{"id":1037172,"date":"2024-12-31T12:12:55","date_gmt":"2024-12-31T04:12:55","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1037172.html"},"modified":"2024-12-31T12:12:57","modified_gmt":"2024-12-31T04:12:57","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e4%b8%8b%e4%b8%80%e9%a1%b5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1037172.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u4e0b\u4e00\u9875"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/25ba30aa-e8d7-4bc5-8c3c-70909ec4ac26.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u4e0b\u4e00\u9875\" \/><\/p>\n<p><p> <strong>Python\u722c\u53d6\u4e0b\u4e00\u9875\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5\u3001\u6a21\u62df\u70b9\u51fb\u7ffb\u9875\u3001\u4f7f\u7528Selenium\u7b49\u3002<\/strong><\/p>\n<\/p>\n<p><p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u6570\u636e\u722c\u53d6\uff0c\u5e76\u91cd\u70b9\u4ecb\u7ecd\u51e0\u79cd\u5e38\u89c1\u7684\u7ffb\u9875\u65b9\u5f0f\uff0c\u5305\u62ec\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5\u548c\u6a21\u62df\u70b9\u51fb\u7ffb\u9875\u3002\u6211\u4eec\u8fd8\u4f1a\u63d0\u4f9b\u4e00\u4e9b\u5b9e\u7528\u7684\u4ee3\u7801\u793a\u4f8b\uff0c\u5e2e\u52a9\u8bfb\u8005\u66f4\u597d\u5730\u7406\u89e3\u548c\u5e94\u7528\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5<\/h3>\n<\/p>\n<p><p>\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5\u662f\u722c\u53d6\u591a\u9875\u6570\u636e\u7684\u57fa\u7840\u65b9\u6cd5\u3002\u8fd9\u79cd\u65b9\u6cd5\u9002\u7528\u4e8e\u5927\u591a\u6570\u9759\u6001\u7f51\u9875\uff0c\u901a\u8fc7\u89e3\u6790HTML\u4ee3\u7801\u627e\u5230\u4e0b\u4e00\u9875\u7684URL\uff0c\u7136\u540e\u7ee7\u7eed\u8bf7\u6c42\u548c\u89e3\u6790\u4e0b\u4e00\u9875\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528requests\u548cBeautifulSoup\u89e3\u6790HTML<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528<code>requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528<code>BeautifulSoup<\/code>\u89e3\u6790HTML\u4ee3\u7801\u3002<\/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\/page1&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5<\/h4>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u3002\u901a\u5e38\uff0c\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u4f1a\u5728\u5206\u9875\u7ec4\u4ef6\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u67e5\u627e\u7279\u5b9a\u7684HTML\u6807\u7b7e\u548c\u5c5e\u6027\u6765\u83b7\u53d6\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">next_page = soup.find(&#39;a&#39;, {&#39;class&#39;: &#39;next&#39;}).get(&#39;href&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u6784\u9020\u4e0b\u4e00\u9875\u7684URL\u5e76\u7ee7\u7eed\u722c\u53d6<\/h4>\n<\/p>\n<p><p>\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u627e\u5230\u7684\u94fe\u63a5\u6784\u9020\u4e0b\u4e00\u9875\u7684URL\uff0c\u5e76\u7ee7\u7eed\u53d1\u9001\u8bf7\u6c42\u722c\u53d6\u4e0b\u4e00\u9875\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">next_url = &#39;http:\/\/example.com&#39; + next_page<\/p>\n<p>response = requests.get(next_url)<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u6a21\u62df\u70b9\u51fb\u7ffb\u9875<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u67d0\u4e9b\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u7684\u7f51\u7ad9\uff0c\u4ec5\u4ec5\u901a\u8fc7\u89e3\u6790HTML\u4ee3\u7801\u65e0\u6cd5\u83b7\u53d6\u4e0b\u4e00\u9875\u7684\u6570\u636e\u3002\u8fd9\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u5982Selenium\uff0c\u6765\u6a21\u62df\u7528\u6237\u64cd\u4f5c\u8fdb\u884c\u7ffb\u9875\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5Selenium\u548cWebDriver<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u5b89\u88c5Selenium\u548c\u5bf9\u5e94\u7684WebDriver\u3002\u4ee5Chrome\u6d4f\u89c8\u5668\u4e3a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0b\u8f7dChromeDriver\u5e76\u5c06\u5176\u8def\u5f84\u6dfb\u52a0\u5230\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n<p><h4>2. \u4f7f\u7528Selenium\u8fdb\u884c\u7ffb\u9875<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u6253\u5f00\u7f51\u9875\uff0c\u627e\u5230\u5e76\u70b9\u51fb\u4e0b\u4e00\u9875\u6309\u94ae\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.common.by