![\"python\u5982\u4f55\u722c\u53d6\u7f51\u9875\u5b9a\u5411\u5185\u5bb9\"](\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/2a3e17f5-52e8-47c6-af30-661151404ad1.webp?x-oss-process=image\/auto-orient,1\/format,webp\")
<\/p>\n<\/p>\n
Python\u722c\u53d6\u7f51\u9875\u5b9a\u5411\u5185\u5bb9\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u63d0\u53d6\u7279\u5b9a\u4fe1\u606f\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875\u548c\u53cd\u722c\u866b\u673a\u5236\u3002<\/strong> \u5176\u4e2d\uff0c\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u7ed3\u5408BeautifulSoup\u89e3\u6790HTML\u662f\u6700\u5e38\u7528\u4e14\u57fa\u7840\u7684\u65b9\u6cd5\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\u53ca\u5176\u5e94\u7528\u6280\u5de7\u3002<\/p>\n<\/p>\n Requests\u5e93\u662fPython\u4e2d\u975e\u5e38\u6d41\u884c\u7684HTTP\u5e93\uff0c\u7528\u4e8e\u5411\u7f51\u9875\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u5185\u5bb9\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5requests\u5e93\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u7136\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n url = 'http:\/\/example.com'<\/p>\n response = requests.get(url)<\/p>\n html_content = response.text<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528 BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u7684Python\u5e93\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u89e3\u6790HTML\u5185\u5bb9\u5e76\u63d0\u53d6\u7279\u5b9a\u4fe1\u606f\uff1a<\/p>\n<\/p>\n soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n title = soup.title.string<\/p>\n print(title)<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528 BeautifulSoup\u652f\u6301CSS\u9009\u62e9\u5668\uff0c\u800c\u53e6\u4e00\u4e2a\u5e93lxml\u5219\u652f\u6301XPath\u3002\u9996\u5148\uff0c\u5b89\u88c5lxml\u5e93\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9a\u4fe1\u606f\uff1a<\/p>\n<\/p>\n links = soup.select('a')<\/p>\n for link in links:<\/p>\n print(link.get('href'))<\/p>\n <\/code><\/pre>\n<\/p>\n tree = html.fromstring(html_content)<\/p>\n links = tree.xpath('\/\/a\/@href')<\/p>\n for link in links:<\/p>\n print(link)<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528CSS\u9009\u62e9\u5668\u63d0\u53d6\u6240\u6709\u94fe\u63a5\u7684href\u5c5e\u6027\uff0c\u5e76\u4f7f\u7528XPath\u63d0\u53d6\u6240\u6709\u94fe\u63a5\u3002<\/p>\n<\/p>\n \u6709\u4e9b\u7f51\u9875\u7684\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u4f7f\u7528requests\u5e93\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u5230\u8fd9\u4e9b\u5185\u5bb9\u3002\u8fd9\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u5e76\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9\u3002\u9996\u5148\uff0c\u5b89\u88c5Selenium\u5e93\u548c\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff08\u5982ChromeDriver\uff09\uff1a<\/p>\n<\/p>\n <\/code><\/pre>\n<\/p>\n \u7136\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u5904\u7406\u52a8\u6001\u7f51\u9875\uff1a<\/p>\n<\/p>\n url = 'http:\/\/example.com'<\/p>\n driver = webdriver.Chrome(executable_path='\/path\/to\/chromedriver')<\/p>\n driver.get(url)<\/p>\n html_content = driver.page_source<\/p>\n driver.quit()<\/p>\n soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n <\/code><\/pre>\n<\/p>\n \u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u4f7f\u7528Selenium\u542f\u52a8\u4e00\u4e2aChrome\u6d4f\u89c8\u5668\u5b9e\u4f8b\uff0c\u52a0\u8f7d\u76ee\u6807\u7f51\u9875\u5e76\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u540e\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n \u5f88\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u5404\u79cd\u53cd\u722c\u866b\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u4e3a\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u7b56\u7565\uff1a<\/p>\n<\/p>\n \u901a\u8fc7\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\uff0c\u53ef\u4ee5\u907f\u514dIP\u88ab\u5c01\u7981\uff1a<\/p>\n<\/p>\n 'http': 'http:\/\/proxy.example.com:8080',<\/p>\n 'https': 'https:\/\/proxy.example.com:8080',<\/p>\n }<\/p>\n response = requests.get(url, proxies=proxies)<\/p>\n <\/code><\/pre>\n<\/p>\n \u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u6a21\u62df\u771f\u5b9e\u6d4f\u89c8\u5668\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n 'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3'<\/p>\n }<\/p>\n response = requests.get(url, headers=headers)<\/p>\n <\/code><\/pre>\n<\/p>\n \u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u65f6\u95f4\u548c\u968f\u673a\u5316\u8bf7\u6c42\uff0c\u51cf\u5c11\u88ab\u68c0\u6d4b\u5230\u7684\u6982\u7387\uff1a<\/p>\n<\/p>\n import random<\/p>\n time.sleep(random.uniform(1, 3))<\/p>\n response = requests.get(url)<\/p>\n <\/code><\/pre>\n<\/p>\n Python\u722c\u53d6\u7f51\u9875\u5b9a\u5411\u5185\u5bb9\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u63d0\u53d6\u7279\u5b9a\u4fe1\u606f\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875\u548c\u53cd\u722c\u866b\u673a\u5236\u3002\u4f7f\u7528requests\u5e93\u7ed3\u5408BeautifulSoup\u89e3\u6790HTML\u662f\u6700\u57fa\u7840\u548c\u5e38\u7528\u7684\u65b9\u6cd5<\/strong>\uff0c\u800c\u5904\u7406\u52a8\u6001\u7f51\u9875\u548c\u5e94\u5bf9\u53cd\u722c\u866b\u673a\u5236\u5219\u9700\u8981\u4f7f\u7528Selenium\u5e93\u548c\u5176\u4ed6\u7b56\u7565<\/strong>\u3002\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u5b9a\u5411\u5185\u5bb9\u3002<\/p>\n<\/p>\n \u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7279\u5b9a\u7f51\u9875\u7684\u5185\u5bb9\uff1f<\/strong> \u5728\u722c\u53d6\u7f51\u9875\u65f6\u5e94\u8be5\u9075\u5faa\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\uff1f<\/strong> \u5982\u679c\u722c\u53d6\u7684\u7f51\u9875\u5185\u5bb9\u53d1\u751f\u53d8\u5316\uff0c\u6211\u8be5\u5982\u4f55\u8c03\u6574\u6211\u7684\u722c\u866b\u4ee3\u7801\uff1f<\/strong> \u5982\u4f55\u5904\u7406\u722c\u866b\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u63aa\u65bd\uff1f<\/strong>\u4e00\u3001\u4f7f\u7528Requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n
pip install requests<\/p>\nimport requests<\/p>\nrequests.get()<\/code>\u65b9\u6cd5\u5411\u76ee\u6807URL\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u7684\u5185\u5bb9\u5b58\u50a8\u5728html_content<\/code>\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/strong><\/h2>\n
pip install beautifulsoup4<\/p>\nfrom bs4 import BeautifulSoup<\/p>\nBeautifulSoup<\/code>\u7c7b\u89e3\u6790HTML\u5185\u5bb9\uff0c\u5e76\u901a\u8fc7title<\/code>\u5c5e\u6027\u83b7\u53d6\u7f51\u9875\u7684\u6807\u9898\u3002<\/p>\n<\/p>\n\u4e09\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u63d0\u53d6\u7279\u5b9a\u4fe1\u606f<\/strong><\/h2>\n
pip install lxml<\/p>\n\u4f7f\u7528CSS\u9009\u62e9\u5668<\/h2>\n<\/p>\n
# \u4f7f\u7528CSS\u9009\u62e9\u5668<\/p>\n\u4f7f\u7528XPath<\/h2>\n<\/p>\n
from lxml import html<\/p>\n\u56db\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875<\/strong><\/h2>\n
pip install selenium<\/p>\nfrom selenium import webdriver<\/p>\n\u7ee7\u7eed\u89e3\u6790HTML\u5185\u5bb9<\/strong><\/h2>\n
\u4e94\u3001\u53cd\u722c\u866b\u673a\u5236\u5e94\u5bf9<\/strong><\/h2>\n
1. \u4f7f\u7528\u4ee3\u7406<\/h2>\n<\/p>\n
proxies = {<\/p>\n2. \u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\u5934<\/h2>\n<\/p>\n
headers = {<\/p>\n3. \u4f7f\u7528\u5ef6\u8fdf\u548c\u968f\u673a\u5316\u8bf7\u6c42<\/h2>\n<\/p>\n
import time<\/p>\n\u516d\u3001\u603b\u7ed3<\/strong><\/h2>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
