{"id":5344,"date":"2026-01-10T19:07:29","date_gmt":"2026-01-10T11:07:29","guid":{"rendered":"https:\/\/code.jishujc.com\/?p=5344"},"modified":"2026-01-10T19:07:29","modified_gmt":"2026-01-10T11:07:29","slug":"%e8%87%aa%e5%8a%a8%e5%8c%96x%e7%ab%99%e8%b5%84%e6%ba%90%e9%87%87%e9%9b%86%e6%96%b9%e6%a1%88%e6%90%ad%e5%bb%ba%ef%bc%9apython%e8%84%9a%e6%9c%ac%e7%bc%96%e5%86%99%e4%b8%8e%e5%ae%9e%e6%88%98%e6%a1%88","status":"publish","type":"post","link":"https:\/\/www.qqjishu.com\/index.php\/2026\/01\/10\/%e8%87%aa%e5%8a%a8%e5%8c%96x%e7%ab%99%e8%b5%84%e6%ba%90%e9%87%87%e9%9b%86%e6%96%b9%e6%a1%88%e6%90%ad%e5%bb%ba%ef%bc%9apython%e8%84%9a%e6%9c%ac%e7%bc%96%e5%86%99%e4%b8%8e%e5%ae%9e%e6%88%98%e6%a1%88\/","title":{"rendered":"\u81ea\u52a8\u5316x\u7ad9\u8d44\u6e90\u91c7\u96c6\u65b9\u6848\u642d\u5efa\uff1aPython\u811a\u672c\u7f16\u5199\u4e0e\u5b9e\u6218\u6848\u4f8b"},"content":{"rendered":"

\u5c06x\u7ad9\u8d44\u6e90\u91c7\u96c6\u4efb\u52a1\u81ea\u52a8\u5316\uff0c\u662f\u63d0\u5347\u6548\u7387\u3001\u91ca\u653e\u4eba\u529b\u7684\u5173\u952e\u4e00\u6b65\u3002\u672c\u6587\u5c06\u624b\u628a\u624b\u5e26\u60a8\u4f7f\u7528Python\u642d\u5efa\u4e00\u4e2a\u81ea\u52a8\u5316\u91c7\u96c6\u65b9\u6848\uff0c\u5e76\u901a\u8fc7\u4e00\u4e2a\u5b9e\u6218\u6848\u4f8b\u8fdb\u884c\u6f14\u793a\u3002<\/p>\n

\u7b2c\u4e00\u90e8\u5206\uff1a\u65b9\u6848\u67b6\u6784\u8bbe\u8ba1<\/strong>
\n\u4e00\u4e2a\u5065\u58ee\u7684\u81ea\u52a8\u5316\u91c7\u96c6\u65b9\u6848\u901a\u5e38\u5305\u542b\u4ee5\u4e0b\u6a21\u5757\uff1a<\/p>\n

    \n
  1. \n

    \u4efb\u52a1\u8c03\u5ea6\u5668<\/strong>\uff1a\u51b3\u5b9a\u4f55\u65f6\u542f\u52a8\u91c7\u96c6\u4efb\u52a1\u3002\u53ef\u4ee5\u4f7f\u7528\u7cfb\u7edf\u7684Cron\uff08Linux\uff09\u6216\u8ba1\u5212\u4efb\u52a1\uff08Windows\uff09\uff0c\u4e5f\u53ef\u4ee5\u4f7f\u7528Python\u7684APScheduler<\/code>\u5e93\u5b9e\u73b0\u66f4\u590d\u6742\u7684\u8c03\u5ea6\u3002<\/p>\n<\/li>\n

  2. \n

    \u6838\u5fc3\u91c7\u96c6\u5668<\/strong>\uff1a\u8d1f\u8d23\u53d1\u9001\u8bf7\u6c42\u3001\u89e3\u6790\u9875\u9762\u3001\u63d0\u53d6\u6570\u636e\u3002\u8fd9\u662f\u65b9\u6848\u7684\u6838\u5fc3\u3002<\/p>\n<\/li>\n

  3. \n

    \u53cd\u722c\u5e94\u5bf9\u6a21\u5757<\/strong>\uff1a\u96c6\u6210\u4ee3\u7406IP\u3001\u968f\u673a\u8bf7\u6c42\u5934\u3001\u8bf7\u6c42\u95f4\u9694\u63a7\u5236\u7b49\u3002<\/p>\n<\/li>\n

