc3\u6280\u80fd\u9700\u6c42；<\/li>\n
- \u53cd\u722c\u4f11\u7720：\u89e3\u6790\u5b8c\u4e00\u9875\u540e\u4f11\u7720 5 \u79d2，\u964d\u4f4e\u88ab\u68c0\u6d4b\u98ce\u9669\u3002<\/li>\n<\/ul>\n
（3）\u6838\u5fc3\u722c\u53d6（crawl）<\/h5>\n
- \n
- \u5173\u952e\u8bcd\u904d\u5386：\u9010\u4e2a\u722c\u53d6\u6240\u6709\u6807\u51c6\u5316\u5173\u952e\u8bcd\u7684\u5c97\u4f4d\u6570\u636e；<\/li>\n
- \u63a5\u53e3\u6570\u636e\u83b7\u53d6：dp.listen.wait(timeout=10) \u7b49\u5f85\u63a5\u53e3\u54cd\u5e94，\u8d85\u65f6 10 \u79d2\u907f\u514d\u65e0\u9650\u7b49\u5f85；<\/li>\n
- \u9875\u6570\u5bb9\u9519：\u63d0\u53d6\u603b\u9875\u6570\u65f6\u505a\u7c7b\u578b\u8f6c\u6362\u548c\u6700\u5c0f\u503c\u9650\u5236，\u907f\u514d\u6570\u636e\u683c\u5f0f\u5f02\u5e38；<\/li>\n
- \u7ffb\u9875\u903b\u8f91：\u901a\u8fc7\u70b9\u51fb \u201c\u4e0b\u4e00\u9875\u201d \u6309\u94ae\u5b9e\u73b0\u7ffb\u9875，\u7ed3\u5408\u6eda\u52a8\u5230\u5e95\u90e8\u786e\u4fdd\u6309\u94ae\u52a0\u8f7d，\u517c\u5bb9 51job \u7684\u61d2\u52a0\u8f7d\u673a\u5236\u3002<\/li>\n<\/ul>\n
（4）\u6570\u636e\u4fdd\u5b58\u4e0e\u8d44\u6e90\u91ca\u653e<\/h5>\n
- \n
- save_data()：\u5c06\u6240\u6709\u5c97\u4f4d\u6570\u636e\u4fdd\u5b58\u4e3a JSON \u6587\u4ef6，ensure_ascii=False \u907f\u514d\u4e2d\u6587\u4e71\u7801，indent=4 \u683c\u5f0f\u5316\u8f93\u51fa\u4fbf\u4e8e\u9605\u8bfb；<\/li>\n
- close()：\u722c\u866b\u7ed3\u675f\u540e\u505c\u6b62\u63a5\u53e3\u76d1\u542c\u3001\u5173\u95ed\u6d4f\u89c8\u5668，\u907f\u514d\u8d44\u6e90\u6cc4\u9732\u3002<\/li>\n<\/ul>\n
\u4e94\u3001\u8fd0\u884c\u8bf4\u660e\u4e0e\u7ed3\u679c\u5c55\u793a<\/h3>\n
1. \u8fd0\u884c\u6b65\u9aa4<\/h4>\n
- \u590d\u5236\u4ee3\u7801\u5230\u672c\u5730，\u4fdd\u5b58\u4e3a51job_spider.py；<\/li>\n
- \u4fee\u6539JOB_BIG_TYPE（\u6269\u5c55\u5c97\u4f4d\u7c7b\u578b）\u3001CITY_CODE（\u5207\u6362\u722c\u53d6\u57ce\u5e02）\u3001MAX_PAGE_PER_KEYWORD（\u8c03\u6574\u7ffb\u9875\u6570）；<\/li>\n
- \u7ec8\u7aef\u6267\u884c\u547d\u4ee4： python 51job_spider.py\n <\/li>\n
2. \u8fd0\u884c\u65e5\u5fd7\u793a\u4f8b
<\/h4>\n3. \u8f93\u51fa\u6587\u4ef6\u793a\u4f8b（51job_crawled_data.json）<\/h4>\n
<\/p>\n\u516d\u3001\u6ce8\u610f\u4e8b\u9879\u4e0e\u4f18\u5316\u5efa\u8bae<\/h3>\n
1. \u6838\u5fc3\u6ce8\u610f\u4e8b\u9879<\/h4>\n
- \n
- \u53cd\u722c\u673a\u5236\u89c4\u907f：\n
- \n
- \u5207\u52ff\u5c06MAX_PAGE_PER_KEYWORD\u8bbe\u7f6e\u8fc7\u5927（\u5efa\u8bae\u22645），\u4e14\u4f11\u7720\u65f6\u95f4\u4e0d\u53ef\u5220\u9664 \/ \u51cf\u5c0f；<\/li>\n
- \u907f\u514d\u77ed\u65f6\u95f4\u5185\u91cd\u590d\u8fd0\u884c，\u5efa\u8bae\u95f4\u9694\u226530 \u5206\u949f；<\/li>\n
- \u4e0a\u7ebf\u8fd0\u884c\u65f6\u542f\u7528headless=True，\u51cf\u5c11\u6d4f\u89c8\u5668\u7279\u5f81\u66b4\u9732\u3002<\/li>\n<\/ul>\n<\/li>\n
- \u63a5\u53e3\u76d1\u542c\u5931\u6548：\u82e5search-pc\u5173\u952e\u8bcd\u65e0\u6cd5\u5339\u914d\u63a5\u53e3，\u53ef\u6253\u5f00\u6d4f\u89c8\u5668 F12\u2192\u7f51\u7edc\u2192\u7b5b\u9009 XHR，\u627e\u5230 51job \u641c\u7d22\u63a5\u53e3\u7684 URL \/ \u54cd\u5e94，\u4fee\u6539\u76d1\u542c\u5173\u952e\u8bcd\u3002<\/li>\n
