{"id":1179555,"date":"2025-01-15T18:25:20","date_gmt":"2025-01-15T10:25:20","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1179555.html"},"modified":"2025-01-15T18:25:23","modified_gmt":"2025-01-15T10:25:23","slug":"python%e5%a6%82%e4%bd%95%e4%b8%8b%e8%bd%bd%e7%bd%91%e9%a1%b5%e6%96%87%e4%bb%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1179555.html","title":{"rendered":"python\u5982\u4f55\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25113929\/e96d0d45-7a34-4a07-a6a2-fb6d60cf3683.webp\" alt=\"python\u5982\u4f55\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\" \/><\/p>\n<p><p> <strong>Python\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528requests\u5e93\u3001\u4f7f\u7528urllib\u5e93\u3001\u4f7f\u7528BeautifulSoup\u5e93\u7b49\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528requests\u5e93\u662f\u6700\u5e38\u89c1\u4e14\u7b80\u5355\u7684\u65b9\u6cd5\u3002\u4e0b\u9762\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4e2d\u4e00\u79cd\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u5b89\u88c5requests\u5e93\uff1a\u9996\u5148\u9700\u8981\u5b89\u88c5requests\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\uff1a\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u975e\u5e38\u7b80\u5355\uff0c\u53ea\u9700\u8981\u51e0\u884c\u4ee3\u7801\u5373\u53ef\u5b9e\u73b0\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u9996\u5148\u901a\u8fc7<code>requests.get<\/code>\u65b9\u6cd5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u5c06\u5185\u5bb9\u5199\u5165\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<strong>\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u8fd9\u91cc\u7684\u6587\u4ef6\u5199\u5165\u6a21\u5f0f\u4f7f\u7528\u7684\u662f<code>wb<\/code>\uff0c\u8868\u793a\u4ee5\u4e8c\u8fdb\u5236\u6a21\u5f0f\u5199\u5165\u6587\u4ef6<\/strong>\u3002\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u4e0b\u8f7d\u7684\u6587\u4ef6\u5185\u5bb9\u4fdd\u6301\u539f\u59cb\u683c\u5f0f\uff0c\u4e0d\u4f1a\u56e0\u4e3a\u7f16\u7801\u95ee\u9898\u5bfc\u81f4\u6587\u4ef6\u635f\u574f\u3002<\/p>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u4f7f\u7528Python\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\u7684\u5176\u4ed6\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u4e00\u4e9b\u5b9e\u8df5\u4e2d\u7684\u6280\u5de7\u548c\u6ce8\u610f\u4e8b\u9879\u3002<\/p>\n<\/p>\n<p><h2>\u4e00\u3001\u4f7f\u7528requests\u5e93<\/h2>\n<\/p>\n<p><h3>1. \u5b89\u88c5\u4e0e\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>\u5982\u4e0a\u6240\u8ff0\uff0crequests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u5e93\u4e4b\u4e00\u3002\u5b89\u88c5\u65b9\u6cd5\u975e\u5e38\u7b80\u5355\uff0c\u53ea\u9700\u8981\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5c31\u53ef\u4ee5\u5f00\u59cb\u4f7f\u7528requests\u5e93\u8fdb\u884c\u7f51\u9875\u6587\u4ef6\u7684\u4e0b\u8f7d\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528requests\u5e93\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>2. \u6dfb\u52a0\u8bf7\u6c42\u5934<\/h3>\n<\/p>\n<p><p>\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u670d\u52a1\u5668\u53ef\u80fd\u4f1a\u6839\u636e\u8bf7\u6c42\u5934\u7684\u4fe1\u606f\u6765\u5224\u65ad\u8bf7\u6c42\u662f\u5426\u5408\u6cd5\u3002\u4f8b\u5982\uff0c\u6709\u4e9b\u7f51\u7ad9\u53ef\u80fd\u4f1a\u68c0\u67e5User-Agent\u5934\u6765\u5224\u65ad\u8bf7\u6c42\u662f\u5426\u6765\u81ea\u4e8e\u6d4f\u89c8\u5668\u3002\u4e3a\u4e86\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u53ef\u4ee5\u5728\u8bf7\u6c42\u65f6\u6dfb\u52a0User-Agent\u5934\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>headers = {&#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.36&#39;}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u53ef\u4ee5\u907f\u514d\u4e00\u4e9b\u56e0\u7f3a\u5c11\u8bf7\u6c42\u5934\u800c\u5bfc\u81f4\u7684\u8bf7\u6c42\u5931\u8d25\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>3. \u5904\u7406\u4e0d\u540c\u7f16\u7801<\/h3>\n<\/p>\n<p><p>\u5728\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u6709\u65f6\u9700\u8981\u5904\u7406\u4e0d\u540c\u7684\u7f16\u7801\u683c\u5f0f\u3002requests\u5e93\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684\u65b9\u6cd5\u6765\u5904\u7406\u7f16\u7801\u95ee\u9898\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528<code>response.encoding<\/code>\u6765\u8bbe\u7f6e\u7f16\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<h2><strong>\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801<\/strong><\/h2>\n<p>response.encoding = response.apparent_encoding<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=response.encoding) as file:<\/p>\n<p>    file.write(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u7f51\u9875\u5185\u5bb9\u4ee5\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h2>\u4e8c\u3001\u4f7f\u7528urllib\u5e93<\/h2>\n<\/p>\n<p><h3>1. \u5b89\u88c5\u4e0e\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>urllib\u5e93\u662fPython\u5185\u7f6e\u7684HTTP\u5e93\uff0c\u4e0d\u9700\u8981\u989d\u5916\u5b89\u88c5\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528urllib\u5e93\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import urllib.request<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = urllib.request.urlopen(url)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.read())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528urllib\u5e93\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>2. \u6dfb\u52a0\u8bf7\u6c42\u5934<\/h3>\n<\/p>\n<p><p>\u4e0erequests\u5e93\u7c7b\u4f3c\uff0c\u53ef\u4ee5\u5728\u8bf7\u6c42\u65f6\u6dfb\u52a0\u8bf7\u6c42\u5934\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import urllib.request<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>headers = {&#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.36&#39;}<\/p>\n<p>req = urllib.request.Request(url, headers=headers)<\/p>\n<p>response = urllib.request.urlopen(req)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.read())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\uff0c\u53ef\u4ee5\u907f\u514d\u4e00\u4e9b\u56e0\u7f3a\u5c11\u8bf7\u6c42\u5934\u800c\u5bfc\u81f4\u7684\u8bf7\u6c42\u5931\u8d25\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>3. \u5904\u7406\u4e0d\u540c\u7f16\u7801<\/h3>\n<\/p>\n<p><p>\u5728\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u4e5f\u9700\u8981\u5904\u7406\u4e0d\u540c\u7684\u7f16\u7801\u683c\u5f0f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5904\u7406\u7f16\u7801\u95ee\u9898\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import urllib.request<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = urllib.request.urlopen(url)<\/p>\n<h2><strong>\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801<\/strong><\/h2>\n<p>encoding = response.headers.get_content_charset(f<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>lobj=&quot;utf-8&quot;)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=encoding) as file:<\/p>\n<p>    file.write(response.read().decode(encoding))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u7f51\u9875\u5185\u5bb9\u4ee5\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h2>\u4e09\u3001\u4f7f\u7528BeautifulSoup\u5e93<\/h2>\n<\/p>\n<p><h3>1. \u5b89\u88c5\u4e0e\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\uff0c\u901a\u5e38\u4e0erequests\u5e93\u6216urllib\u5e93\u7ed3\u5408\u4f7f\u7528\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528BeautifulSoup\u5e93\u4e0b\u8f7d\u5e76\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    file.write(soup.prettify())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528BeautifulSoup\u5e93\u4e0b\u8f7d\u5e76\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>2. \u63d0\u53d6\u7279\u5b9a\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u5e93\u7684\u5f3a\u5927\u4e4b\u5904\u5728\u4e8e\u53ef\u4ee5\u8f7b\u677e\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>links = soup.find_all(&#39;a&#39;)<\/p>\n<p>with open(&#39;links.txt&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    for link in