\u8981\u4f7f\u7528Python\u722c\u53d6\u7279\u5b9a\u7f51\u9875\u7684\u5185\u5bb9\uff0c\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u5e93\uff0c\u6bd4\u5982requests<\/code>\u6765\u53d1\u9001HTTP\u8bf7\u6c42\uff0cBeautifulSoup<\/code>\u6765\u89e3\u6790HTML\u5185\u5bb9\u3002\u9996\u5148\uff0c\u4f7f\u7528requests.get()<\/code>\u83b7\u53d6\u7f51\u9875\u6570\u636e\uff0c\u7136\u540e\u5229\u7528BeautifulSoup<\/code>\u89e3\u6790HTML\u6587\u6863\uff0c\u901a\u8fc7\u67e5\u627e\u6807\u7b7e\u548c\u7c7b\u540d\u7b49\u65b9\u5f0f\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u786e\u4fdd\u719f\u6089\u7f51\u7ad9\u7684\u7ed3\u6784\uff0c\u4ee5\u4fbf\u51c6\u786e\u5b9a\u4f4d\u76ee\u6807\u5185\u5bb9\u3002<\/p>\n
\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u65f6\uff0c\u9075\u5faa\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\u975e\u5e38\u91cd\u8981\u3002\u9075\u5b88\u7f51\u7ad9\u7684robots.txt<\/code>\u6587\u4ef6\u4e2d\u89c4\u5b9a\u7684\u722c\u53d6\u89c4\u5219\uff0c\u907f\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u7684\u8d1f\u62c5\u3002\u6b64\u5916\uff0c\u4e0d\u5e94\u6536\u96c6\u654f\u611f\u4fe1\u606f\u6216\u4fb5\u72af\u7248\u6743\u7684\u5185\u5bb9\u3002\u5728\u4f7f\u7528\u722c\u53d6\u7684\u6570\u636e\u65f6\uff0c\u52a1\u5fc5\u5c0a\u91cd\u539f\u521b\u8005\u7684\u6743\u5229\uff0c\u5e76\u5728\u5fc5\u8981\u65f6\u83b7\u53d6\u6388\u6743\u3002<\/p>\n
\u7f51\u9875\u5185\u5bb9\u7684\u53d8\u5316\u662f\u5e38\u89c1\u7684\u60c5\u51b5\uff0c\u53ef\u80fd\u4f1a\u5bfc\u81f4\u722c\u866b\u65e0\u6cd5\u6b63\u5e38\u5de5\u4f5c\u3002\u4e3a\u4e86\u9002\u5e94\u8fd9\u4e9b\u53d8\u5316\uff0c\u53ef\u4ee5\u5b9a\u671f\u68c0\u67e5\u7f51\u9875\u7684\u7ed3\u6784\uff0c\u786e\u4fdd\u4f60\u7684\u9009\u62e9\u5668\u4ecd\u7136\u6709\u6548\u3002\u5982\u679c\u7f51\u7ad9\u8fdb\u884c\u4e86\u91cd\u6784\uff0c\u53ef\u80fd\u9700\u8981\u4fee\u6539\u4f60\u7684\u89e3\u6790\u903b\u8f91\u3002\u540c\u65f6\uff0c\u4f7f\u7528\u5f02\u5e38\u5904\u7406\u673a\u5236\u6355\u83b7\u9519\u8bef\uff0c\u5e76\u8bb0\u5f55\u65e5\u5fd7\uff0c\u4ee5\u4fbf\u4e8e\u540e\u7eed\u7684\u8c03\u8bd5\u548c\u7ef4\u62a4\u3002<\/p>\n
\u5f88\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u63aa\u65bd\u6765\u4fdd\u62a4\u81ea\u8eab\u6570\u636e\u3002\u5728\u722c\u866b\u8fc7\u7a0b\u4e2d\uff0c\u5982\u679c\u9047\u5230IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u95ee\u9898\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u4ee3\u7406IP\u3001\u8bbe\u7f6e\u8bf7\u6c42\u5934\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u6216\u8005\u4f7f\u7528\u65f6\u95f4\u5ef6\u8fdf\u6765\u964d\u4f4e\u8bbf\u95ee\u9891\u7387\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u81ea\u52a8\u5316\u5de5\u5177\u5982Selenium\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff0c\u4ece\u800c\u7ed5\u8fc7\u4e00\u4e9b\u57fa\u7840\u7684\u53cd\u722c\u673a\u5236\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u7f51\u9875\u5b9a\u5411\u5185\u5bb9\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790 […]","protected":false},"author":3,"featured_media":1032515,"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\/1032512"}],"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=1032512"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1032512\/revisions"}],"predecessor-version":[{"id":1032517,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1032512\/revisions\/1032517"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1032515"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1032512"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1032512"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1032512"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}