import By<\/p>\n<p>from selenium.webdriver.common.keys import Keys<\/p>\n<p>from selenium.webdriver.common.action_ch<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>ns import ActionChains<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;http:\/\/example.com\/page1&#39;)<\/p>\n<h2><strong>\u627e\u5230\u4e0b\u4e00\u9875\u6309\u94ae\u5e76\u70b9\u51fb<\/strong><\/h2>\n<p>next_button = driver.find_element(By.CLASS_NAME, &#39;next&#39;)<\/p>\n<p>next_button.click()<\/p>\n<h2><strong>\u7b49\u5f85\u9875\u9762\u52a0\u8f7d<\/strong><\/h2>\n<p>driver.implicitly_wait(5)<\/p>\n<h2><strong>\u83b7\u53d6\u65b0\u7684\u9875\u9762\u5185\u5bb9<\/strong><\/h2>\n<p>html = driver.page_source<\/p>\n<p>soup = BeautifulSoup(html, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528Scrapy\u6846\u67b6<\/h3>\n<\/p>\n<p><p>Scrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u5185\u7f6e\u4e86\u591a\u79cd\u529f\u80fd\uff0c\u5305\u62ec\u5904\u7406\u7ffb\u9875\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Scrapy\u8f7b\u677e\u5730\u722c\u53d6\u591a\u9875\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u5b89\u88c5Scrapy<\/h4>\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><pre><code class=\"language-bash\">scrapy startproject myproject<\/p>\n<p>cd myproject<\/p>\n<p>scrapy genspider myspider example.com<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h4>\n<\/p>\n<p><p>\u5728\u751f\u6210\u7684<code>myspider.py<\/code>\u6587\u4ef6\u4e2d\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff0c\u5904\u7406\u7ffb\u9875\u903b\u8f91\u3002<\/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\/page1&#39;]<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        # \u5904\u7406\u5f53\u524d\u9875\u9762\u7684\u6570\u636e<\/p>\n<p>        for item in response.css(&#39;div.item&#39;):<\/p>\n<p>            yield {<\/p>\n<p>                &#39;title&#39;: item.css(&#39;h2::text&#39;).get(),<\/p>\n<p>                &#39;link&#39;: item.css(&#39;a::attr(href)&#39;).get(),<\/p>\n<p>            }<\/p>\n<p>        # \u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u5e76\u7ee7\u7eed\u722c\u53d6<\/p>\n<p>        next_page = response.css(&#39;a.next::attr(href)&#39;).get()<\/p>\n<p>        if next_page:<\/p>\n<p>            yield response.follow(next_page, self.parse)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u7684\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u53cd\u722c\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u6211\u4eec\u9700\u8981\u91c7\u53d6\u4e00\u5b9a\u7684\u63aa\u65bd\u6765\u7ed5\u8fc7\u8fd9\u4e9b\u9650\u5236\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528\u4ee3\u7406IP<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406IP\uff0c\u6211\u4eec\u53ef\u4ee5\u907f\u514d\u56e0\u9891\u7e41\u8bf7\u6c42\u800c\u88ab\u5c01\u7981IP\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/proxy_ip:proxy_port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;https:\/\/proxy_ip:proxy_port&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u6dfb\u52a0\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n<p><p>\u6dfb\u52a0\u8bf7\u6c42\u5934\u53ef\u4ee5\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\uff0c\u51cf\u5c11\u88ab\u68c0\u6d4b\u4e3a\u722c\u866b\u7684\u98ce\u9669\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">headers = {<\/p>\n<p>    &#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\/537.3&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3. \u4f7f\u7528\u968f\u673a\u5ef6\u8fdf<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u5728\u6bcf\u6b21\u8bf7\u6c42\u4e4b\u95f4\u6dfb\u52a0\u968f\u673a\u5ef6\u8fdf\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u6a21\u62df\u4eba\u7c7b\u64cd\u4f5c\uff0c\u964d\u4f4e\u88ab\u53cd\u722c\u673a\u5236\u68c0\u6d4b\u5230\u7684\u6982\u7387\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>import