links:<\/p>\n<p>        href = link.get(&#39;href&#39;)<\/p>\n<p>        if href:<\/p>\n<p>            file.write(href + &#39;\\n&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528BeautifulSoup\u5e93\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>3. \u5904\u7406\u4e0d\u540c\u7f16\u7801<\/h3>\n<\/p>\n<p><p>\u4e0erequests\u5e93\u548curllib\u5e93\u7c7b\u4f3c\uff0c\u5728\u4f7f\u7528BeautifulSoup\u5e93\u65f6\u4e5f\u9700\u8981\u5904\u7406\u4e0d\u540c\u7684\u7f16\u7801\u683c\u5f0f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5904\u7406\u7f16\u7801\u95ee\u9898\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<h2><strong>\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801<\/strong><\/h2>\n<p>response.encoding = response.apparent_encoding<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    file.write(soup.prettify())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u7f51\u9875\u5185\u5bb9\u4ee5\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h2>\u56db\u3001\u4f7f\u7528selenium\u5e93<\/h2>\n<\/p>\n<p><h3>1. \u5b89\u88c5\u4e0e\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>Selenium\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316\u6d4b\u8bd5\u7684\u5de5\u5177\uff0c\u4f46\u4e5f\u53ef\u4ee5\u7528\u4e8e\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u3002\u9996\u5148\u9700\u8981\u5b89\u88c5Selenium\u5e93\u548c\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u4f8b\u5982ChromeDriver\u3002\u4ee5\u4e0b\u662f\u5b89\u88c5Selenium\u5e93\u7684\u547d\u4ee4\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(url)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    file.write(driver.page_source)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528Selenium\u5e93\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u5e76\u5c06\u5176\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>2. \u6a21\u62df\u7528\u6237\u64cd\u4f5c<\/h3>\n<\/p>\n<p><p>Selenium\u5e93\u7684\u5f3a\u5927\u4e4b\u5904\u5728\u4e8e\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u4f8b\u5982\u70b9\u51fb\u6309\u94ae\u3001\u586b\u5199\u8868\u5355\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u6a21\u62df\u7528\u6237\u70b9\u51fb\u6309\u94ae\u5e76\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u6a21\u62df\u7528\u6237\u70b9\u51fb\u6309\u94ae<\/strong><\/h2>\n<p>button = driver.find_element_by_id(&#39;button-id&#39;)<\/p>\n<p>button.click()<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as file:<\/p>\n<p>    file.write(driver.page_source)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u4e2a\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u7528\u6237\u70b9\u51fb\u6309\u94ae\u5e76\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>3. \u5904\u7406\u4e0d\u540c\u7f16\u7801<\/h3>\n<\/p>\n<p><p>\u5728\u4f7f\u7528Selenium\u5e93\u65f6\uff0c\u4e5f\u9700\u8981\u5904\u7406\u4e0d\u540c\u7684\u7f16\u7801\u683c\u5f0f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5904\u7406\u7f16\u7801\u95ee\u9898\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801<\/strong><\/h2>\n<p>page_source = driver.page_source<\/p>\n<p>encoding = driver.execute_script(&quot;return document.characterSet;&quot;)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;w&#39;, encoding=encoding) as file:<\/p>\n<p>    file.write(page_source)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u7f51\u9875\u5185\u5bb9\u4ee5\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h2>\u4e94\u3001\u5b9e\u8df5\u4e2d\u7684\u6280\u5de7\u548c\u6ce8\u610f\u4e8b\u9879<\/h2>\n<\/p>\n<p><h3>1. \u5904\u7406\u91cd\u5b9a\u5411<\/h3>\n<\/p>\n<p><p>\u5728\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u6709\u65f6\u4f1a\u9047\u5230\u91cd\u5b9a\u5411\u7684\u60c5\u51b5\u3002requests\u5e93\u548curllib\u5e93\u90fd\u53ef\u4ee5\u81ea\u52a8\u5904\u7406\u91cd\u5b9a\u5411\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url, allow_redirects=True)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u5728\u9047\u5230\u91cd\u5b9a\u5411\u65f6\