{"id":1166530,"date":"2025-01-15T15:33:18","date_gmt":"2025-01-15T07:33:18","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1166530.html"},"modified":"2025-01-15T15:33:21","modified_gmt":"2025-01-15T07:33:21","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e6%96%b0%e6%b5%aa%e6%96%b0%e9%97%bb","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1166530.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb"},"content":{"rendered":"

\"python\u5982\u4f55\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\"<\/p>\n

Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6\u3002<\/strong> \u5176\u4e2d\uff0c\u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u5e93\u662f\u6700\u5e38\u7528\u7684\u65b9\u5f0f\uff0c\u56e0\u4e3a\u5b83\u4eec\u7b80\u5355\u6613\u7528\u4e14\u529f\u80fd\u5f3a\u5927\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u5982\u4f55\u4f7f\u7528requests\u548cBeautifulSoup\u5e93\u6765\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n
    \n
  1. \n

    \u5b89\u88c5requests\u5e93<\/strong><\/p>\n<\/p>\n

    \u9996\u5148\uff0c\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86requests\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

    pip install requests<\/p>\n
    <\/code><\/pre>\n<\/p>\n<\/li>\n
  2. \n
    \u53d1\u9001HTTP\u8bf7\u6c42<\/strong><\/p>\n<\/p>\n
    \u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u7f51\u9875\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
    import requests<\/p>\n
    url = 'https:\/\/news.sina.com.cn\/'<\/p>\n
    response = requests.get(url)<\/p>\n
    if response.status_code == 200:<\/p>\n
        print("Successfully fetched the webpage")<\/p>\n
        content = response.text<\/p>\n
        print(content)<\/p>\n
    else:<\/p>\n
        print("FAI<\/a>led to fetch the webpage")<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u4ee5\u4e0a\u4ee3\u7801\u5c06\u7f51\u9875\u5185\u5bb9\u5b58\u50a8\u5728content<\/code>\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n
    \u4e8c\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n
      \n
    1. \n
      \u5b89\u88c5BeautifulSoup\u5e93<\/strong><\/p>\n<\/p>\n
      \u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86BeautifulSoup\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
      pip install beautifulsoup4<\/p>\n
      <\/code><\/pre>\n<\/p>\n<\/li>\n
    2. \n
      \u89e3\u6790HTML\u9875\u9762<\/strong><\/p>\n<\/p>\n
      \u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790\u83b7\u53d6\u5230\u7684HTML\u9875\u9762\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
      from bs4 import BeautifulSoup<\/p>\n
      soup = BeautifulSoup(content, 'html.parser')<\/p>\n
      \u67e5\u627e\u6240\u6709\u65b0\u95fb\u6807\u9898<\/strong><\/h2>\n
      titles = soup.find_all('h2')<\/p>\n
      for title in titles:<\/p>\n
          print(title.get_text())<\/p>\n
      <\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
      \u4e09\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f<\/h3>\n<\/p>\n
        \n
      1. \n
        \u5bfc\u5165\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5757<\/strong><\/p>\n<\/p>\n
        \u4f7f\u7528Python\u7684re\u6a21\u5757\u6765\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
        import re<\/p>\n
        pattern = re.compile(r'<h2.*?>(.*?)<\/h2>', re.S)<\/p>\n
        titles = re.findall(pattern, content)<\/p>\n
        for title in titles:<\/p>\n
            print(title)<\/p>\n
        <\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
        \u56db\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6<\/h3>\n<\/p>\n
          \n
        1. \n
          \u5b89\u88c5Scrapy\u6846\u67b6<\/strong><\/p>\n<\/p>\n
          \u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86Scrapy\u6846\u67b6\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
          pip install scrapy<\/p>\n
          <\/code><\/pre>\n<\/p>\n<\/li>\n
        2. \n
          \u521b\u5efaScrapy\u9879\u76ee<\/strong><\/p>\n<\/p>\n
