{"id":1049397,"date":"2024-12-31T13:59:03","date_gmt":"2024-12-31T05:59:03","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1049397.html"},"modified":"2024-12-31T13:59:06","modified_gmt":"2024-12-31T05:59:06","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e7%99%be%e5%ba%a6%e6%96%87%e5%ba%93","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1049397.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u767e\u5ea6\u6587\u5e93"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u722c\u767e\u5ea6\u6587\u5e93\"<\/p>\n

\u5982\u4f55\u7528Python\u722c\u767e\u5ea6\u6587\u5e93<\/strong><\/p>\n<\/p>\n

\u722c\u53d6\u767e\u5ea6\u6587\u5e93\u5185\u5bb9\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u6b65\u9aa4\uff1a\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875HTML\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u3001\u6a21\u62df\u767b\u5f55\u83b7\u53d6\u6743\u9650\u3001\u5904\u7406JavaScript\u6e32\u67d3\u9875\u9762\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u6b65\u9aa4\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875HTML\u5185\u5bb9<\/h2>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u6765\u83b7\u53d6\u767e\u5ea6\u6587\u5e93\u9875\u9762\u7684HTML\u5185\u5bb9\u3002requests\u6a21\u5757\u662fPython\u4e2d\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u8bf7\u6c42\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u3002<\/p>\n<\/p>\n

import requests<\/p>\n
def get_html_content(url):<\/p>\n
    headers = {<\/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
    response = requests.get(url, headers=headers)<\/p>\n
    if response.status_code == 200:<\/p>\n
        return response.text<\/p>\n
    else:<\/p>\n
        return None<\/p>\n
url = 'https:\/\/wenku.bAI<\/a>du.com\/view\/some_document.html'<\/p>\n
html_content = get_html_content(url)<\/p>\n
print(html_content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875HTML\u5185\u5bb9<\/strong>\uff1a\u6211\u4eec\u9700\u8981\u6307\u5b9a\u8bf7\u6c42\u5934\uff08headers\uff09\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u4ee5\u9632\u6b62\u88ab\u767e\u5ea6\u6587\u5e93\u68c0\u6d4b\u5230\u662f\u722c\u866b\u8bf7\u6c42\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863<\/h2>\n<\/p>\n
\u83b7\u53d6\u5230HTML\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528BeautifulSoup\u6a21\u5757\u6765\u89e3\u6790HTML\u6587\u6863\u3002BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684Python\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
def parse_html_content(html_content):<\/p>\n
    soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n
    # Extract specific content based on the structure of the HTML document<\/p>\n
    title = soup.find('title').get_text()<\/p>\n
    paragraphs = soup.find_all('p')<\/p>\n
    document_content = []<\/p>\n
    for paragraph in paragraphs:<\/p>\n
        document_content.append(paragraph.get_text())<\/p>\n
    return title, document_content<\/p>\n
title, document_content = parse_html_content(html_content)<\/p>\n
print(f"Title: {title}")<\/p>\n
print("Content:")<\/p>\n
for paragraph in document_content:<\/p>\n
    print(paragraph)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863<\/strong>\uff1a\u6211\u4eec\u53ef\u4ee5\u6839\u636eHTML\u6587\u6863\u7684\u7ed3\u6784\u63d0\u53d6\u6240\u9700\u7684\u5185\u5bb9\uff0c\u4f8b\u5982\u6587\u6863\u6807\u9898\u548c\u6bb5\u843d\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u6a21\u62df\u767b\u5f55\u83b7\u53d6\u6743\u9650<\/h2>\n<\/p>\n
\u6709\u4e9b\u767e\u5ea6\u6587\u5e93\u6587\u6863\u9700\u8981\u767b\u5f55\u624d\u80fd\u67e5\u770b\u5168\u90e8\u5185\u5bb9\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u9700\u8981\u6a21\u62df\u767b\u5f55\u767e\u5ea6\u8d26\u53f7\uff0c\u4ee5\u83b7\u53d6\u67e5\u770b\u6587\u6863\u7684\u6743\u9650\u3002\u6a21\u62df\u767b\u5f55\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4f1a\u8bdd\uff08Session\uff09\u5bf9\u8c61\u6765\u4fdd\u6301\u767b\u5f55\u72b6\u6001\u3002<\/p>\n<\/p>\n