- \u5730\u533a\u7f16\u7801\u83b7\u53d6：\u5728 51job \u5b98\u7f51\u5207\u6362\u57ce\u5e02\u540e，\u590d\u5236 URL \u4e2d\u7684jobArea\u53c2\u6570\u503c（\u5982\u5317\u4eac = 101010100）\u3002<\/li>\n<\/ul>\n
2. \u8fdb\u9636\u4f18\u5316\u5efa\u8bae<\/h4>\n
- \n
- \u96c6\u6210 Kafka：\u5728parse_jobs\u65b9\u6cd5\u4e2d\u6dfb\u52a0 Kafka \u751f\u4ea7\u8005，\u5c06\u89e3\u6790\u540e\u7684\u5c97\u4f4d\u6570\u636e\u6295\u9012\u5230 Kafka \u4e3b\u9898，\u5b9e\u73b0 \u201c\u722c\u53d6\u2192\u6d88\u606f\u7f13\u51b2\u2192\u6d88\u8d39\u5b58\u50a8\u201d \u89e3\u8026；<\/li>\n
- \u6570\u636e\u5165\u5e93：\u7f16\u5199 JSON \u6587\u4ef6\u89e3\u6790\u811a\u672c，\u5c06\u6570\u636e\u5b58\u5165 MySQL\/MongoDB\/Elasticsearch，\u4fbf\u4e8e\u540e\u7eed\u67e5\u8be2\u5206\u6790；<\/li>\n
- \u591a\u7ebf\u7a0b\u722c\u53d6：\u6309\u5173\u952e\u8bcd\u5206\u7ebf\u7a0b\u722c\u53d6（\u9700\u63a7\u5236\u5e76\u53d1\u6570\u22643），\u63d0\u5347\u722c\u53d6\u6548\u7387；<\/li>\n
- \u6570\u636e\u53bb\u91cd：\u57fa\u4e8ejob_id\u6216 \u201c\u5c97\u4f4d\u540d\u79f0 + \u516c\u53f8 + \u85aa\u8d44\u201d \u53bb\u91cd，\u907f\u514d\u91cd\u590d\u6570\u636e；<\/li>\n
- \u90ae\u4ef6\u544a\u8b66：\u6dfb\u52a0\u5f02\u5e38\u90ae\u4ef6\u901a\u77e5，\u722c\u53d6\u5931\u8d25\u65f6\u53ca\u65f6\u63d0\u9192\u3002<\/li>\n<\/ul>\n
\u4e03\u3001\u603b\u7ed3<\/h3>\n
- \u672c\u6b21\u5b9e\u6218\u57fa\u4e8eDrissionPage\u7684\u63a5\u53e3\u76d1\u542c\u7279\u6027，\u907f\u5f00\u4e86 51job \u590d\u6742\u7684\u9875\u9762\u7ed3\u6784，\u76f4\u63a5\u83b7\u53d6\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7a33\u5b9a\u6027\u8fdc\u9ad8\u4e8e\u4f20\u7edf\u9875\u9762\u89e3\u6790\u722c\u866b；<\/li>\n
- \u4ee3\u7801\u8bbe\u8ba1\u4e0a\u517c\u987e \u201c\u6613\u7528\u6027\u201d \u548c \u201c\u5065\u58ee\u6027\u201d：\u81ea\u5b9a\u4e49\u914d\u7f6e\u6a21\u5757\u53ef\u5feb\u901f\u8c03\u6574\u722c\u53d6\u89c4\u5219，\u5168\u91cf\u5bb9\u9519\u5904\u7406\u907f\u514d\u7a0b\u5e8f\u5d29\u6e83，\u5b8c\u5584\u7684\u65e5\u5fd7\u4fbf\u4e8e\u8c03\u8bd5；<\/li>\n
- \u6838\u5fc3\u6d41\u7a0b（\u5173\u952e\u8bcd\u751f\u6210\u2192\u63a5\u53e3\u76d1\u542c\u2192\u6570\u636e\u89e3\u6790\u2192\u7ffb\u9875\u2192\u4fdd\u5b58）\u53ef\u590d\u7528\u81f3\u5176\u4ed6\u62db\u8058\u5e73\u53f0（\u5982 BOSS \u76f4\u8058\u3001\u667a\u8054\u62db\u8058），\u4ec5\u9700\u4fee\u6539\u63a5\u53e3\u5173\u952e\u8bcd\u548c\u6570\u636e\u89e3\u6790\u903b\u8f91；<\/li>\n
- \u6269\u5c55\u65b9\u5411\u4e0a，\u53ef\u96c6\u6210 Kafka\u3001\u6570\u636e\u5e93\u3001\u591a\u7ebf\u7a0b\u7b49，\u9002\u914d\u4f01\u4e1a\u7ea7\u6570\u636e\u722c\u53d6\u573a\u666f\u3002<\/li>\n
\u5982\u679c\u672c\u6587\u5bf9\u4f60\u6709\u5e2e\u52a9，\u6b22\u8fce\u70b9\u8d5e + \u6536\u85cf + \u5173\u6ce8！\u8fd0\u884c\u8fc7\u7a0b\u4e2d\u9047\u5230\u95ee\u9898，\u53ef\u5728\u8bc4\u8bba\u533a\u7559\u8a00，\u6211\u4f1a\u7b2c\u4e00\u65f6\u95f4\u89e3\u7b54～<\/p>\n","protected":false},"excerpt":{"rendered":"
\u4e00\u3001\u524d\u8a00