random<\/p>\n<p>time.sleep(random.uniform(1, 3))<\/p>\n<p>response = requests.get(url)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u4e00\u4e9b\u5185\u5bb9\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u7ad9\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u6216Scrapy-Splash\u6765\u5904\u7406\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528Selenium<\/h4>\n<\/p>\n<p><p>Selenium\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u9002\u7528\u4e8e\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.common.by import By<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;http:\/\/example.com&#39;)<\/p>\n<h2><strong>\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n<p>driver.implicitly_wait(5)<\/p>\n<h2><strong>\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9<\/strong><\/h2>\n<p>html = driver.page_source<\/p>\n<p>soup = BeautifulSoup(html, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u4f7f\u7528Scrapy-Splash<\/h4>\n<\/p>\n<p><p>Scrapy-Splash\u662f\u4e00\u4e2aScrapy\u63d2\u4ef6\uff0c\u4f7f\u7528Splash\u6e32\u67d3JavaScript\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u5b89\u88c5Scrapy-Splash\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install scrapy-splash<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728Scrapy\u9879\u76ee\u7684<code>settings.py<\/code>\u4e2d\u6dfb\u52a0Splash\u914d\u7f6e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">SPLASH_URL = &#39;http:\/\/localhost:8050&#39;<\/p>\n<p>DOWNLOADER_MIDDLEWARES = {<\/p>\n<p>    &#39;scrapy_splash.SplashCookiesMiddleware&#39;: 723,<\/p>\n<p>    &#39;scrapy_splash.SplashMiddleware&#39;: 725,<\/p>\n<p>    &#39;scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware&#39;: 810,<\/p>\n<p>}<\/p>\n<p>SPIDER_MIDDLEWARES = {<\/p>\n<p>    &#39;scrapy_splash.SplashDeduplicateArgsMiddleware&#39;: 100,<\/p>\n<p>}<\/p>\n<p>DUPEFILTER_CLASS = &#39;scrapy_splash.SplashAwareDupeFilter&#39;<\/p>\n<p>HTTPCACHE_STORAGE = &#39;scrapy_splash.SplashAwareFSCacheStorage&#39;<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u722c\u866b\u4ee3\u7801\u4e2d\u4f7f\u7528SplashRequest\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import scrapy<\/p>\n<p>from scrapy_splash import SplashRequest<\/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 start_requests(self):<\/p>\n<p>        for url in self.start_urls:<\/p>\n<p>            yield SplashRequest(url, self.parse, args={&#39;wait&#39;: 2})<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        # \u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u5185\u5bb9<\/p>\n<p>        for item in response.css(&#39;div.item&#39;):<\/p>\n<p>            yield {<\/p>\n<p>                &#39;title&#39;: item.css(&#39;h2::text&#39;).get(),<\/p>\n<p>                &#39;link&#39;: item.css(&#39;a::attr(href)&#39;).get(),<\/p>\n<p>            }<\/p>\n<p>        # \u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\u5e76\u7ee7\u7eed\u722c\u53d6<\/p>\n<p>        next_page = response.css(&#39;a.next::attr(href)&#39;).get()<\/p>\n<p>        if next_page:<\/p>\n<p>            yield SplashRequest(response.urljoin(next_page), self.parse, args={&#39;wait&#39;: 2})<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u4e86\u51e0\u79cd\u5e38\u89c1\u7684Python\u722c\u53d6\u4e0b\u4e00\u9875\u7684\u65b9\u6cd5\uff0c\u5305\u62ec\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5\u3001\u6a21\u62df\u70b9\u51fb\u7ffb\u9875\u4ee5\u53ca\u4f7f\u7528Scrapy\u6846\u67b6\u3002\u6211\u4eec\u8fd8\u8ba8\u8bba\u4e86\u5982\u4f55\u5904\u7406\u53cd\u722c\u673a\u5236\u548c\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u3002\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\u548c\u6280\u5de7\uff0c\u60a8\u53ef\u4ee5\u66f4\u6709\u6548\u5730\u722c\u53d6\u591a\u9875\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u65e0\u8bba\u662f\u7b80\u5355\u7684\u9759\u6001\u7f51\u9875\u8fd8\u662f\u590d\u6742\u7684\u52a8\u6001\u5185\u5bb9\uff0c\u901a\u8fc7\u638c\u63e1\u8fd9\u4e9b\