{"id":940087,"date":"2024-12-26T20:52:32","date_gmt":"2024-12-26T12:52:32","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/940087.html"},"modified":"2024-12-26T20:52:35","modified_gmt":"2024-12-26T12:52:35","slug":"python%e5%a6%82%e4%bd%95%e8%8e%b7%e5%be%97url","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/940087.html","title":{"rendered":"python\u5982\u4f55\u83b7\u5f97url"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25074852\/1e0a7e77-11ce-42d4-adf2-aa054b7eeb98.webp\" alt=\"python\u5982\u4f55\u83b7\u5f97url\" \/><\/p>\n<p><p> <strong>\u5728Python\u4e2d\u83b7\u53d6URL\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5305\u62ec\u4f7f\u7528\u6807\u51c6\u5e93\u3001\u7b2c\u4e09\u65b9\u5e93\u548c\u6846\u67b6\u7b49\u3002\u5e38\u89c1\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528<code>urllib<\/code>\u5e93\u3001\u4f7f\u7528<code>requests<\/code>\u5e93\u3001\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u89e3\u6790\u5b57\u7b26\u4e32\u3001\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6846\u67b6Scrapy\u3002<\/strong>\u5176\u4e2d\uff0c<code>requests<\/code>\u5e93\u56e0\u5176\u7b80\u5355\u6613\u7528\u800c\u5907\u53d7\u63a8\u5d07\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd<code>requests<\/code>\u5e93\u7684\u4f7f\u7528\u3002<\/p>\n<\/p>\n<p><p><code>requests<\/code>\u5e93\u662f\u4e00\u4e2a\u4eba\u6027\u5316\u7684HTTP\u5e93\uff0c\u4e13\u95e8\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u548c\u5904\u7406\u54cd\u5e94\u3002\u5b83\u4f7f\u5f97Python\u7a0b\u5e8f\u5458\u80fd\u591f\u5feb\u901f\u3001\u7b80\u4fbf\u5730\u4e0e\u7f51\u7ad9\u8fdb\u884c\u4ea4\u4e92\u3002\u4f7f\u7528<code>requests<\/code>\u5e93\u83b7\u53d6URL\uff0c\u53ea\u9700\u7b80\u5355\u7684\u51e0\u884c\u4ee3\u7801\u5373\u53ef\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>response = requests.get(&#39;http:\/\/example.com&#39;)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0a\u8ff0\u4ee3\u7801\u901a\u8fc7<code>requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001HTTP GET\u8bf7\u6c42\uff0c\u83b7\u53d6\u76ee\u6807URL\u7684\u5185\u5bb9\uff0c\u5e76\u6253\u5370\u54cd\u5e94\u6587\u672c\u3002\u8fd9\u79cd\u65b9\u6cd5\u9002\u7528\u4e8e\u9700\u8981\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001RESTful API\u6570\u636e\u7b49\u573a\u666f\u3002<\/p>\n<\/p>\n<hr>\n<p><h3>\u4e00\u3001URLLIB\u5e93\u7684\u4f7f\u7528<\/h3>\n<\/p>\n<p><p><code>urllib<\/code>\u662fPython\u6807\u51c6\u5e93\u7684\u4e00\u90e8\u5206\uff0c\u7528\u4e8e\u5904\u7406URL\u64cd\u4f5c\u3002\u5b83\u63d0\u4f9b\u4e86\u7b80\u5355\u7684\u63a5\u53e3\u6765\u5904\u7406HTTP\u8bf7\u6c42\u548c\u54cd\u5e94\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528<code>urllib.request<\/code>\u6a21\u5757<\/h4>\n<\/p>\n<p><p><code>urllib.request<\/code>\u662f\u7528\u4e8e\u6253\u5f00\u548c\u8bfb\u53d6URL\u7684\u6a21\u5757\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import urllib.request<\/p>\n<p>response = urllib.request.urlopen(&#39;http:\/\/example.com&#39;)<\/p>\n<p>html = response.read()<\/p>\n<p>print(html.decode(&#39;utf-8&#39;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u6cd5\u9002\u7528\u4e8e\u7b80\u5355\u7684\u8bf7\u6c42\u64cd\u4f5c\uff0c\u4f46\u4e0e<code>requests<\/code>\u5e93\u76f8\u6bd4\uff0c<code>urllib<\/code>\u5904\u7406\u590d\u6742\u8bf7\u6c42\u65f6\u663e\u5f97\u7e41\u7410\u3002<\/p>\n<\/p>\n<p><h4>2. \u4f7f\u7528<code>urllib.parse<\/code>\u6a21\u5757<\/h4>\n<\/p>\n<p><p><code>urllib.parse<\/code>\u6a21\u5757\u63d0\u4f9b\u4e86\u89e3\u6790URL\u7684\u529f\u80fd\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from urllib.parse import urlparse<\/p>\n<p>url = &#39;http:\/\/www.example.com\/path\/to\/page?name=ferret&amp;color=purple&#39;<\/p>\n<p>parsed_url = urlparse(url)<\/p>\n<p>print(parsed_url.scheme)  # \u8f93\u51fa: &#39;http&#39;<\/p>\n<p>print(parsed_url.netloc)  # \u8f93\u51fa: &#39;www.example.com&#39;<\/p>\n<p>print(parsed_url.path)    # \u8f93\u51fa: &#39;\/path\/to\/page&#39;<\/p>\n<p>print(parsed_url.query)   # \u8f93\u51fa: &#39;name=ferret&amp;color=purple&#39;<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7<code>urlparse<\/code>\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790URL\uff0c\u63d0\u53d6\u51fa\u534f\u8bae\u3001\u57df\u540d\u3001\u8def\u5f84\u3001\u67e5\u8be2\u53c2\u6570\u7b49\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001REQUESTS\u5e93\u7684\u4f7f\u7528<\/h3>\n<\/p>\n<p><p><code>requests<\/code>\u5e93\u662fPython\u4e2d\u6700\u6d41\u884c\u7684HTTP\u8bf7\u6c42\u5e93\u4e4b\u4e00\uff0c\u56e0\u5176\u7b80\u6d01\u548c\u5f3a\u5927\u529f\u80fd\u800c\u88ab\u5e7f\u6cdb\u4f7f\u7528\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5<code>requests<\/code>\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u786e\u4fdd\u5b89\u88c5\u4e86<code>requests<\/code>\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u57fa\u672c\u4f7f\u7528<\/h4>\n<\/p>\n<p><p>\u83b7\u53d6URL\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>response = requests.get(&#39;http:\/\/example.com&#39;)<\/p>\n<p>print(response.status_code)  # \u8f93\u51faHTTP\u72b6\u6001\u7801<\/p>\n<p>print(response.text)         # \u8f93\u51fa\u8fd4\u56de\u7684HTML\u5185\u5bb9<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u53ef\u4ee5\u770b\u5230\uff0c<code>requests<\/code>\u5e93\u4e0d\u4ec5\u53ef\u4ee5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u8fd8\u53ef\u4ee5\u83b7\u5f97HTTP\u54cd\u5e94\u72b6\u6001\u7801\u7b49\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h4>3. \u5904\u7406\u8bf7\u6c42\u53c2\u6570<\/h4>\n<\/p>\n<p><p>\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7<code>params<\/code>\u53c2\u6570\u4f20\u9012\u67e5\u8be2\u53c2\u6570\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>payload = {&#39;key1&#39;: &#39;value1&#39;, &#39;key2&#39;: &#39;value2&#39;}<\/p>\n<p>response = requests.get(&#39;http:\/\/httpbin.org\/get&#39;, params=payload)<\/p>\n<p>print(response.url)  # \u8f93\u51fa\u5b8c\u6574\u7684\u8bf7\u6c42URL<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4. \u5904\u7406POST\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u9664\u4e86GET\u8bf7\u6c42\uff0c<code>requests<\/code>\u5e93\u8fd8\u652f\u6301POST\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>payload = {&#39;key1&#39;: &#39;value1&#39;, &#39;key2&#39;: &#39;value2&#39;}<\/p>\n<p>response = requests.post(&#39;http:\/\/httpbin.org\/post&#39;, data=payload)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u53ef\u4ee5\u5c06\u8868\u5355\u6570\u636e\u53d1\u9001\u5230\u670d\u52a1\u5668\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u89e3\u6790URL<\/h3>\n<\/p>\n<p><p>\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u5b57\u7b26\u4e32\u5904\u7406\u5de5\u5177\uff0c\u4e5f\u53ef\u7528\u4e8e\u89e3\u6790URL\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>url = &#39;http:\/\/www.example.com\/path\/to\/page?name=ferret&amp;color=purple&#39;<\/p>\n<p>pattern = re.compile(r&#39;(https?:\/\/)([^\/]+)(.