{"id":1100611,"date":"2025-01-08T15:41:37","date_gmt":"2025-01-08T07:41:37","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1100611.html"},"modified":"2025-01-08T15:41:40","modified_gmt":"2025-01-08T07:41:40","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%99%bb%e9%99%86%e7%bd%91%e9%a1%b5-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1100611.html","title":{"rendered":"\u5982\u4f55\u7528python\u767b\u9646\u7f51\u9875"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25063800\/418887d3-83d4-4037-b59c-ae0897265c83.webp\" alt=\"\u5982\u4f55\u7528python\u767b\u9646\u7f51\u9875\" \/><\/p>\n<p><p> <strong>\u5982\u4f55\u7528Python\u767b\u9646\u7f51\u9875<\/strong><\/p>\n<\/p>\n<p><p>\u7528Python\u767b\u9646\u7f51\u9875\u7684\u6838\u5fc3\u5728\u4e8e\u4f7f\u7528Python\u7684HTTP\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u5b8c\u6210\u8eab\u4efd\u9a8c\u8bc1\u548c\u6570\u636e\u6293\u53d6\u3002<strong>\u4f7f\u7528requests\u5e93\u3001\u5904\u7406Cookies\u3001\u89e3\u6790HTML\u8868\u5355\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/strong>\u662f\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u7684\u4e3b\u8981\u6b65\u9aa4\u3002\u7279\u522b\u5730\uff0c<strong>requests\u5e93<\/strong>\u662fPython\u4e2d\u8fdb\u884cHTTP\u8bf7\u6c42\u7684\u5f3a\u5927\u5de5\u5177\uff0c\u63d0\u4f9b\u4e86\u7b80\u6d01\u7684API\u6765\u5904\u7406\u5404\u79cdHTTP\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><p><strong>\u8be6\u7ec6\u63cf\u8ff0\u8bf7\u6c42\u5e93\uff1a<\/strong>requests\u5e93\u662fPython\u4e2d\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u7b2c\u4e09\u65b9\u5e93\u3002\u5b83\u652f\u6301GET\u3001POST\u3001PUT\u3001DELETE\u7b49\u5e38\u89c1\u7684HTTP\u65b9\u6cd5\uff0c\u5e76\u4e14\u53ef\u4ee5\u81ea\u52a8\u5904\u7406Cookies\u3001\u4f1a\u8bdd\u7ba1\u7406\u3001SSL\u9a8c\u8bc1\u7b49\u590d\u6742\u64cd\u4f5c\u3002\u4f7f\u7528requests\u5e93\u53ef\u4ee5\u8ba9\u4f60\u8f7b\u677e\u5730\u4e0e\u7f51\u7edc\u8d44\u6e90\u8fdb\u884c\u4ea4\u4e92\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u8bf7\u6c42\u5e93\u7684\u5b89\u88c5\u4e0e\u57fa\u7840\u64cd\u4f5c<\/h3>\n<\/p>\n<p><p><strong>1. \u5b89\u88c5requests\u5e93<\/strong><\/p>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u9700\u8981\u786e\u4fdd\u4f60\u5df2\u7ecf\u5b89\u88c5\u4e86requests\u5e93\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u6765\u5b89\u88c5\u5b83\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><strong>2. \u4f7f\u7528requests\u5e93\u8fdb\u884c\u57fa\u672c\u8bf7\u6c42<\/strong><\/p>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\uff0c\u4f60\u53ef\u4ee5\u53d1\u9001\u5404\u79cdHTTP\u8bf7\u6c42\uff0c\u4f8b\u5982GET\u548cPOST\u8bf7\u6c42\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684GET\u8bf7\u6c42\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>response = requests.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>print(response.status_code)  # \u8f93\u51fa\u72b6\u6001\u7801<\/p>\n<p>print(response.text)  # \u8f93\u51fa\u54cd\u5e94\u5185\u5bb9<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5bf9\u4e8ePOST\u8bf7\u6c42\uff0c\u4f60\u53ef\u4ee5\u53d1\u9001\u6570\u636e\u8868\u5355\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">data = {&#39;username&#39;: &#39;your_username&#39;, &#39;password&#39;: &#39;your_password&#39;}<\/p>\n<p>response = requests.post(&#39;https:\/\/example.com\/login&#39;, data=data)<\/p>\n<p>print(response.status_code)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u5904\u7406Cookies\u4e0e\u4f1a\u8bdd<\/h3>\n<\/p>\n<p><p><strong>1. \u4f1a\u8bdd\u5bf9\u8c61<\/strong><\/p>\n<\/p>\n<p><p>requests\u5e93\u7684Session\u5bf9\u8c61\u5141\u8bb8\u4f60\u8de8\u591a\u4e2a\u8bf7\u6c42\u4fdd\u6301\u4f1a\u8bdd\u72b6\u6001\uff0c\u5e76\u81ea\u52a8\u5904\u7406Cookies\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528Session\u5bf9\u8c61\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">session = requests.Session()<\/p>\n<h2><strong>\u9996\u6b21\u8bf7\u6c42\u83b7\u53d6Cookies<\/strong><\/h2>\n<p>response = session.get(&#39;https:\/\/example.com\/login&#39;)<\/p>\n<h2><strong>\u4f7f\u7528Cookies\u8fdb\u884c\u767b\u5f55<\/strong><\/h2>\n<p>login_data = {&#39;username&#39;: &#39;your_username&#39;, &#39;password&#39;: &#39;your_password&#39;}<\/p>\n<p>response = session.post(&#39;https:\/\/example.com\/login&#39;, data=login_data)<\/p>\n<p>print(response.status_code)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><strong>2. \u624b\u52a8\u5904\u7406Cookies<\/strong><\/p>\n<\/p>\n<p><p>\u4f60\u4e5f\u53ef\u4ee5\u624b\u52a8\u7ba1\u7406Cookies\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">response = requests.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>cookies = response.cookies<\/p>\n<h2><strong>\u4f7f\u7528\u83b7\u53d6\u7684Cookies\u53d1\u9001\u540e\u7eed\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/example.com\/somepage&#39;, cookies=cookies)<\/p>\n<p>print(response.status_code)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790HTML\u8868\u5355<\/h3>\n<\/p>\n<p><p>\u5728\u8bb8\u591a\u60c5\u51b5\u4e0b\uff0c\u767b\u5f55\u7f51\u9875\u9700\u8981\u586b\u5199HTML\u8868\u5355\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\u5e76\u63d0\u53d6\u8868\u5355\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p><strong>1. \u5b89\u88c5BeautifulSoup<\/strong><\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><strong>2. \u89e3\u6790HTML\u8868\u5355<\/strong><\/p>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u8868\u5355\u5e76\u63d0\u4ea4\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>import requests<\/p>\n<h2><strong>\u83b7\u53d6\u767b\u5f55\u9875\u9762<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/example.com\/login&#39;)<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u8868\u5355\u6570\u636e<\/strong><\/h2>\n<p>form = soup.find(&#39;form&#39;)<\/p>\n<p>login_data = {}<\/p>\n<p>for input_tag in form.find_all(&#39;input&#39;):<\/p>\n<p>    name = input_tag.get(&#39;name&#39;)<\/p>\n<p>    value = input_tag.get(&#39;value&#39;, &#39;&#39;)<\/p>\n<p>    login_data[name] = value<\/p>\n<h2><strong>\u586b\u5199\u7528\u6237\u540d\u548c\u5bc6\u7801<\/strong><\/h2>\n<p>login_data[&#39;username&#39;] = &#39;your_username&#39;<\/p>\n<p>login_data[&#39;password&#39;] = &#39;your_password&#39;<\/p>\n<h2><strong>\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n<p>action = form.get(&#39;action&#39;)<\/p>\n<p>post_url = &#39;https:\/\/example.com&#39; + action<\/p>\n<p>response = requests.post(post_url, data=login_data)<\/p>\n<p>print(response.status_code)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\u5019\uff0c\u4ec5\u4ec5\u53d1\u9001\u8bf7\u6c42\u548c\u5904\u7406Cookies\u662f\u4e0d\u591f\u7684\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u6a21\u62df\u6d4f\u89c8\u5668\u7684\u884c\u4e3a\u3002\u4f8b\u5982\uff0c\u5904\u7406JavaScript\u6e32\u67d3\u7684\u9875\u9762\u3002Selenium\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002<\/p>\n<\/p>\n<p><p><strong>1. \u5b89\u88c5Selenium<\/strong><\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><strong>2. \u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668<\/strong><\/p>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u8fdb\u884c\u7f51\u9875\u767b\u5f55\u7684\u793a\u4f8b\uff1a<\/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<h2><strong>\u542f\u52a8\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver = webdriver.Chrome()<\/p>\n<h2><strong>\u6253\u5f00\u767b\u5f55\u9875\u9762<\/strong><\/h2>\n<p>driver.get(&#39;https:\/\/example.com\/login&#39;)<\/p>\n<h2><strong>\u586b\u5199\u7528\u6237\u540d\u548c\u5bc6\u7801<\/strong><\/h2>\n<p>username_input = driver.find_element(By.NAME, &#39;username&#39;)<\/p>\n<p>password_input = driver.find_element(By.NAME, &#39;password&#39;)<\/p>\n<p>username_input.send_keys(&#39;your_username&#39;)<\/p>\n<p>password_input.send_keys(&#39;your_password&#39;)<\/p>\n<h2><strong>\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n<p>password_input.send_keys(Keys.RETURN)<\/p>\n<h2><strong>\u68c0\u67e5\u767b\u5f55\u7ed3\u679c<\/strong><\/h2>\n<p>print(driver.page_source)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528Python\u767b\u5f55\u7f51\u9875\u6d89\u53ca\u591a\u4e2a\u6b65\u9aa4\uff0c\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u5904\u7406Cookies\u3001\u89e3\u6790HTML\u8868\u5355\u4ee5\u53ca\u5728\u5fc5\u8981\u65f6\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002requests\u5e93\u662f\u5904\u7406HTTP\u8bf7\u6c42\u7684\u6838\u5fc3\u5de5\u5177\uff0c\u800cBeautifulSoup\u548cSelenium\u5219\u5206\u522b\u7528\u4e8e\u89e3\u6790HTML\u548c\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u638c\u63e1\u8fd9\u4e9b\u5de5\u5177\u548c\u6280\u672f\uff0c\u4f60\u53ef\u4ee5\u6784\u5efa\u5f3a\u5927\u7684\u81ea\u52a8\u5316\u811a\u672c\u6765\u5904\u7406\u5404\u79cd\u7f51\u9875\u4ea4\u4e92\u548c\u6570\u636e\u6293\u53d6\u4efb\u52a1\u3002\u8fd9\u4e0d\u4ec5\u53ef\u4ee5\u8282\u7701\u65f6\u95f4\u548c\u7cbe\u529b\uff0c\u8fd8\u80fd\u63d0\u9ad8\u5de5\u4f5c\u6548\u7387\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u6a21\u62df\u7f51\u9875\u767b\u5f55\uff1f<\/strong><br \/>\u4f7f\u7528Python\u6a21\u62df\u7f51\u9875\u767b\u5f55\u901a\u5e38\u6d89\u53ca\u5230\u4f7f\u7528\u5e93\u5982requests\u548cBeautifulSoup\u3002\u4f60\u53ef\u4ee5\u901a\u8fc7requests\u5e93\u53d1\u9001POST\u8bf7\u6c42\uff0c\u5e76\u5728\u8bf7\u6c42\u4e2d\u5305\u542b\u4f60\u7684\u767b\u5f55\u51ed\u8bc1\uff08\u5982\u7528\u6237\u540d\u548c\u5bc6\u7801\uff09\u3002\u6210\u529f\u540e\uff0c\u4f7f\u7528session\u5bf9\u8c61\u6765\u4fdd\u6301\u767b\u5f55\u72b6\u6001\uff0c\u5e76\u8bbf\u95ee\u9700\u8981\u6743\u9650\u7684\u9875\u9762\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\u5982\u4f55\u5904\u7406\u7f51\u9875\u7684\u9a8c\u8bc1\u7801\uff1f<\/strong><br \/>\u5982\u679c\u767b\u5f55\u9875\u9762\u8981\u6c42\u8f93\u5165\u9a8c\u8bc1\u7801\uff0c\u5904\u7406\u8d77\u6765\u4f1a\u590d\u6742\u4e00\u4e9b\u3002\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u56fe\u50cf\u8bc6\u522b\u5e93\uff0c\u5982Tesseract\u6216Pytesseract\u6765\u8bc6\u522b\u9a8c\u8bc1\u7801\u3002\u5982\u679c\u9a8c\u8bc1\u7801\u662f\u52a8\u6001\u751f\u6210\u7684\uff0c\u53ef\u80fd\u9700\u8981\u4f7f\u7528Selenium\u5e93\u6765\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u751a\u81f3\u901a\u8fc7\u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801\u6765\u5b8c\u6210\u767b\u5f55\u8fc7\u7a0b\u3002<\/p>\n<p><strong>\u6709\u54ea\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316\u64cd\u4f5c\uff1f<\/strong><br \/>Python\u4e2d\u6709\u591a\u4e2a\u5e93\u53ef\u4ee5\u5e2e\u52a9\u8fdb\u884c\u7f51\u9875\u81ea\u52a8\u5316\uff0c\u5305\u62ecSelenium\u3001Requests\u548cBeautifulSoup\u3002Selenium\u9002\u5408\u9700\u8981\u4e0eJavaScript\u4ea4\u4e92\u7684\u52a8\u6001\u7f51\u9875\uff0c\u800cRequests\u548cBeautifulSoup\u5219\u9002\u5408\u5904\u7406\u9759\u6001\u7f51\u9875\u7684\u8bf7\u6c42\u548c\u89e3\u6790\u3002\u6839\u636e\u4f60\u7684\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u5c06\u4f7f\u4f60\u7684\u81ea\u52a8\u5316\u8fc7\u7a0b\u66f4\u52a0\u9ad8\u6548\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528Python\u767b\u9646\u7f51\u9875 \u7528Python\u767b\u9646\u7f51\u9875\u7684\u6838\u5fc3\u5728\u4e8e\u4f7f\u7528Python\u7684HTTP\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u5b8c\u6210 [&hellip;]","protected":false},"author":3,"featured_media":1100619,"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\/1100611"}],"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=1100611"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100611\/revisions"}],"predecessor-version":[{"id":1100620,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100611\/revisions\/1100620"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1100619"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1100611"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1100611"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1100611"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}