          \u521b\u5efa\u4e00\u4e2a\u65b0\u7684Scrapy\u9879\u76ee\uff0c\u5e76\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          scrapy startproject sinanews<\/p>\n
          cd sinanews<\/p>\n
          scrapy genspider sinanews_spider news.sina.com.cn<\/p>\n
          <\/code><\/pre>\n<\/p>\n<\/li>\n
        3. \n
          \u7f16\u5199\u722c\u866b\u4ee3\u7801<\/strong><\/p>\n<\/p>\n
          \u7f16\u8f91sinanews_spider.py<\/code>\u6587\u4ef6\uff0c\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          import scrapy<\/p>\n
          class SinanewsSpider(scrapy.Spider):<\/p>\n
              name = 'sinanews_spider'<\/p>\n
              allowed_domains = ['news.sina.com.cn']<\/p>\n
              start_urls = ['https:\/\/news.sina.com.cn\/']<\/p>\n
              def parse(self, response):<\/p>\n
                  titles = response.xpath('\/\/h2\/text()').getall()<\/p>\n
                  for title in titles:<\/p>\n
                      yield {'title': title}<\/p>\n
          <\/code><\/pre>\n<\/p>\n<\/li>\n
        4. \n
          \u8fd0\u884c\u722c\u866b<\/strong><\/p>\n<\/p>\n
          \u8fd0\u884c\u722c\u866b\uff0c\u83b7\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u6807\u9898\uff1a<\/p>\n<\/p>\n
          scrapy crawl sinanews_spider<\/p>\n
          <\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n
          \u4ee5\u4e0a\u4ecb\u7ecd\u4e86\u4f7f\u7528requests\u5e93\u3001BeautifulSoup\u5e93\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u548cScrapy\u6846\u67b6\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u57fa\u672c\u65b9\u6cd5\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u6bcf\u4e2a\u65b9\u6cd5\u7684\u5b9e\u73b0\u7ec6\u8282\u548c\u6ce8\u610f\u4e8b\u9879\u3002<\/p>\n<\/p>\n
          \u4e00\u3001\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n
          1. \u5b89\u88c5requests\u5e93<\/h4>\n<\/p>\n
          \u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86requests\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
          pip install requests<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          requests\u5e93\u662f\u4e00\u4e2a\u7b80\u6d01\u800c\u5f3a\u5927\u7684HTTP\u8bf7\u6c42\u5e93\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u7f51\u9875\u722c\u53d6\u4efb\u52a1\u3002<\/p>\n<\/p>\n
          2. \u53d1\u9001HTTP\u8bf7\u6c42<\/h4>\n<\/p>\n
          \u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u7f51\u9875\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          import requests<\/p>\n
          url = 'https:\/\/news.sina.com.cn\/'<\/p>\n
          response = requests.get(url)<\/p>\n
          if response.status_code == 200:<\/p>\n
              print("Successfully fetched the webpage")<\/p>\n
              content = response.text<\/p>\n
              print(content)<\/p>\n
          else:<\/p>\n
              print("Failed to fetch the webpage")<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u9996\u5148\u5bfc\u5165requests\u5e93\uff0c\u7136\u540e\u5b9a\u4e49\u8981\u722c\u53d6\u7684URL\u3002\u4f7f\u7528requests.get()\u65b9\u6cd5\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u68c0\u67e5\u54cd\u5e94\u72b6\u6001\u7801\u662f\u5426\u4e3a200\uff08\u8868\u793a\u8bf7\u6c42\u6210\u529f\uff09\u3002\u5982\u679c\u8bf7\u6c42\u6210\u529f\uff0c\u5c06\u7f51\u9875\u5185\u5bb9\u5b58\u50a8\u5728content\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n
          \u4e8c\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u9875\u9762<\/h3>\n<\/p>\n
          1. \u5b89\u88c5BeautifulSoup\u5e93<\/h4>\n<\/p>\n
          \u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86BeautifulSoup\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
          pip install beautifulsoup4<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          BeautifulSoup\u5e93\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n
          2. \u89e3\u6790HTML\u9875\u9762<\/h4>\n<\/p>\n
          \u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790\u83b7\u53d6\u5230\u7684HTML\u9875\u9762\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          from bs4 import BeautifulSoup<\/p>\n