\n51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO<\/p>\n","protected":false},"author":2,"featured_media":74211,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,190,677],"topic":[],"class_list":["post-74213","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-python","tag-190","tag-677"],"yoast_head":"\n\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/74213.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-02-09T04:35:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/74213.html\",\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-02-09T04:35:25+00:00\",\"dateModified\":\"2026-02-09T04:35:25+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/74213.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/74213.html","og_locale":"zh_CN","og_type":"article","og_title":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u4e00\u3001\u524d\u8a00 51job \u4f5c\u4e3a\u56fd\u5185\u4e3b\u6d41\u7684\u62db\u8058\u5e73\u53f0，\u5176\u5c97\u4f4d\u6570\u636e\u662f\u6c42\u804c\u5206\u6790\u3001\u884c\u4e1a\u8c03\u7814\u7684\u91cd\u8981\u6570\u636e\u6e90\u3002\u4f20\u7edf\u7684\u9875\u9762\u5143\u7d20\u89e3\u6790\u722c\u866b\u6613\u53d7\u9875\u9762\u7ed3\u6784\u53d8\u66f4\u5f71\u54cd，\u4e14\u53cd\u722c\u98ce\u9669\u9ad8；\u672c\u6587\u5c06\u57fa\u4e8eDrissionPage\u6846\u67b6，\u91c7\u7528\u63a5\u53e3\u76d1\u542c\u7684\u65b9\u5f0f\u76f4\u63a5\u83b7\u53d6 51job \u7684\u7ed3\u6784\u5316 JSON \u6570\u636e，\u7ed3\u5408\u300c\u81ea\u52a8\u5173\u952e\u8bcd\u751f\u6210\u3001\u5c97\u4f4d\u6570\u636e\u6807\u51c6\u5316\u3001\u667a\u80fd\u7ffb\u9875\u3001\u53cd\u722c\u4f11\u7720\u300d\u7b49\u7279\u6027，\u5b9e\u73b0 51job \u5c97\u4f4d\u6570\u636e\u7684\u6279\u91cf\u722c\u53d6，\u6700\u7ec8\u8f93\u51fa\u7ed3\u6784\u5316 JSO","og_url":"https:\/\/www.wsisp.com\/helps\/74213.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-02-09T04:35:25+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/02\/20260209043522-6989640a6c680.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"6 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/74213.html","url":"https:\/\/www.wsisp.com\/helps\/74213.html","name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-02-09T04:35:25+00:00","dateModified":"2026-02-09T04:35:25+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/74213.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/74213.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u3010Python \u722c\u866b\u5b9e\u6218\u3011\u57fa\u4e8e DrissionPage \u722c\u53d6 51job \u5168\u91cf\u5c97\u4f4d\u6570\u636e\uff08\u63a5\u53e3\u76d1\u542c + \u81ea\u52a8\u7ffb\u9875 + \u6570\u636e\u6807\u51c6\u5316\uff09"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=74213"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/74213\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/74211"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=74213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=74213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=74213"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=74213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
- \u53cd\u722c\u673a\u5236\u89c4\u907f：\n