u4ecd\u7136\u80fd\u591f\u6b63\u786e\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>2. \u8bbe\u7f6e\u8d85\u65f6<\/h3>\n<\/p>\n<p><p>\u4e3a\u4e86\u9632\u6b62\u8bf7\u6c42\u957f\u65f6\u95f4\u6302\u8d77\uff0c\u53ef\u4ee5\u8bbe\u7f6e\u8bf7\u6c42\u7684\u8d85\u65f6\u65f6\u95f4\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url, timeout=10)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u5728\u8bf7\u6c42\u8d85\u65f6\u65f6\u629b\u51fa\u5f02\u5e38\uff0c\u4ece\u800c\u907f\u514d\u7a0b\u5e8f\u957f\u65f6\u95f4\u7b49\u5f85\u3002<\/p>\n<\/p>\n<p><h3>3. \u5904\u7406\u5f02\u5e38<\/h3>\n<\/p>\n<p><p>\u5728\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u65f6\uff0c\u9700\u8981\u5904\u7406\u5404\u79cd\u53ef\u80fd\u7684\u5f02\u5e38\u60c5\u51b5\u3002\u4f8b\u5982\uff0c\u7f51\u7edc\u4e2d\u65ad\u3001\u670d\u52a1\u5668\u9519\u8bef\u7b49\u3002\u53ef\u4ee5\u4f7f\u7528try-except\u5757\u6765\u6355\u83b7\u5e76\u5904\u7406\u8fd9\u4e9b\u5f02\u5e38\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>try:<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    response.raise_for_status()<\/p>\n<p>    with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>        file.write(response.content)<\/p>\n<p>except requests.exceptions.RequestException as e:<\/p>\n<p>    print(f&quot;Error: {e}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u786e\u4fdd\u5728\u9047\u5230\u5f02\u5e38\u65f6\u7a0b\u5e8f\u4e0d\u4f1a\u5d29\u6e83\uff0c\u5e76\u53ef\u4ee5\u63d0\u4f9b\u6709\u7528\u7684\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>4. \u4f7f\u7528\u4ee3\u7406<\/h3>\n<\/p>\n<p><p>\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u4ee3\u7406\u6765\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528\u4ee3\u7406\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/10.10.1.10:3128&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/10.10.1.10:1080&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p>with open(&#39;example.html&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    file.write(response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u901a\u8fc7\u4ee3\u7406\u670d\u52a1\u5668\u6765\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\uff0c\u4ece\u800c\u907f\u514dIP\u88ab\u5c01\u7981\u7b49\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>5. \u5206\u5757\u4e0b\u8f7d<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u5927\u6587\u4ef6\u4e0b\u8f7d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5206\u5757\u4e0b\u8f7d\u6765\u8282\u7701\u5185\u5b58\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com\/largefile&#39;<\/p>\n<p>response = requests.get(url, stream=True)<\/p>\n<p>with open(&#39;largefile&#39;, &#39;wb&#39;) as file:<\/p>\n<p>    for chunk in response.iter_content(chunk_size=1024):<\/p>\n<p>        if chunk:<\/p>\n<p>            file.write(chunk)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u907f\u514d\u4e00\u6b21\u6027\u5c06\u5927\u6587\u4ef6\u52a0\u8f7d\u5230\u5185\u5b58\u4e2d\uff0c\u4ece\u800c\u63d0\u9ad8\u4e0b\u8f7d\u6548\u7387\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u5404\u79cd\u65b9\u6cd5\u548c\u6280\u5de7\uff0c\u53ef\u4ee5\u5728Python\u4e2d\u9ad8\u6548\u5730\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\uff0c\u5e76\u5904\u7406\u5404\u79cd\u5b9e\u9645\u5e94\u7528\u4e2d\u7684\u95ee\u9898\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u4e0b\u8f7d\u7279\u5b9a\u7c7b\u578b\u7684\u6587\u4ef6\uff0c\u6bd4\u5982PDF\u6216\u56fe\u7247\uff1f<\/strong><br \/>\u53ef\u4ee5\u4f7f\u7528Python\u7684<code>requests<\/code>\u5e93\u6765\u4e0b\u8f7d\u7279\u5b9a\u7c7b\u578b\u7684\u6587\u4ef6\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5df2\u5b89\u88c5<code>requests<\/code>\u5e93\u3002\u63a5\u7740\uff0c\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u6587\u4ef6\u7684\u5185\u5bb9\uff0c\u5e76\u5c06\u5176\u5199\u5165\u672c\u5730\u6587\u4ef6\u3002\u4f8b\u5982\uff0c\u5bf9\u4e8ePDF\u6587\u4ef6\uff0c\u53ef\u4ee5\u5982\u4e0b\u64cd\u4f5c\uff1a<\/p>\n<pre><code