          soup = BeautifulSoup(content, 'html.parser')<\/p>\n
          \u67e5\u627e\u6240\u6709\u65b0\u95fb\u6807\u9898<\/strong><\/h2>\n
          titles = soup.find_all('h2')<\/p>\n
          for title in titles:<\/p>\n
              print(title.get_text())<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u9996\u5148\u5bfc\u5165BeautifulSoup\u5e93\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup()\u65b9\u6cd5\u89e3\u6790HTML\u9875\u9762\u3002\u4f7f\u7528find_all()\u65b9\u6cd5\u67e5\u627e\u6240\u6709\u7684h2\u6807\u7b7e\uff0c\u5e76\u6253\u5370\u6bcf\u4e2a\u6807\u9898\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n
          \u4e09\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f<\/h3>\n<\/p>\n
          1. \u5bfc\u5165\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5757<\/h4>\n<\/p>\n
          \u4f7f\u7528Python\u7684re\u6a21\u5757\u6765\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          import re<\/p>\n
          pattern = re.compile(r'<h2.*?>(.*?)<\/h2>', re.S)<\/p>\n
          titles = re.findall(pattern, content)<\/p>\n
          for title in titles:<\/p>\n
              print(title)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u9996\u5148\u5bfc\u5165re\u6a21\u5757\uff0c\u7136\u540e\u5b9a\u4e49\u4e00\u4e2a\u5339\u914dh2\u6807\u7b7e\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u3002\u4f7f\u7528re.findall()\u65b9\u6cd5\u627e\u5230\u6240\u6709\u5339\u914d\u7684\u6807\u9898\uff0c\u5e76\u6253\u5370\u6bcf\u4e2a\u6807\u9898\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n
          \u56db\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6<\/h3>\n<\/p>\n
          1. \u5b89\u88c5Scrapy\u6846\u67b6<\/h4>\n<\/p>\n
          \u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86Scrapy\u6846\u67b6\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
          pip install scrapy<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          Scrapy\u662f\u4e00\u4e2a\u7528\u4e8e\u722c\u53d6\u7f51\u7ad9\u5e76\u4ece\u9875\u9762\u4e2d\u63d0\u53d6\u7ed3\u6784\u5316\u6570\u636e\u7684\u5e94\u7528\u6846\u67b6\uff0c\u975e\u5e38\u9002\u5408\u5927\u89c4\u6a21\u722c\u53d6\u4efb\u52a1\u3002<\/p>\n<\/p>\n
          2. \u521b\u5efaScrapy\u9879\u76ee<\/h4>\n<\/p>\n
          \u521b\u5efa\u4e00\u4e2a\u65b0\u7684Scrapy\u9879\u76ee\uff0c\u5e76\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          scrapy startproject sinanews<\/p>\n
          cd sinanews<\/p>\n
          scrapy genspider sinanews_spider news.sina.com.cn<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u9996\u5148\u4f7f\u7528scrapy startproject\u547d\u4ee4\u521b\u5efa\u4e00\u4e2a\u65b0\u7684Scrapy\u9879\u76ee\uff0c\u7136\u540e\u8fdb\u5165\u9879\u76ee\u76ee\u5f55\uff0c\u5e76\u4f7f\u7528scrapy genspider\u547d\u4ee4\u751f\u6210\u4e00\u4e2a\u65b0\u7684\u722c\u866b\u3002<\/p>\n<\/p>\n
          3. \u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h4>\n<\/p>\n
          \u7f16\u8f91sinanews_spider.py\u6587\u4ef6\uff0c\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          import scrapy<\/p>\n
          class SinanewsSpider(scrapy.Spider):<\/p>\n
              name = 'sinanews_spider'<\/p>\n
              allowed_domains = ['news.sina.com.cn']<\/p>\n
              start_urls = ['https:\/\/news.sina.com.cn\/']<\/p>\n
              def parse(self, response):<\/p>\n
                  titles = response.xpath('\/\/h2\/text()').getall()<\/p>\n
                  for title in titles:<\/p>\n
                      yield {'title': title}<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u5b9a\u4e49\u4e86\u4e00\u4e2a\u65b0\u7684\u722c\u866b\u7c7bSinanewsSpider\uff0c\u7ee7\u627f\u81eascrapy.Spider\u3002\u5b9a\u4e49\u4e86\u722c\u866b\u7684\u540d\u79f0\u3001\u5141\u8bb8\u7684\u57df\u540d\u548c\u8d77\u59cbURL\u3002\u5728parse()\u65b9\u6cd5\u4e2d\uff0c\u4f7f\u7528XPath\u67e5\u627e\u6240\u6709h2\u6807\u7b7e\u7684\u6587\u672c\u5185\u5bb9\uff0c\u5e76\u751f\u6210\u5305\u542b\u6807\u9898\u7684\u5b57\u5178\u3002<\/p>\n<\/p>\n