  4. \n

    \u6570\u636e\u5904\u7406\u5668<\/strong>\uff1a\u5bf9\u91c7\u96c6\u5230\u7684\u539f\u59cb\u6570\u636e\u8fdb\u884c\u6e05\u6d17\u3001\u53bb\u91cd\u3001\u683c\u5f0f\u5316\u3002<\/p>\n<\/li>\n

  5. \n

    \u5b58\u50a8\u6a21\u5757<\/strong>\uff1a\u5c06\u5904\u7406\u540e\u7684\u6570\u636e\u4fdd\u5b58\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u3002<\/p>\n<\/li>\n

  6. \n

    \u76d1\u63a7\u4e0e\u65e5\u5fd7<\/strong>\uff1a\u8bb0\u5f55\u8fd0\u884c\u72b6\u6001\u548c\u9519\u8bef\u4fe1\u606f\uff0c\u4fbf\u4e8e\u6392\u67e5\u95ee\u9898\u3002<\/p>\n<\/li>\n<\/ol>\n

    \u7b2c\u4e8c\u90e8\u5206\uff1a\u5b9e\u6218\u6848\u4f8b\u2014\u2014\u81ea\u52a8\u5316\u91c7\u96c6\u67d0\u8d44\u8baf\u7f51\u7ad9\u6587\u7ae0<\/strong>
    \n\u76ee\u6807<\/strong>\uff1a\u6bcf\u5929\u5b9a\u65f6\u91c7\u96c6\u67d0\u8d44\u8baf\u7f51\u7ad9\u201c\u79d1\u6280\u201d\u677f\u5757\u7684\u6700\u65b0\u6587\u7ae0\u6807\u9898\u3001\u94fe\u63a5\u548c\u53d1\u5e03\u65e5\u671f\u3002
    \n\u6280\u672f\u9009\u578b<\/strong>\uff1aRequests<\/code>,\u00a0BeautifulSoup<\/code>,\u00a0APScheduler<\/code>,\u00a0SQLite<\/code>\u3002<\/p>\n

    \u6b65\u9aa41\uff1a\u7f16\u5199\u6838\u5fc3\u91c7\u96c6\u51fd\u6570<\/strong><\/p>\n

