﻿{"id":3297,"date":"2024-10-24T17:08:55","date_gmt":"2024-10-24T09:08:55","guid":{"rendered":"http:\/\/www.jiayus.com\/?p=3297"},"modified":"2024-10-24T17:08:55","modified_gmt":"2024-10-24T09:08:55","slug":"%e7%94%b2%e9%b1%bc%e8%88%86%e6%83%85%e7%9b%91%e6%b5%8b%e8%bd%af%e4%bb%b6%e7%94%a8python%e7%88%ac%e8%99%ab%e6%8a%93%e6%96%b0%e6%b5%aa%e5%be%ae%e5%8d%9a%e7%bd%91%e7%ab%99%e6%95%b0%e6%8d%ae%e7%9a%84","status":"publish","type":"post","link":"http:\/\/www.jiayus.com\/?p=3297","title":{"rendered":"\u7532\u9c7c\u8206\u60c5\u76d1\u6d4b\u8f6f\u4ef6\u7528python\u722c\u866b\u6293\u65b0\u6d6a\u5fae\u535a\u7f51\u7ad9\u6570\u636e\u7684\u4ee3\u7801"},"content":{"rendered":"\n<p>\u4f7f\u7528Python\u722c\u866b\u6293\u53d6\u65b0\u6d6a\u5fae\u535a\u7684\u6570\u636e\u662f\u4e00\u4e2a\u590d\u6742\u7684\u4efb\u52a1\uff0c\u56e0\u4e3a\u65b0\u6d6a\u5fae\u535a\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u5e76\u4e14\u5f88\u591a\u6570\u636e\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u3002\u6b64\u5916\uff0c\u722c\u53d6\u7f51\u7ad9\u6570\u636e\u9700\u9075\u5b88\u8be5\u7f51\u7ad9\u7684\u670d\u52a1\u6761\u6b3e\u548c\u9690\u79c1\u653f\u7b56\u3002\u5982\u679c\u4f60\u53ea\u662f\u60f3\u83b7\u53d6\u4e00\u4e9b\u516c\u5f00\u7684\u6570\u636e\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u5fae\u535a\u7684API\uff08\u5982\u679c\u53ef\u7528\uff09\u3002<\/p>\n\n\n\n<p>\u7136\u800c\uff0c\u5982\u679c\u4f60\u786e\u5b9e\u9700\u8981\u624b\u52a8\u6293\u53d6\u6570\u636e\uff0c\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u7684\u4f8b\u5b50\uff0c\u4f7f\u7528<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u5e93\u6765\u6293\u53d6\u5fae\u535a\u7684\u7b80\u5355\u9875\u9762\u6570\u636e\u3002\u8bf7\u6ce8\u610f\uff0c\u8fd9\u79cd\u65b9\u6cd5\u901a\u5e38\u53ea\u80fd\u6293\u53d6\u9759\u6001\u9875\u9762\u5185\u5bb9\uff0c\u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\uff08\u5982\u901a\u8fc7AJAX\u52a0\u8f7d\u7684\u5fae\u535a\u5185\u5bb9\uff09\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u3002<\/p>\n\n\n\n<p>\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u5e93\uff1a<\/p>\n\n\n\n<p>bash<br>pip install requests beautifulsoup4<br>\u4e0b\u9762\u662f\u4e00\u4e2a\u57fa\u672c\u7684Python\u722c\u866b\u4ee3\u7801\u793a\u4f8b\uff0c\u5b83\u6293\u53d6\u4e00\u4e2a\u5fae\u535a\u7528\u6237\u7684\u9996\u9875\u4fe1\u606f\uff08\u6ce8\u610f\uff1a\u6b64\u4ee3\u7801\u53ef\u80fd\u65e0\u6cd5\u5de5\u4f5c\uff0c\u56e0\u4e3a\u5fae\u535a\u7684\u9875\u9762\u7ed3\u6784\u4f1a\u4e0d\u65ad\u53d8\u5316\uff0c\u4e14\u53ef\u80fd\u6709\u53cd\u722c\u866b\u673a\u5236\uff09\uff1a<\/p>\n\n\n\n<p>python<br>import requests<br>from bs4 import BeautifulSoup<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">\u5fae\u535a\u7528\u6237\u4e3b\u9875\u7684URL\uff08\u66ff\u6362\u4e3a\u4f60\u60f3\u722c\u53d6\u7684\u7528\u6237\u4e3b\u9875URL\uff09<\/h1>\n\n\n\n<p>url = &#8216;https:\/\/weibo.com\/u\/\u4f60\u7684\u7528\u6237ID&#8217;<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee<\/h1>\n\n\n\n<p>headers = {<br>&#8216;User-Agent&#8217;: &#8216;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#8217;}<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">\u53d1\u9001HTTP GET\u8bf7\u6c42<\/h1>\n\n\n\n<p>response = requests.get(url, headers=headers)<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">\u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/h1>\n\n\n\n<p>if