          4. \u8fd0\u884c\u722c\u866b<\/h4>\n<\/p>\n
          \u8fd0\u884c\u722c\u866b\uff0c\u83b7\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u6807\u9898\uff1a<\/p>\n<\/p>\n
          scrapy crawl sinanews_spider<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528scrapy crawl\u547d\u4ee4\u8fd0\u884c\u722c\u866b\uff0c\u5e76\u83b7\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u6807\u9898\u3002<\/p>\n<\/p>\n
          \u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
          \u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u4f18\u70b9\u548c\u9002\u7528\u573a\u666f\uff0c\u5f00\u53d1\u8005\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
          \u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u5e93\u9002\u5408\u5c0f\u89c4\u6a21\u722c\u53d6\u4efb\u52a1\uff0c\u4ee3\u7801\u7b80\u5355\u6613\u61c2\uff0c\u9002\u5408\u521d\u5b66\u8005\u3002<\/strong><\/p>\n
          \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u9002\u5408\u7b80\u5355\u7684\u6587\u672c\u5339\u914d\u548c\u63d0\u53d6\u4efb\u52a1\uff0c\u4f46\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u7f16\u5199\u53ef\u80fd\u6bd4\u8f83\u590d\u6742\uff0c\u4e0d\u9002\u5408\u5904\u7406\u590d\u6742\u7684HTML\u7ed3\u6784\u3002<\/strong><\/p>\n
          \u4f7f\u7528Scrapy\u6846\u67b6\u9002\u5408\u5927\u89c4\u6a21\u722c\u53d6\u4efb\u52a1\uff0c\u5177\u6709\u9ad8\u6548\u7684\u722c\u53d6\u548c\u6570\u636e\u63d0\u53d6\u80fd\u529b\uff0c\u4f46\u6846\u67b6\u7684\u5b66\u4e60\u66f2\u7ebf\u8f83\u9661\uff0c\u9700\u8981\u4e00\u5b9a\u7684\u5f00\u53d1\u7ecf\u9a8c\u3002<\/strong><\/p>\n<\/p>\n
          \u516d\u3001\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u5e94\u5bf9\u53cd\u722c\u63aa\u65bd<\/h3>\n<\/p>\n
          \u5728\u5b9e\u9645\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u53cd\u722c\u63aa\u65bd\uff0c\u4f8b\u5982\uff1aIP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u3001\u52a8\u6001\u52a0\u8f7d\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u5e94\u5bf9\u53cd\u722c\u63aa\u65bd\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
          1. \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n
          \u5728\u53d1\u9001HTTP\u8bf7\u6c42\u65f6\uff0c\u53ef\u4ee5\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee\uff0c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          headers = {<\/p>\n
              'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36'<\/p>\n
          }<\/p>\n
          response = requests.get(url, headers=headers)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u5b9a\u4e49\u4e86\u4e00\u4e2a\u8bf7\u6c42\u5934\u5b57\u5178\uff0c\u5e76\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u5c06\u5176\u4f5c\u4e3a\u53c2\u6570\u4f20\u9012\u7ed9requests.get()\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
          2. \u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n
          \u4f7f\u7528\u4ee3\u7406\u53ef\u4ee5\u9690\u85cf\u771f\u5b9eIP\uff0c\u907f\u514d\u88ab\u5c01\u7981\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          proxies = {<\/p>\n
              'http': 'http:\/\/10.10.10.10:8000',<\/p>\n
              'https': 'http:\/\/10.10.10.10:8000'<\/p>\n
          }<\/p>\n
          response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u5b9a\u4e49\u4e86\u4e00\u4e2a\u4ee3\u7406\u5b57\u5178\uff0c\u5e76\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u5c06\u5176\u4f5c\u4e3a\u53c2\u6570\u4f20\u9012\u7ed9requests.get()\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
          3. \u4f7f\u7528\u968f\u673a\u5ef6\u65f6<\/h4>\n<\/p>\n
          \u5728\u53d1\u9001\u8bf7\u6c42\u65f6\uff0c\u6dfb\u52a0\u968f\u673a\u5ef6\u65f6\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4\u88ab\u5c01\u7981\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          import time<\/p>\n
          import random<\/p>\n
          time.sleep(random.uniform(1, 3))<\/p>\n