    \n
    \n
    \n
    \n
    python<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n
    import<\/span> requests\nfrom<\/span> bs4 import<\/span> BeautifulSoup\nimport<\/span> sqlite3\nimport<\/span> time\nimport<\/span> random\n\ndef<\/span> fetch_tech_news<\/span>(<\/span>)<\/span>:<\/span>\n    url =<\/span> \u2018https:<\/span>\/\/<\/span>example-<\/span>news.<\/span>com\/<\/span>tech\u2019\n    headers =<\/span> {<\/span>\u2018User-<\/span>Agent\u2019:<\/span> \u2018\u4f60\u7684\u6d4f\u89c8\u5668UA\u2019}<\/span>\n    try<\/span>:<\/span>\n        resp =<\/span> requests.<\/span>get(<\/span>url,<\/span> headers=<\/span>headers,<\/span> timeout=<\/span>10<\/span>)<\/span>\n        resp.<\/span>raise_for_status(<\/span>)<\/span> # \u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/span>\n        soup =<\/span> BeautifulSoup(<\/span>resp.<\/span>text\uff0c \u2018html.<\/span>parser\u2019)<\/span>\n        news_items =<\/span> soup.<\/span>select(<\/span>\u2018.<\/span>article-<\/span>list<\/span> .<\/span>item\u2019)<\/span> # \u4f7f\u7528CSS\u9009\u62e9\u5668\u5b9a\u4f4d<\/span>\n        data_list =<\/span> [<\/span>]<\/span>\n        for<\/span> item in<\/span> news_items:<\/span>\n            title =<\/span> item.<\/span>select_one(<\/span>\u2018h2 a\u2019)<\/span>.<\/span>text.<\/span>strip(<\/span>)<\/span>\n            link =<\/span> item.<\/span>select_one(<\/span>\u2018h2 a\u2019)<\/span>[<\/span>\u2018href\u2019]<\/span>\n            date =<\/span> item.<\/span>select_one(<\/span>\u2018.<\/span>date\u2019)<\/span>.<\/span>text.<\/span>strip(<\/span>)<\/span>\n            data_list.<\/span>append(<\/span>(<\/span>title\uff0c link\uff0c date)<\/span>)<\/span>\n        save_to_db(<\/span>data_list)<\/span>\n        print<\/span>(<\/span>f\u201c\u6210\u529f\u91c7\u96c6{<\/span>len<\/span>(<\/span>data_list)<\/span>}<\/span>\u6761\u6570\u636e\u3002\u201d)<\/span>\n    except<\/span> Exception as<\/span> e:<\/span>\n        print<\/span>(<\/span>f\u201c\u91c7\u96c6\u5931\u8d25:<\/span> {<\/span>e}<\/span>\u201d)<\/span>\n    time.<\/span>sleep(<\/span>random.<\/span>uniform(<\/span>1<\/span>\uff0c 3<\/span>)<\/span>)<\/span> # \u793c\u8c8c\u6027\u5ef6\u65f6<\/span><\/pre>\n<\/div>\n
    \u6b65\u9aa42\uff1a\u7f16\u5199\u6570\u636e\u5b58\u50a8\u51fd\u6570<\/strong><\/p>\n
    \n
    \n
    \n
    \n
    python<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n
    def<\/span> save_to_db<\/span>(<\/span>data_list)<\/span>:<\/span>\n    conn =<\/span> sqlite3.<\/span>connect(<\/span>\u2018news.<\/span>db\u2019)<\/span>\n    c =<\/span> conn.<\/span>cursor(<\/span>)<\/span>\n    c.<\/span>execute(<\/span>\u2018\u2018\u2018CREATE TABLE IF NOT EXISTS tech_news\n                 (<\/span>id<\/span> INTEGER PRIMARY KEY\uff0c title TEXT\uff0c link TEXT UNIQUE\uff0c date TEXT)<\/span>\u2019\u2019\u2019)<\/span>\n    for<\/span> data in<\/span> data_list:<\/span>\n        try<\/span>:<\/span>\n            c.<\/span>execute(<\/span>\u201cINSERT OR IGNORE INTO tech_news (<\/span>title\uff0c link\uff0c date)<\/span> VALUES (<\/span>?,<\/span> ?,<\/span> ?)<\/span>\u201d\uff0c data)<\/span>\n        except<\/span> sqlite3.<\/span>Error as<\/span> e:<\/span>\n            print<\/span>(<\/span>f\u201c\u63d2\u5165\u6570\u636e\u5931\u8d25:<\/span> {<\/span>e}<\/span>\u201d)<\/span>\n    conn.<\/span>commit(<\/span>)<\/span>\n    conn.<\/span>close(<\/span>)<\/span><\/pre>\n<\/div>\n
    \u6b65\u9aa43\uff1a\u4f7f\u7528APScheduler\u8bbe\u7f6e\u5b9a\u65f6\u4efb\u52a1<\/strong><\/p>\n
    \n
    \n
    \n
    \n
    python<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n
    from<\/span> apscheduler.<\/span>schedulers.<\/span>blocking import<\/span> BlockingScheduler\nscheduler =<\/span> BlockingScheduler(<\/span>)<\/span>\n# \u6bcf\u5929\u4e0a\u53489\u70b9\u548c\u4e0b\u53485\u70b9\u5404\u6267\u884c\u4e00\u6b21<\/span>\nscheduler.<\/span>add_job(<\/span>fetch_tech_news\uff0c \u2018cron\u2019\uff0c hour=<\/span>\u20189<\/span>,<\/span>17<\/span>\u2019)<\/span>\nprint<\/span>(<\/span>\u2018\u81ea\u52a8\u5316\u91c7\u96c6\u4efb\u52a1\u5df2\u542f\u52a8\uff0c\u6309 Ctrl+<\/span>C \u9000\u51fa\u3002\u2019)<\/span>\ntry<\/span>:<\/span>\n    scheduler.<\/span>start(<\/span>)<\/span>\nexcept<\/span> (<\/span>KeyboardInterrupt\uff0c SystemExit)<\/span>:<\/span>\n    pass<\/span><\/pre>\n<\/div>\n
    \u65b9\u6848\u4f18\u5316\u4e0e\u6269\u5c55\uff1a<\/strong><\/p>\n