def login_baidu(username, password):<\/p>\n
    session = requests.Session()<\/p>\n
    login_url = 'https:\/\/passport.baidu.com\/v2\/?login'<\/p>\n
    payload = {<\/p>\n
        'username': username,<\/p>\n
        'password': password,<\/p>\n
        # Add other required login parameters<\/p>\n
    }<\/p>\n
    response = session.post(login_url, data=payload)<\/p>\n
    if response.status_code == 200 and '\u6210\u529f' in response.text:<\/p>\n
        return session<\/p>\n
    else:<\/p>\n
        return None<\/p>\n
username = 'your_username'<\/p>\n
password = 'your_password'<\/p>\n
session = login_baidu(username, password)<\/p>\n
if session:<\/p>\n
    url = 'https:\/\/wenku.baidu.com\/view\/some_document.html'<\/p>\n
    html_content = session.get(url).text<\/p>\n
    title, document_content = parse_html_content(html_content)<\/p>\n
    print(f"Title: {title}")<\/p>\n
    print("Content:")<\/p>\n
    for paragraph in document_content:<\/p>\n
        print(paragraph)<\/p>\n
else:<\/p>\n
    print("Login failed")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u6a21\u62df\u767b\u5f55\u83b7\u53d6\u6743\u9650<\/strong>\uff1a\u6211\u4eec\u9700\u8981\u4f7f\u7528\u4f1a\u8bdd\u5bf9\u8c61\u6765\u4fdd\u6301\u767b\u5f55\u72b6\u6001\uff0c\u5e76\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u643a\u5e26\u767b\u5f55\u540e\u7684Cookie\u4fe1\u606f\u3002<\/p>\n<\/p>\n
\u56db\u3001\u5904\u7406JavaScript\u6e32\u67d3\u9875\u9762<\/h2>\n<\/p>\n
\u6709\u4e9b\u767e\u5ea6\u6587\u5e93\u9875\u9762\u662f\u901a\u8fc7JavaScript\u6e32\u67d3\u7684\uff0crequests\u6a21\u5757\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u5185\u5bb9\u3002\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528Selenium\u7b49\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u83b7\u53d6\u5b8c\u6574\u7684\u9875\u9762\u5185\u5bb9\u3002<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
from selenium.webdriver.common.by import By<\/p>\n
from selenium.webdriver.chrome.service import Service<\/p>\n
from selenium.webdriver.chrome.options import Options<\/p>\n
def get_full_page_content(url):<\/p>\n
    chrome_options = Options()<\/p>\n
    chrome_options.add_argument('--headless')<\/p>\n
    chrome_options.add_argument('--disable-gpu')<\/p>\n
    service = Service('path_to_chromedriver')<\/p>\n
    driver = webdriver.Chrome(service=service, options=chrome_options)<\/p>\n
    driver.get(url)<\/p>\n
    # Wait for the page to fully load<\/p>\n
    driver.implicitly_wait(10)<\/p>\n
    full_page_content = driver.page_source<\/p>\n
    driver.quit()<\/p>\n
    return full_page_content<\/p>\n
url = 'https:\/\/wenku.baidu.com\/view\/some_document.html'<\/p>\n
full_page_content = get_full_page_content(url)<\/p>\n
title, document_content = parse_html_content(full_page_content)<\/p>\n
print(f"Title: {title}")<\/p>\n
print("Content:")<\/p>\n
for paragraph in document_content:<\/p>\n
    print(paragraph)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5904\u7406JavaScript\u6e32\u67d3\u9875\u9762<\/strong>\uff1a\u901a\u8fc7\u4f7f\u7528Selenium\u7b49\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\uff0c\u6211\u4eec\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u7b49\u5f85\u9875\u9762\u5b8c\u5168\u52a0\u8f7d\u540e\u83b7\u53d6\u5b8c\u6574\u7684\u9875\u9762\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u4fdd\u5b58\u548c\u5904\u7406\u722c\u53d6\u7684\u6570\u636e<\/h2>\n<\/p>\n
\u5728\u6210\u529f\u722c\u53d6\u5230\u767e\u5ea6\u6587\u5e93\u7684\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u53ef\u80fd\u9700\u8981\u5c06\u8fd9\u4e9b\u6570\u636e\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u5904\u7406\u548c\u5206\u6790\u3002<\/p>\n<\/p>\n
import json<\/p>\n
def save_to_file(title, document_content, filename):<\/p>\n
    with open(filename, 'w', encoding='utf-8') as f:<\/p>\n
        data = {<\/p>\n
            'title': title,<\/p>\n
            'content': document_content<\/p>\n
        }<\/p>\n
        json.dump(data, f, ensure_ascii=False, indent=4)<\/p>\n