          response = requests.get(url, headers=headers)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528time.sleep()\u65b9\u6cd5\u6dfb\u52a0\u968f\u673a\u5ef6\u65f6\u3002<\/p>\n<\/p>\n
          4. \u5904\u7406\u52a8\u6001\u52a0\u8f7d<\/h4>\n<\/p>\n
          \u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u540e\u7684\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
          from selenium import webdriver<\/p>\n
          driver = webdriver.Chrome()<\/p>\n
          driver.get(url)<\/p>\n
          time.sleep(3)  # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/p>\n
          content = driver.page_source<\/p>\n
          driver.quit()<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528Selenium\u5e93\u542f\u52a8Chrome\u6d4f\u89c8\u5668\uff0c\u8bbf\u95ee\u76ee\u6807URL\uff0c\u5e76\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\u540e\u83b7\u53d6\u9875\u9762\u5185\u5bb9\u3002<\/p>\n<\/p>\n
          \u4e03\u3001\u5b8c\u6574\u793a\u4f8b\u4ee3\u7801<\/h3>\n<\/p>\n
          \u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b8c\u6574\u793a\u4f8b\u4ee3\u7801\uff0c\u7ed3\u5408\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u6807\u9898\uff1a<\/p>\n<\/p>\n
          import requests<\/p>\n
          from bs4 import BeautifulSoup<\/p>\n
          import re<\/p>\n
          import time<\/p>\n
          import random<\/p>\n
          from selenium import webdriver<\/p>\n
          \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong><\/h2>\n
          headers = {<\/p>\n
              'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36'<\/p>\n
          }<\/p>\n
          \u8bbe\u7f6e\u4ee3\u7406<\/strong><\/h2>\n
          proxies = {<\/p>\n
              'http': 'http:\/\/10.10.10.10:8000',<\/p>\n
              'https': 'http:\/\/10.10.10.10:8000'<\/p>\n
          }<\/p>\n
          \u53d1\u9001HTTP\u8bf7\u6c42<\/strong><\/h2>\n
          url = 'https:\/\/news.sina.com.cn\/'<\/p>\n
          response = requests.get(url, headers=headers, proxies=proxies)<\/p>\n
          if response.status_code == 200:<\/p>\n
              print("Successfully fetched the webpage")<\/p>\n
              content = response.text<\/p>\n
              # \u89e3\u6790HTML\u9875\u9762<\/p>\n
              soup = BeautifulSoup(content, 'html.parser')<\/p>\n
              # \u67e5\u627e\u6240\u6709\u65b0\u95fb\u6807\u9898<\/p>\n
              titles = soup.find_all('h2')<\/p>\n
              for title in titles:<\/p>\n
                  print(title.get_text())<\/p>\n
          else:<\/p>\n
              print("Failed to fetch the webpage")<\/p>\n
          \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f<\/strong><\/h2>\n
          pattern = re.compile(r'<h2.*?>(.*?)<\/h2>', re.S)<\/p>\n
          titles = re.findall(pattern, content)<\/p>\n
          for title in titles:<\/p>\n
              print(title)<\/p>\n
          \u4f7f\u7528Selenium\u5904\u7406\u52a8\u6001\u52a0\u8f7d<\/strong><\/h2>\n
          driver = webdriver.Chrome()<\/p>\n
          driver.get(url)<\/p>\n
          time.sleep(3)  # \u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/p>\n
          content = driver.page_source<\/p>\n
          driver.quit()<\/p>\n
          soup = BeautifulSoup(content, 'html.parser')<\/p>\n
          titles = soup.find_all('h2')<\/p>\n
          for title in titles:<\/p>\n
              print(title.get_text())<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u516b\u3001\u603b\u7ed3\u4e0e\u5c55\u671b<\/h3>\n<\/p>\n
          \u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u8be6\u7ec6\u8ba8\u8bba\u4e86\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u3002\u4ecb\u7ecd\u4e86\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML\u9875\u9762\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4fe1\u606f\u3001\u4f7f\u7528Scrapy\u6846\u67b6\u8fdb\u884c\u5927\u89c4\u6a21\u722c\u53d6\u7684\u65b9\u6cd5\u3002\u5e76\u63d0\u4f9b\u4e86\u5e94\u5bf9\u53cd\u722c\u63aa\u65bd\u7684\u65b9\u6cd5\u548c\u5b8c\u6574\u793a\u4f8b\u4ee3\u7801\u3002<\/p>\n<\/p>\n
