{"id":53655,"date":"2025-08-12T14:49:44","date_gmt":"2025-08-12T06:49:44","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/53655.html"},"modified":"2025-08-12T14:49:44","modified_gmt":"2025-08-12T06:49:44","slug":"%e4%bd%bf%e7%94%a8reqwestselect%e5%ae%9e%e7%8e%b0%e7%ae%80%e5%8d%95%e7%bd%91%e9%a1%b5%e7%88%ac%e8%99%ab","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/53655.html","title":{"rendered":"\u4f7f\u7528reqwest+select\u5b9e\u73b0\u7b80\u5355\u7f51\u9875\u722c\u866b"},"content":{"rendered":"

\u8fd9\u7bc7\u6587\u7ae0\u662f\u4e00\u4e2a\u7b80\u5355\u7684Rust\u722c\u866b\u793a\u4f8b，\u6211\u5c06\u722c\u53d6\u8be5\u7f51\u7ad9\u7684\u56fe\u4e66\u4fe1\u606f，\u5305\u62ec\u4e66\u540d\u3001\u4ef7\u683c\u548c\u5e93\u5b58\u72b6\u6001\u3002\u4f7f\u7528reqwest\u5e93\u53d1\u9001HTTP\u8bf7\u6c42，select\u5e93\u89e3\u6790HTML\u5185\u5bb9\u3002\u4ee3\u7801\u7ed3\u6784\u6e05\u6670，\u5305\u542b\u9519\u8bef\u5904\u7406\u548c\u57fa\u672c\u7684\u6570\u636e\u63d0\u53d6\u903b\u8f91\u3002<\/p>\n

\u9002\u5408Rust\u722c\u866b\u65b0\u624b\u5b66\u4e60\u7f51\u7edc\u8bf7\u6c42\u3001HTML\u89e3\u6790\u548c\u6570\u636e\u63d0\u53d6\u7684\u57fa\u672c\u6d41\u7a0b\u3002\u901a\u8fc7\u8fd9\u4e2a\u793a\u4f8b，\u4f60\u53ef\u4ee5\u4e86\u89e3\u5982\u4f55\u6784\u5efa\u4e00\u4e2a\u5b8c\u6574\u7684\u722c\u866b\u5de5\u4f5c\u6d41\u3002<\/p>\n

\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\"<\/p>\n

\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u3001\u6280\u672f\u6210\u719f\u4e14\u6613\u4e8e\u7406\u89e3\u7684 Rust \u722c\u866b\u6559\u7a0b\u3002\u6211\u4eec\u5c06\u521b\u5efa\u4e00\u4e2a\u722c\u53d6\u56fe\u4e66\u4fe1\u606f（\u6807\u9898\u3001\u4ef7\u683c）\u7684\u722c\u866b，\u76ee\u6807\u7f51\u7ad9\u662f\u4e13\u4e3a\u722c\u866b\u7ec3\u4e60\u8bbe\u8ba1\u7684 books.toscrape.com\u3002<\/p>\n

\u9879\u76ee\u51c6\u5907<\/h4>\n

1\u3001\u521b\u5efa\u65b0\u9879\u76ee：<\/p>\n

cargo new book_scraper
\ncd<\/span> book_scraper<\/p>\n

2\u3001\u6dfb\u52a0\u4f9d\u8d56 (Cargo.toml)：<\/p>\n

[dependencies]
\nreqwest = { version = "0.11", features = ["blocking"] } # \u540c\u6b65HTTP\u5ba2\u6237\u7aef
\nscraper = "0.13" # HTML\u89e3\u6790\u5e93
\nselect = "0.5" # CSS\u9009\u62e9\u5668\u5e93
\nanyhow = "1.0" # \u7b80\u5316\u9519\u8bef\u5904\u7406<\/p>\n

\u5b8c\u6574\u4ee3\u7801 (src\/main.rs)<\/h4>\n

use<\/span> anyhow::<\/span><\/span>{<\/span>Context<\/span>,<\/span> Result<\/span>}<\/span>;<\/span>
\nuse<\/span> select::<\/span>document::<\/span><\/span>Document<\/span>;<\/span>
\nuse<\/span> select::<\/span>predicate::<\/span><\/span>{<\/span>Class<\/span>,<\/span> Name<\/span>}<\/span>;<\/span><\/p>\n

fn<\/span> main<\/span>(<\/span>)<\/span> -><\/span> Result<\/span><<\/span>(<\/span>)<\/span>><\/span> {<\/span>
\n \/\/ \u76ee\u6807\u7f51\u7ad9<\/span>
\n let<\/span> url =<\/span> "http:\/\/books.toscrape.com\/"<\/span>;<\/span><\/p>\n