response.status_code == 200:<br># \u89e3\u6790HTML\u5185\u5bb9<br>soup = BeautifulSoup(response.content, &#8216;html.parser&#8217;)<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u8fd9\u91cc\u53ef\u4ee5\u6839\u636e\u5fae\u535a\u9875\u9762\u7684HTML\u7ed3\u6784\u6765\u63d0\u53d6\u4f60\u9700\u8981\u7684\u4fe1\u606f  \n# \u4f8b\u5982\uff0c\u63d0\u53d6\u5fae\u535a\u5217\u8868\u4e2d\u7684\u5fae\u535a\u5185\u5bb9\uff08\u6ce8\u610f\uff1a\u4ee5\u4e0b\u4ee3\u7801\u9700\u8981\u6839\u636e\u5b9e\u9645\u9875\u9762\u7ed3\u6784\u8fdb\u884c\u8c03\u6574\uff09  \nweibo_list = soup.find_all('div', class_='c')  # \u5047\u8bbe\u5fae\u535a\u5185\u5bb9\u88ab\u5305\u542b\u5728\u8fd9\u6837\u7684div\u4e2d  \n\nfor weibo in weibo_list:  \n    # \u63d0\u53d6\u5fae\u535a\u7684\u5177\u4f53\u5185\u5bb9\uff0c\u8fd9\u91cc\u53ea\u662f\u793a\u4f8b\uff0c\u5b9e\u9645\u63d0\u53d6\u65b9\u6cd5\u9700\u8981\u6839\u636eHTML\u7ed3\u6784\u6765\u786e\u5b9a  \n    content = weibo.find('span', class_='ctt').get_text()  \n    print(content)  <\/code><\/pre>\n\n\n\n<p>else:<br>print(&#8216;Failed to retrieve the webpage. Status code:&#8217;, response.status_code)<\/p>\n\n\n\n<p><strong>\u6ce8\u610f<\/strong>\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>\u53cd\u722c\u866b\u673a\u5236<\/strong>\uff1a\u65b0\u6d6a\u5fae\u535a\u6709\u5f3a\u5927\u7684\u53cd\u722c\u866b\u673a\u5236\uff0c\u5305\u62ecIP\u5c01\u9501\u3001\u9a8c\u8bc1\u7801\u9a8c\u8bc1\u7b49\u3002\u5982\u679c\u4f60\u7684\u8bf7\u6c42\u9891\u7387\u8fc7\u9ad8\u6216\u8005\u884c\u4e3a\u7279\u5f81\u660e\u663e\u662f\u722c\u866b\uff0c\u5f88\u5bb9\u6613\u88ab\u68c0\u6d4b\u5230\u5e76\u5c01\u9501\u3002<\/li>\n\n\n\n<li><strong>\u52a8\u6001\u5185\u5bb9<\/strong>\uff1a\u5fae\u535a\u7684\u5f88\u591a\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u8fd9\u610f\u5473\u7740\u4f7f\u7528\u7b80\u5355\u7684HTTP\u8bf7\u6c42\u548cHTML\u89e3\u6790\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u6240\u6709\u5185\u5bb9\u3002\u5bf9\u4e8e\u8fd9\u79cd\u60c5\u51b5\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u66f4\u9ad8\u7ea7\u7684\u722c\u866b\u6280\u672f\uff0c\u5982Selenium\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002<\/li>\n\n\n\n<li><strong>API<\/strong>\uff1a\u5982\u679c\u53ef\u80fd\u7684\u8bdd\uff0c\u6700\u597d\u4f7f\u7528\u5fae\u535a\u63d0\u4f9b\u7684\u5b98\u65b9API\u6765\u83b7\u53d6\u6570\u636e\u3002\u8fd9\u901a\u5e38\u662f\u83b7\u53d6\u6570\u636e\u7684\u5408\u6cd5\u4e14\u66f4\u53ef\u9760\u7684\u65b9\u5f0f\u3002<\/li>\n\n\n\n<li><strong>\u6cd5\u5f8b\u4e0e\u9053\u5fb7<\/strong>\uff1a\u5728\u722c\u53d6\u7f51\u7ad9\u6570\u636e\u4e4b\u524d\uff0c\u8bf7\u786e\u4fdd\u4f60\u4e86\u89e3\u5e76\u9075\u5b88\u8be5\u7f51\u7ad9\u7684\u670d\u52a1\u6761\u6b3e\u548c\u9690\u79c1\u653f\u7b56\u3002\u672a\u7ecf\u6388\u6743\u7684\u722c\u53d6\u884c\u4e3a\u53ef\u80fd\u8fdd\u53cd\u6cd5\u5f8b\u6216\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002<\/li>\n\n\n\n<li><strong>\u9891\u7387\u63a7\u5236<\/strong>\uff1a\u5728\u722c\u53d6\u6570\u636e\u65f6\uff0c\u8bf7\u63a7\u5236\u8bf7\u6c42\u7684\u9891\u7387\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u7684\u8d1f\u8f7d\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>\u4f7f\u7528Python\u722c\u866b\u6293\u53d6\u65b0\u6d6a\u5fae\u535a\u7684\u6570\u636e\u662f\u4e00\u4e2a\u590d\u6742\u7684\u4efb\u52a1\uff0c\u56e0\u4e3a\u65