          \u722c\u866b\u5f00\u53d1\u662f\u4e00\u9879\u6280\u672f\u6027\u8f83\u5f3a\u7684\u4efb\u52a1\uff0c\u9700\u8981\u5bf9\u7f51\u9875\u7ed3\u6784\u548c\u7f51\u7edc\u534f\u8bae\u6709\u4e00\u5b9a\u7684\u4e86\u89e3\u3002<\/strong> \u5728\u5b9e\u9645\u5f00\u53d1\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u95ee\u9898\u548c\u6311\u6218\uff0c\u9700\u8981\u4e0d\u65ad\u5b66\u4e60\u548c\u5b9e\u8df5\uff0c\u79ef\u7d2f\u7ecf\u9a8c\uff0c\u63d0\u9ad8\u89e3\u51b3\u95ee\u9898\u7684\u80fd\u529b\u3002<\/p>\n<\/p>\n
          \u672a\u6765\uff0c\u968f\u7740\u4e92\u8054\u7f51\u6280\u672f\u7684\u53d1\u5c55\uff0c\u722c\u866b\u6280\u672f\u4e5f\u5c06\u4e0d\u65ad\u6f14\u8fdb\u3002\u5e0c\u671b\u672c\u6587\u80fd\u4e3a\u8bfb\u8005\u63d0\u4f9b\u4e00\u4e9b\u6709\u7528\u7684\u53c2\u8003\u548c\u542f\u53d1\uff0c\u5e2e\u52a9\u5927\u5bb6\u66f4\u597d\u5730\u638c\u63e1\u722c\u866b\u6280\u672f\uff0c\u5e94\u7528\u4e8e\u5b9e\u9645\u5f00\u53d1\u4e2d\u3002<\/p>\n<\/p>\n
          \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
           \u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong>
          \u8981\u4f7f\u7528Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u4e00\u4e9b\u5fc5\u8981\u7684\u5e93\uff0c\u5982Requests\u7528\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff0cBeautifulSoup\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u63a5\u7740\uff0c\u786e\u5b9a\u8981\u722c\u53d6\u7684\u65b0\u95fb\u9875\u9762\u7684URL\uff0c\u5e76\u4f7f\u7528Requests\u5e93\u83b7\u53d6\u9875\u9762\u5185\u5bb9\u3002\u89e3\u6790HTML\u540e\uff0c\u53ef\u4ee5\u63d0\u53d6\u6240\u9700\u7684\u65b0\u95fb\u6807\u9898\u3001\u53d1\u5e03\u65f6\u95f4\u548c\u5185\u5bb9\u7b49\u4fe1\u606f\uff0c\u6700\u540e\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002<\/p>\n
          \u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong>
          \u5728\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u6216\u5176\u4ed6\u7f51\u7ad9\u65f6\uff0c\u52a1\u5fc5\u9075\u5faa\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002\u8bb8\u591a\u7f51\u7ad9\u5728\u5176robots.txt\u6587\u4ef6\u4e2d\u89c4\u5b9a\u4e86\u5141\u8bb8\u548c\u7981\u6b62\u7684\u722c\u866b\u884c\u4e3a\uff0c\u9075\u5b88\u8fd9\u4e9b\u89c4\u5219\u662f\u57fa\u672c\u7684\u9053\u5fb7\u4e49\u52a1\u3002\u6b64\u5916\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u9875\u9762\u4ee5\u9632\u6b62\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8d1f\u62c5\uff0c\u9002\u5f53\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u4e5f\u662f\u5f88\u91cd\u8981\u7684\u3002<\/p>\n
          \u4f7f\u7528Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u673a\u5236\uff1f<\/strong>
          \u65b0\u6d6a\u65b0\u95fb\u53ef\u80fd\u4f1a\u91c7\u53d6\u53cd\u722c\u63aa\u65bd\u6765\u4fdd\u62a4\u5176\u5185\u5bb9\uff0c\u5e38\u89c1\u7684\u624b\u6bb5\u5305\u62ecIP\u5c01\u7981\u548c\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406IP\u6765\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\uff0c\u6216\u4f7f\u7528\u968f\u673a\u7684User-Agent\u5934\u6765\u6a21\u62df\u4e0d\u540c\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002\u6b64\u5916\uff0c\u9002\u5f53\u964d\u4f4e\u722c\u53d6\u9891\u7387\u548c\u4f7f\u7528\u65f6\u95f4\u5ef6\u8fdf\u4e5f\u80fd\u5e2e\u52a9\u51cf\u5c11\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u65b0\u6d6a\u65b0\u95fb\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3 […]","protected":false},"author":3,"featured_media":1166540,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1166530"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1166530"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1166530\/revisions"}],"predecessor-version":[{"id":1166542,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1166530\/revisions\/1166542"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1166540"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1166530"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1166530"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1166530"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}