class=\"language-python\">import requests\n\nurl = &#39;https:\/\/example.com\/file.pdf&#39;\nresponse = requests.get(url)\n\nwith open(&#39;file.pdf&#39;, &#39;wb&#39;) as f:\n    f.write(response.content)\n<\/code><\/pre>\n<p>\u786e\u4fdd\u66ff\u6362<code>url<\/code>\u4e3a\u5b9e\u9645\u6587\u4ef6\u7684\u94fe\u63a5\uff0c\u8fd0\u884c\u6b64\u4ee3\u7801\u5373\u53ef\u4e0b\u8f7d\u6587\u4ef6\u3002<\/p>\n<p><strong>\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\u65f6\u5982\u4f55\u5904\u7406\u91cd\u5b9a\u5411\u6216\u9519\u8bef\u72b6\u6001\u7801\uff1f<\/strong><br \/>\u5728\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u91cd\u5b9a\u5411\u6216\u9519\u8bef\u72b6\u6001\u7801\u3002\u4f7f\u7528<code>requests<\/code>\u5e93\u7684<code>allow_redirects<\/code>\u53c2\u6570\u53ef\u4ee5\u63a7\u5236\u662f\u5426\u8ddf\u968f\u91cd\u5b9a\u5411\u3002\u8fd8\u53ef\u4ee5\u68c0\u67e5\u54cd\u5e94\u7684\u72b6\u6001\u7801\uff0c\u786e\u4fdd\u6587\u4ef6\u4e0b\u8f7d\u6210\u529f\u3002\u4f8b\u5982\uff1a<\/p>\n<pre><code class=\"language-python\">response = requests.get(url, allow_redirects=True)\n\nif response.status_code == 200:\n    with open(&#39;file.html&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as f:\n        f.write(response.text)\nelse:\n    print(f&quot;\u4e0b\u8f7d\u5931\u8d25\uff0c\u72b6\u6001\u7801: {response.status_code}&quot;)\n<\/code><\/pre>\n<p>\u8fd9\u79cd\u65b9\u5f0f\u53ef\u4ee5\u6709\u6548\u7ba1\u7406\u4e0d\u540c\u7684HTTP\u54cd\u5e94\u3002<\/p>\n<p><strong>\u5982\u4f55\u4e0b\u8f7d\u6574\u4e2a\u7f51\u9875\uff0c\u5305\u62ec\u5176\u6240\u6709\u8d44\u6e90\uff08\u5982CSS\u3001JavaScript\u548c\u56fe\u7247\uff09\uff1f<\/strong><br \/>\u82e5\u60f3\u4e0b\u8f7d\u6574\u4e2a\u7f51\u9875\u53ca\u5176\u8d44\u6e90\uff0c\u53ef\u4ee5\u4f7f\u7528<code>beautifulsoup4<\/code>\u548c<code>requests<\/code>\u5e93\u7684\u7ed3\u5408\u3002\u9996\u5148\u4e0b\u8f7d\u7f51\u9875HTML\uff0c\u7136\u540e\u89e3\u6790\u5176\u4e2d\u7684\u8d44\u6e90\u94fe\u63a5\uff0c\u5e76\u9010\u4e00\u4e0b\u8f7d\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u57fa\u672c\u793a\u4f8b\uff1a<\/p>\n<pre><code class=\"language-python\">import requests\nfrom bs4 import BeautifulSoup\nimport os\n\nurl = &#39;https:\/\/example.com&#39;\nresponse = requests.get(url)\n\nsoup = BeautifulSoup(response.text, &#39;html.parser&#39;)\n\n# \u521b\u5efa\u6587\u4ef6\u5939\u5b58\u50a8\u8d44\u6e90\nif not os.path.exists(&#39;resources&#39;):\n    os.makedirs(&#39;resources&#39;)\n\n# \u4e0b\u8f7d\u56fe\u7247\nfor img in soup.find_all(&#39;img&#39;):\n    img_url = img[&#39;src&#39;]\n    img_response = requests.get(img_url)\n    img_name = os.path.join(&#39;resources&#39;, img_url.split(&#39;\/&#39;)[-1])\n    \n    with open(img_name, &#39;wb&#39;) as f:\n        f.write(img_response.content)\n<\/code><\/pre>\n<p>\u6b64\u793a\u4f8b\u4ec5\u4e0b\u8f7d\u56fe\u7247\uff0c\u5176\u4ed6\u8d44\u6e90\uff08\u5982CSS\u548cJavaScript\uff09\u53ef\u7c7b\u4f3c\u5904\u7406\u3002\u901a\u8fc7\u8fd9\u6837\u7684\u65b9\u5f0f\uff0c\u53ef\u4ee5\u5b9e\u73b0\u5bf9\u6574\u4e2a\u7f51\u9875\u5185\u5bb9\u7684\u4e0b\u8f7d\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u4e0b\u8f7d\u7f51\u9875\u6587\u4ef6\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528requests\u5e93\u3001\u4f7f\u7528urllib\u5e93\u3001\u4f7f\u7528BeautifulSoup\u5e93 [&hellip;]","protected":false},"author":3,"featured_media":1179567,"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\/1179555"}],"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=1179555"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179555\/revisions"}],"predecessor-version":[{"id":1179570,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179555\/revisions\/1179570"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1179567"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1179555"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1179555"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1179555"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}