u6280\u672f\uff0c\u60a8\u90fd\u53ef\u4ee5\u7075\u6d3b\u5730\u5e94\u5bf9\u5404\u79cd\u722c\u53d6\u573a\u666f\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u4e2d\u7684\u4e0b\u4e00\u9875\u5185\u5bb9\uff1f<\/strong><\/p>\n<p>\u5728Python\u4e2d\uff0c\u722c\u53d6\u7f51\u9875\u7684\u4e0b\u4e00\u9875\u901a\u5e38\u9700\u8981\u89e3\u6790\u5f53\u524d\u9875\u9762\u7684\u7ed3\u6784\uff0c\u5bfb\u627e\u201c\u4e0b\u4e00\u9875\u201d\u94fe\u63a5\u7684URL\u3002\u53ef\u4ee5\u4f7f\u7528\u5e93\u5982BeautifulSoup\u548crequests\u6765\u5b9e\u73b0\u8fd9\u4e2a\u8fc7\u7a0b\u3002\u5177\u4f53\u6b65\u9aa4\u5305\u62ec\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u89e3\u6790HTML\u4ee5\u627e\u5230\u4e0b\u4e00\u9875\u7684\u94fe\u63a5\uff0c\u6700\u540e\u4f7f\u7528\u76f8\u540c\u7684\u65b9\u5f0f\u8bf7\u6c42\u4e0b\u4e00\u9875\u5185\u5bb9\u5e76\u7ee7\u7eed\u722c\u53d6\u3002<\/p>\n<p><strong>\u4f7f\u7528requests\u548cBeautifulSoup\u65f6\uff0c\u5982\u4f55\u5904\u7406\u5206\u9875\uff1f<\/strong><\/p>\n<p>\u5904\u7406\u5206\u9875\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7BeautifulSoup\u89e3\u6790HTML\uff0c\u627e\u5230\u201c\u4e0b\u4e00\u9875\u201d\u94fe\u63a5\u3002\u901a\u5e38\uff0c\u8fd9\u4e2a\u94fe\u63a5\u4f1a\u6709\u7279\u5b9a\u7684CSS\u7c7b\u6216ID\uff0c\u53ef\u4ee5\u901a\u8fc7\u67e5\u627e\u8fd9\u4e9b\u7279\u5f81\u6765\u63d0\u53d6URL\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u6709\u65f6\u9700\u8981\u5904\u7406JavaScript\u751f\u6210\u7684\u5185\u5bb9\uff0c\u8fd9\u79cd\u60c5\u51b5\u4e0b\u53ef\u4ee5\u8003\u8651\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u5982\u4f55\u907f\u514d\u88ab\u7f51\u7ad9\u5c01\u7981\uff1f<\/strong><\/p>\n<p>\u4e3a\u4e86\u907f\u514d\u88ab\u7f51\u7ad9\u5c01\u7981\uff0c\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u6709\u6548\u7684\u63aa\u65bd\u3002\u9996\u5148\uff0c\u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u53d1\u9001\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u3002\u5176\u6b21\uff0c\u4f7f\u7528\u968f\u673a\u7684User-Agent\u6765\u6a21\u62df\u4e0d\u540c\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002\u6b64\u5916\uff0c\u8003\u8651\u4f7f\u7528\u4ee3\u7406IP\u6765\u5206\u6563\u8bf7\u6c42\u6765\u6e90\uff0c\u51cf\u5c11\u88ab\u68c0\u6d4b\u7684\u98ce\u9669\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u9700\u8981\u767b\u5f55\u7684\u7f51\u7ad9\u7684\u4e0b\u4e00\u9875\u722c\u53d6\uff1f<\/strong><\/p>\n<p>\u5bf9\u4e8e\u9700\u8981\u767b\u5f55\u7684\u7f51\u7ad9\uff0c\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u7684\u4f1a\u8bdd\u529f\u80fd\u3002\u9996\u5148\uff0c\u6a21\u62df\u767b\u5f55\u8fc7\u7a0b\uff0c\u4fdd\u5b58\u4f1a\u8bdd\u4fe1\u606f\u3002\u767b\u5f55\u540e\uff0c\u4f7f\u7528\u76f8\u540c\u7684\u4f1a\u8bdd\u5bf9\u8c61\u53d1\u9001\u8bf7\u6c42\u4ee5\u83b7\u53d6\u4e0b\u4e00\u9875\u5185\u5bb9\u3002\u5728\u5904\u7406\u8fd9\u79cd\u60c5\u51b5\u65f6\uff0c\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684\u722c\u53d6\u89c4\u5219\u548c\u6761\u6b3e\uff0c\u4ee5\u514d\u9020\u6210\u4e0d\u5fc5\u8981\u7684\u9ebb\u70e6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6\u4e0b\u4e00\u9875\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u89e3\u6790\u4e0b\u4e00\u9875\u94fe\u63a5\u3001\u6a21\u62df\u70b9\u51fb\u7ffb\u9875\u3001\u4f7f\u7528Selenium\u7b49\u3002 \u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6 [&hellip;]","protected":false},"author":3,"featured_media":1037180,"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\/1037172"}],"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=1037172"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1037172\/revisions"}],"predecessor-version":[{"id":1037182,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1037172\/revisions\/1037182"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1037180"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1037172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1037172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1037172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}