*)&#39;)<\/p>\n<p>match = pattern.match(url)<\/p>\n<p>if match:<\/p>\n<p>    print(&quot;Scheme:&quot;, match.group(1))<\/p>\n<p>    print(&quot;Dom<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>n:&quot;, match.group(2))<\/p>\n<p>    print(&quot;Path:&quot;, match.group(3))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u6b63\u5219\u8868\u8fbe\u5f0f\u80fd\u591f\u9ad8\u6548\u63d0\u53d6URL\u4e2d\u7684\u5404\u4e2a\u90e8\u5206\uff0c\u9002\u7528\u4e8e\u9700\u8981\u5bf9URL\u8fdb\u884c\u590d\u6742\u89e3\u6790\u7684\u573a\u666f\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6846\u67b6Scrapy<\/h3>\n<\/p>\n<p><p>Scrapy\u662f\u4e00\u4e2a\u7528\u4e8e\u6293\u53d6\u7f51\u7ad9\u6570\u636e\u7684\u722c\u866b\u6846\u67b6\uff0c\u529f\u80fd\u5f3a\u5927\uff0c\u9002\u5408\u5927\u89c4\u6a21\u6570\u636e\u91c7\u96c6\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5Scrapy<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528pip\u5b89\u88c5Scrapy\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install scrapy<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u521b\u5efaScrapy\u9879\u76ee<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528\u547d\u4ee4\u884c\u521b\u5efaScrapy\u9879\u76ee\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">scrapy startproject myproject<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u7f16\u5199\u722c\u866b<\/h4>\n<\/p>\n<p><p>\u5728<code>myproject\/spiders<\/code>\u76ee\u5f55\u4e0b\u521b\u5efa\u722c\u866b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import scrapy<\/p>\n<p>class MySpider(scrapy.Spider):<\/p>\n<p>    name = &#39;myspider&#39;<\/p>\n<p>    start_urls = [&#39;http:\/\/example.com&#39;]<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        self.log(&#39;Visited %s&#39; % response.url)<\/p>\n<p>        # \u5904\u7406\u9875\u9762\u5185\u5bb9<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4. \u8fd0\u884c\u722c\u866b<\/h4>\n<\/p>\n<p><p>\u5728\u9879\u76ee\u6839\u76ee\u5f55\u4e0b\u8fd0\u884c\u722c\u866b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">scrapy crawl myspider<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>Scrapy\u80fd\u591f\u9ad8\u6548\u7ba1\u7406\u548c\u8c03\u5ea6\u722c\u866b\u4efb\u52a1\uff0c\u9002\u7528\u4e8e\u590d\u6742\u7684\u7f51\u9875\u6570\u636e\u91c7\u96c6\u9879\u76ee\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u5728Python\u4e2d\uff0c\u83b7\u53d6URL\u7684\u65b9\u5f0f\u591a\u79cd\u591a\u6837\u3002\u5bf9\u4e8e\u7b80\u5355\u7684HTTP\u8bf7\u6c42\uff0c<code>requests<\/code>\u5e93\u662f\u9996\u9009\uff1b\u9700\u8981\u89e3\u6790URL\u65f6\uff0c\u53ef\u5229\u7528<code>urllib.parse<\/code>\u6216\u6b63\u5219\u8868\u8fbe\u5f0f\uff1b\u800c\u5bf9\u4e8e\u5927\u89c4\u6a21\u7684\u6570\u636e\u6293\u53d6\u4efb\u52a1\uff0cScrapy\u662f\u5f3a\u5927\u7684\u89e3\u51b3\u65b9\u6848\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u63d0\u9ad8\u5f00\u53d1\u6548\u7387\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u4e2d\u63d0\u53d6\u7f51\u9875\u7684URL\uff1f<\/strong><br \/>\u5728Python\u4e2d\u63d0\u53d6\u7f51\u9875\u7684URL\uff0c\u53ef\u4ee5\u4f7f\u7528<code>requests<\/code>\u5e93\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u901a\u8fc7<code>BeautifulSoup<\/code>\u6216\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u89e3\u6790HTML\u3002\u9996\u5148\uff0c\u901a\u8fc7<code>requests.get()<\/code>\u65b9\u6cd5\u83b7\u53d6\u7f51\u9875\uff0c\u63a5\u7740\u5229\u7528<code>BeautifulSoup<\/code>\u89e3\u6790HTML\u6587\u6863\uff0c\u641c\u7d22\u5e76\u63d0\u53d6\u6240\u9700\u7684\u94fe\u63a5\u3002<\/p>\n<p><strong>\u6211\u9700\u8981\u54ea\u4e9b\u5e93\u624d\u80fd\u5728Python\u4e2d\u83b7\u53d6URL\uff1f<\/strong><br \/>\u8981\u5728Python\u4e2d\u83b7\u53d6\u548c\u89e3\u6790URL\uff0c\u4e3b\u8981\u4f7f\u7528<code>requests<\/code>\u5e93\u6765\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u548c<code>BeautifulSoup<\/code>\u5e93\u6765\u89e3\u6790HTML\u5185\u5bb9\u3002\u53ef\u4ee5\u901a\u8fc7<code>pip install requests beautifulsoup4<\/code>\u547d\u4ee4\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u83b7\u53d6\u7684URL\u4ee5\u786e\u4fdd\u5176\u6709\u6548\u6027\uff1f<\/strong><br \/>\u83b7\u53d6URL\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>validators<\/code>\u5e93\u6216<code>urllib<\/code>\u6a21\u5757\u4e2d\u7684<code>urlparse<\/code>\u65b9\u6cd5\u68c0\u67e5URL\u7684\u6709\u6548\u6027\u3002\u901a\u8fc7\u8fd9\u4e9b\u5de5\u5177\uff0c\u53ef\u4ee5\u9a8c\u8bc1URL\u683c\u5f0f\u662f\u5426\u6b63\u786e\uff0c\u5e76\u786e\u4fdd\u94fe\u63a5\u53ef\u4ee5\u6b63\u5e38\u8bbf\u95ee\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\u83b7\u53d6URL\u7684\u6700\u4f73\u5b9e\u8df5\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u5728Python\u4e2d\u83b7\u53d6URL\u65f6\uff0c\u5efa\u8bae\u4f7f\u7528\u5f02\u5e38\u5904\u7406\u673a\u5236\u6765\u6355\u83b7\u8bf7\u6c42\u9519\u8bef\uff0c\u5e76\u4f7f\u7528\u65f6\u95f4\u5ef6\u8fdf\uff08\u5982<code>time.sleep()<\/code>\uff09\u6765\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u591a\u8bf7\u6c42\uff0c\u4ece\u800c\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002\u540c\u65f6\uff0c\u9075\u5faa\u7f51\u7ad9\u7684\u722c\u866b\u534f\u8bae\uff08robots.txt\uff09\u4e5f\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u83b7\u53d6URL\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5305\u62ec\u4f7f\u7528\u6807\u51c6\u5e93\u3001\u7b2c\u4e09\u65b9\u5e93\u548c\u6846\u67b6\u7b49\u3002\u5e38\u89c1\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528urllib\u5e93\u3001\u4f7f [&hellip;]","protected":false},"author":3,"featured_media":940089,"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\/940087"}],"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=940087"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/940087\/revisions"}],"predecessor-version":[{"id":940090,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/940087\/revisions\/940090"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/940089"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=940087"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=940087"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=940087"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}