b0\u6d6a\u5fae\u535a\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u5e76\u4e14\u5f88\u591a\u6570\u636e\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\u3002\u6b64\u5916\uff0c\u722c\u53d6\u7f51\u7ad9\u6570\u636e\u9700\u9075\u5b88\u8be5\u7f51\u7ad9\u7684\u670d\u52a1\u6761\u6b3e\u548c\u9690\u79c1\u653f\u7b56\u3002\u5982\u679c\u4f60\u53ea\u662f\u60f3\u83b7\u53d6\u4e00\u4e9b\u516c\u5f00\u7684\u6570\u636e\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u5fae\u535a\u7684API\uff08\u5982\u679c\u53ef\u7528\uff09\u3002 \u7136\u800c\uff0c\u5982\u679c\u4f60\u786e\u5b9e\u9700\u8981\u624b\u52a8\u6293\u53d6\u6570\u636e\uff0c\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u7684\u4f8b\u5b50\uff0c\u4f7f\u7528requests\u548cBeautifulSoup\u5e93\u6765\u6293\u53d6\u5fae\u535a\u7684\u7b80\u5355\u9875\u9762\u6570\u636e\u3002\u8bf7\u6ce8\u610f\uff0c\u8fd9\u79cd\u65b9\u6cd5\u901a\u5e38\u53ea\u80fd\u6293\u53d6\u9759\u6001\u9875\u9762\u5185\u5bb9\uff0c\u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\uff08\u5982\u901a\u8fc7AJAX\u52a0\u8f7d\u7684\u5fae\u535a\u5185\u5bb9\uff09\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u3002 \u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5requests\u548cBeautifulSoup\u5e93\uff1a bashpip install requests beautifulsoup4\u4e0b\u9762\u662f\u4e00\u4e2a\u57fa\u672c\u7684Python\u722c\u866b\u4ee3\u7801\u793a\u4f8b\uff0c\u5b83\u6293\u53d6\u4e00\u4e2a\u5fae\u535a\u7528\u6237\u7684\u9996\u9875\u4fe1\u606f\uff08\u6ce8\u610f\uff1a\u6b64\u4ee3\u7801\u53ef\u80fd\u65e0\u6cd5\u5de5\u4f5c\uff0c\u56e0\u4e3a\u5fae\u535a\u7684\u9875\u9762\u7ed3\u6784\u4f1a\u4e0d\u65ad\u53d8\u5316\uff0c\u4e14\u53ef\u80fd\u6709\u53cd\u722c\u866b\u673a\u5236\uff09\uff1a pythonimport requestsfrom bs4 import BeautifulSoup \u5fae\u535a\u7528\u6237\u4e3b\u9875\u7684URL\uff08\u66ff\u6362\u4e3a\u4f60\u60f3\u722c\u53d6\u7684\u7528\u6237\u4e3b\u9875URL\uff09 url = &#8216;https:\/\/weibo.com\/u\/\u4f60\u7684\u7528\u6237ID&#8217; \u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee headers = {&#8216;User-Agent&#8217;: &#8216;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#8217;} \u53d1\u9001HTTP GET\u8bf7\u6c42 response = requests.get(url, headers=headers) \u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f if response.status_code == 200:# \u89e3\u6790HTML\u5185\u5bb9soup = BeautifulSoup(response.content, &#8216;html.parser&#8217;) else:print(&#8216;Failed to retrieve the webpage. Status code:&#8217;, response.status_code)&hellip; <br \/> <a class=\"read-more\" href=\"http:\/\/www.jiayus.com\/?p=3297\">Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-3297","post","type-post","status-publish","format-standard","hentry","category-yqfa"],"_links":{"self":[{"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/posts\/3297","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3297"}],"version-history":[{"count":1,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/posts\/3297\/revisions"}],"predecessor-version":[{"id":3298,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=\/wp\/v2\/posts\/3297\/revisions\/3298"}],"wp:attachment":[{"href":"http:\/\/www.jiayus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3297"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3297"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.jiayus.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}