\/\/ \u53d1\u9001HTTP GET\u8bf7\u6c42<\/span>
\n let<\/span> response =<\/span> reqwest::<\/span>blocking::<\/span><\/span>get<\/span>(<\/span>url)<\/span>
\n .<\/span>with_context<\/span>(<\/span>|<\/span>|<\/span><\/span> format!<\/span>(<\/span>"Failed to fetch {}"<\/span>,<\/span> url)<\/span>)<\/span>?<\/span>;<\/span><\/p>\n

\/\/ \u786e\u4fdd\u8bf7\u6c42\u6210\u529f<\/span>
\n if<\/span> !<\/span>response.<\/span>status<\/span>(<\/span>)<\/span>.<\/span>is_success<\/span>(<\/span>)<\/span> {<\/span>
\n anyhow::<\/span><\/span>bail!<\/span>(<\/span>"Request failed with status: {}"<\/span>,<\/span> response.<\/span>status<\/span>(<\/span>)<\/span>)<\/span>;<\/span>
\n }<\/span><\/p>\n

\/\/ \u8bfb\u53d6HTML\u5185\u5bb9<\/span>
\n let<\/span> html_content =<\/span> response.<\/span>text<\/span>(<\/span>)<\/span>
\n .<\/span>with_context<\/span>(<\/span>|<\/span>|<\/span><\/span> "Failed to read response body"<\/span>)<\/span>?<\/span>;<\/span><\/p>\n

\/\/ \u89e3\u6790HTML\u6587\u6863<\/span>
\n let<\/span> document =<\/span> Document<\/span>::<\/span>from<\/span>(<\/span>html_content.<\/span>as_str<\/span>(<\/span>)<\/span>)<\/span>;<\/span><\/p>\n

println!<\/span>(<\/span>"\u5f00\u59cb\u722c\u53d6: {}"<\/span>,<\/span> url)<\/span>;<\/span>
\n println!<\/span>(<\/span>"{:-^50}"<\/span>,<\/span> "\u56fe\u4e66\u5217\u8868"<\/span>)<\/span>;<\/span><\/p>\n

\/\/ \u67e5\u627e\u6240\u6709\u56fe\u4e66\u6761\u76ee<\/span>
\n for<\/span> book in<\/span> document.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"product_pod"<\/span>)<\/span>)<\/span> {<\/span>
\n \/\/ \u63d0\u53d6\u6807\u9898<\/span>
\n let<\/span> title =<\/span> book.<\/span>find<\/span>(<\/span>Name<\/span>(<\/span>"h3"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>
\n .<\/span>and_then<\/span>(<\/span>|<\/span>h3|<\/span><\/span> h3.<\/span>find<\/span>(<\/span>Name<\/span>(<\/span>"a"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>)<\/span>
\n .<\/span>map<\/span>(<\/span>|<\/span>a|<\/span><\/span> a.<\/span>text<\/span>(<\/span>)<\/span>)<\/span>
\n .<\/span>unwrap_or_else<\/span>(<\/span>|<\/span>|<\/span><\/span> "\u672a\u77e5\u6807\u9898"<\/span>.<\/span>to_string<\/span>(<\/span>)<\/span>)<\/span>;<\/span><\/p>\n

\/\/ \u63d0\u53d6\u4ef7\u683c<\/span>
\n let<\/span> price =<\/span> book.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"price_color"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>
\n .<\/span>map<\/span>(<\/span>|<\/span>p|<\/span><\/span> p.<\/span>text<\/span>(<\/span>)<\/span>)<\/span>
\n .<\/span>unwrap_or_else<\/span>(<\/span>|<\/span>|<\/span><\/span> "\u672a\u77e5\u4ef7\u683c"<\/span>.<\/span>to_string<\/span>(<\/span>)<\/span>)<\/span>;<\/span><\/p>\n

\/\/ \u63d0\u53d6\u5e93\u5b58\u72b6\u6001<\/span>
\n let<\/span> stock =<\/span> book.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"instock"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>
\n .<\/span>map<\/span>(<\/span>|<\/span>s|<\/span><\/span> s.<\/span>text<\/span>(<\/span>)<\/span>.<\/span>trim<\/span>(<\/span>)<\/span>.<\/span>to_string<\/span>(<\/span>)<\/span>)<\/span>
\n .<\/span>unwrap_or_else<\/span>(<\/span>|<\/span>|<\/span><\/span> "\u672a\u77e5\u5e93\u5b58"<\/span>.<\/span>to_string<\/span>(<\/span>)<\/span>)<\/span>;<\/span><\/p>\n

println!<\/span>(<\/span>"\u4e66\u540d: {}"<\/span>,<\/span> title)<\/span>;<\/span>
\n println!<\/span>(<\/span>"\u4ef7\u683c: {}"<\/span>,<\/span> price)<\/span>;<\/span>
\n println!<\/span>(<\/span>"\u5e93\u5b58: {}"<\/span>,<\/span> stock)<\/span>;<\/span>
\n println!<\/span>(<\/span>"{}"<\/span>,<\/span> "-"<\/span>.<\/span>repeat<\/span>(<\/span>40<\/span>)<\/span>)<\/span>;<\/span>
\n }<\/span><\/p>\n

println!<\/span>(<\/span>"\u722c\u53d6\u5b8c\u6210！\u5171\u627e\u5230 {} \u672c\u4e66"<\/span>,<\/span> document.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"product_pod"<\/span>)<\/span>)<\/span>.<\/span>count<\/span>(<\/span>)<\/span>)<\/span>;<\/span>
\n Ok<\/span>(<\/span>(<\/span>)<\/span>)<\/span>
\n}<\/span><\/p>\n

\u4ee3\u7801\u89e3\u6790<\/h4>\n

1\u3001HTTP\u8bf7\u6c42 (reqwest):<\/p>\n

let<\/span> response =<\/span> reqwest::<\/span>blocking::<\/span><\/span>get<\/span>(<\/span>url)<\/span>?<\/span>;<\/span><\/p>\n

\u4f7f\u7528\u540c\u6b65\u65b9\u5f0f\u83b7\u53d6\u7f51\u9875\u5185\u5bb9，\u9002\u5408\u7b80\u5355\u722c\u866b<\/p>\n

2\u3001\u9519\u8bef\u5904\u7406 (anyhow):<\/p>\n

.<\/span>with_context<\/span>(<\/span>|<\/span>|<\/span><\/span> "\u9519\u8bef\u63cf\u8ff0"<\/span>)<\/span>?<\/span>;<\/span><\/p>\n

\u63d0\u4f9b\u53cb\u597d\u7684\u9519\u8bef\u4fe1\u606f，\u81ea\u52a8\u5904\u7406\u9519\u8bef\u4f20\u64ad<\/p>\n

3\u3001HTML\u89e3\u6790 (select):<\/p>\n

let<\/span> document =<\/span> Document<\/span>::<\/span>from<\/span>(<\/span>html_content.<\/span>as_str<\/span>(<\/span>)<\/span>)<\/span>;<\/span><\/p>\n

\u5c06HTML\u5185\u5bb9\u52a0\u8f7d\u5230\u53ef\u67e5\u8be2\u7684\u6587\u6863\u7ed3\u6784\u4e2d<\/p>\n

4\u3001\u5143\u7d20\u67e5\u627e:<\/p>\n

document.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"product_pod"<\/span>)<\/span>)<\/span><\/p>\n

\u4f7f\u7528CSS\u9009\u62e9\u5668\u67e5\u627e\u56fe\u4e66\u5bb9\u5668<\/p>\n

5\u3001\u6570\u636e\u63d0\u53d6:<\/p>\n

book.<\/span>find<\/span>(<\/span>Name<\/span>(<\/span>"h3"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>.<\/span>map<\/span>(<\/span>|<\/span>h3|<\/span><\/span> h3.<\/span>text<\/span>(<\/span>)<\/span>)<\/span><\/p>\n

\u94fe\u5f0f\u8c03\u7528\u5b89\u5168\u63d0\u53d6\u5143\u7d20\u6587\u672c\u5185\u5bb9<\/p>\n

\u8fd0\u884c\u7ed3\u679c\u793a\u4f8b<\/h4>\n

\u5f00\u59cb\u722c\u53d6: http:\/\/books.toscrape.com\/
\n——————\u56fe\u4e66\u5217\u8868——————
\n\u4e66\u540d: A Light in the Attic
\n\u4ef7\u683c: \u00a351.77
\n\u5e93\u5b58: In stock
\n—————————————-
\n\u4e66\u540d: Tipping the Velvet
\n\u4ef7\u683c: \u00a353.74
\n\u5e93\u5b58: In stock
\n—————————————-
\n… (\u5176\u4ed6\u56fe\u4e66) …
\n\u4e66\u540d: The Black Maria
\n\u4ef7\u683c: \u00a322.60
\n\u5e93\u5b58: In stock
\n—————————————-
\n\u722c\u53d6\u5b8c\u6210！\u5171\u627e\u5230 20 \u672c\u4e66<\/p>\n

\u8fdb\u9636\u529f\u80fd\u6dfb\u52a0<\/h4>\n

1\u3001\u4fdd\u5b58\u5230CSV\u6587\u4ef6<\/h5>\n

\u6dfb\u52a0\u4f9d\u8d56：<\/p>\n

csv = "1.1"<\/p>\n

\u4fee\u6539\u4ee3\u7801：<\/p>\n

use<\/span> csv::<\/span><\/span>Writer<\/span>;<\/span><\/p>\n

\/\/ \u5728main\u51fd\u6570\u5f00\u5934\u6dfb\u52a0:<\/span>
\nlet<\/span> mut<\/span> wtr =<\/span> Writer<\/span>::<\/span>from_path<\/span>(<\/span>"books.csv"<\/span>)<\/span>?<\/span>;<\/span>
\nwtr.<\/span>write_record<\/span>(<\/span>&<\/span>[<\/span>"\u4e66\u540d"<\/span>,<\/span> "\u4ef7\u683c"<\/span>,<\/span> "\u5e93\u5b58"<\/span>]<\/span>)<\/span>?<\/span>;<\/span><\/p>\n

\/\/ \u5728\u5faa\u73af\u5185\u66ff\u6362\u6253\u5370\u8bed\u53e5\u4e3a:<\/span>
\nwtr.<\/span>write_record<\/span>(<\/span>&<\/span>[<\/span>&<\/span>title,<\/span> &<\/span>price,<\/span> &<\/span>stock]<\/span>)<\/span>?<\/span>;<\/span><\/p>\n

\/\/ \u5728main\u51fd\u6570\u7ed3\u5c3e\u6dfb\u52a0:<\/span>
\nwtr.<\/span>flush<\/span>(<\/span>)<\/span>?<\/span>;<\/span>
\nprintln!<\/span>(<\/span>"\u6570\u636e\u5df2\u4fdd\u5b58\u5230 books.csv"<\/span>)<\/span>;<\/span><\/p>\n

2\u3001\u81ea\u52a8\u7ffb\u9875<\/h5>\n

let<\/span> mut<\/span> page =<\/span> 1<\/span>;<\/span>
\nlet<\/span> mut<\/span> total_books =<\/span> 0<\/span>;<\/span><\/p>\n

loop<\/span> {<\/span>
\n let<\/span> url =<\/span> format!<\/span>(<\/span>"http:\/\/books.toscrape.com\/catalogue\/page-{}.html"<\/span>,<\/span> page)<\/span>;<\/span><\/p>\n

\/\/ …\u722c\u53d6\u903b\u8f91…<\/span><\/p>\n

\/\/ \u68c0\u67e5\u662f\u5426\u6709\u4e0b\u4e00\u9875<\/span>
\n if<\/span> document.<\/span>find<\/span>(<\/span>Class<\/span>(<\/span>"next"<\/span>)<\/span>)<\/span>.<\/span>next<\/span>(<\/span>)<\/span>.<\/span>is_none<\/span>(<\/span>)<\/span> {<\/span>
\n break<\/span>;<\/span>
\n }<\/span><\/p>\n

page +=<\/span> 1<\/span>;<\/span>
\n \/\/ \u6dfb\u52a0\u5ef6\u65f6\u9632\u6b62\u8bf7\u6c42\u8fc7\u5feb<\/span>
\n std::<\/span>thread::<\/span><\/span>sleep<\/span>(<\/span>std::<\/span>time::<\/span><\/span>Duration<\/span>::<\/span>from_secs<\/span>(<\/span>1<\/span>)<\/span>)<\/span>;<\/span>
\n}<\/span><\/p>\n

\u6ce8\u610f\u4e8b\u9879<\/h4>\n

1\u3001\u5c0a\u91cd\u7f51\u7ad9\u89c4\u5219:<\/p>\n