filename = 'document.json'<\/p>\n
save_to_file(title, document_content, filename)<\/p>\n
print(f"Document saved to {filename}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4fdd\u5b58\u548c\u5904\u7406\u722c\u53d6\u7684\u6570\u636e<\/strong>\uff1a\u6211\u4eec\u53ef\u4ee5\u5c06\u722c\u53d6\u5230\u7684\u6587\u6863\u5185\u5bb9\u4fdd\u5b58\u4e3aJSON\u6587\u4ef6\uff0c\u4ee5\u4fbf\u540e\u7eed\u5904\u7406\u548c\u5206\u6790\u3002<\/p>\n<\/p>\n
\u603b\u7ed3<\/h2>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u722c\u53d6\u767e\u5ea6\u6587\u5e93\u7684\u5185\u5bb9\u3002\u9996\u5148\uff0c\u6211\u4eec\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875HTML\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u3002\u5bf9\u4e8e\u9700\u8981\u767b\u5f55\u7684\u6587\u6863\uff0c\u6211\u4eec\u53ef\u4ee5\u6a21\u62df\u767b\u5f55\u83b7\u53d6\u6743\u9650\uff0c\u5e76\u4f7f\u7528\u4f1a\u8bdd\u5bf9\u8c61\u4fdd\u6301\u767b\u5f55\u72b6\u6001\u3002\u5bf9\u4e8eJavaScript\u6e32\u67d3\u7684\u9875\u9762\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u7b49\u6d4f\u89c8\u5668\u81ea\u52a8\u5316\u5de5\u5177\u6765\u83b7\u53d6\u5b8c\u6574\u7684\u9875\u9762\u5185\u5bb9\u3002\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u722c\u53d6\u5230\u7684\u6570\u636e\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u540e\u7eed\u5904\u7406\u548c\u5206\u6790\u3002<\/p>\n<\/p>\n
\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u722c\u53d6\u767e\u5ea6\u6587\u5e93\u7b49\u7f51\u7ad9\u7684\u5185\u5bb9\u65f6\uff0c\u8bf7\u9075\u5b88\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\u548c\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\uff0c\u907f\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8fc7\u5927\u538b\u529b\u6216\u5f71\u54cd\u4ed6\u4eba\u6b63\u5e38\u4f7f\u7528\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u767e\u5ea6\u6587\u5e93\u4e2d\u7684\u6587\u6863\u5185\u5bb9\uff1f<\/strong>
\u8981\u83b7\u53d6\u767e\u5ea6\u6587\u5e93\u4e2d\u7684\u6587\u6863\u5185\u5bb9\uff0c\u60a8\u9700\u8981\u4f7f\u7528Python\u7684\u7f51\u7edc\u8bf7\u6c42\u5e93\uff08\u5982requests\uff09\u6765\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u89e3\u6790\u8fd4\u56de\u7684HTML\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528Beautiful Soup\u7b49\u5e93\u6765\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u53e6\u5916\uff0c\u60a8\u53ef\u80fd\u9700\u8981\u5904\u7406\u9875\u9762\u4e2d\u7684JavaScript\u5185\u5bb9\u6216\u4f7f\u7528\u4ee3\u7406\u6765\u907f\u514d\u88ab\u7f51\u7ad9\u5c01\u9501\u3002<\/p>\n
\u5728\u722c\u53d6\u767e\u5ea6\u6587\u5e93\u65f6\uff0c\u5982\u4f55\u5904\u7406\u53cd\u722c\u673a\u5236\uff1f<\/strong>
\u767e\u5ea6\u6587\u5e93\u53ef\u80fd\u4f1a\u91c7\u7528\u591a\u79cd\u53cd\u722c\u673a\u5236\uff0c\u5982IP\u5c01\u9501\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u4ee3\u7406IP\u8f6e\u6362\uff0c\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u65f6\u95f4\uff0c\u6a21\u62df\u7528\u6237\u884c\u4e3a\uff08\u5982\u968f\u673a\u7528\u6237\u4ee3\u7406\uff09\uff0c\u5e76\u5728\u5fc5\u8981\u65f6\u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801\u3002<\/p>\n
\u662f\u5426\u53ef\u4ee5\u4f7f\u7528Python\u5e93\u6765\u7b80\u5316\u767e\u5ea6\u6587\u5e93\u7684\u722c\u53d6\u8fc7\u7a0b\uff1f<\/strong>
\u786e\u5b9e\u53ef\u4ee5\u501f\u52a9\u4e00\u4e9b\u73b0\u6709\u7684Python\u5e93\u6765\u7b80\u5316\u722c\u53d6\u8fc7\u7a0b\u3002\u4f8b\u5982\uff0c\u4f7f\u7528Scrapy\u6846\u67b6\u53ef\u4ee5\u5feb\u901f\u6784\u5efa\u722c\u866b\uff0c\u800cPyppeteer\u6216Selenium\u53ef\u4ee5\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u7684\u9875\u9762\uff0c\u5e2e\u52a9\u63d0\u53d6\u9700\u8981\u7684\u5185\u5bb9\u3002\u8fd9\u4e9b\u5e93\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\uff0c\u80fd\u591f\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u7a33\u5b9a\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u7528Python\u722c\u767e\u5ea6\u6587\u5e93 \u722c\u53d6\u767e\u5ea6\u6587\u5e93\u5185\u5bb9\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u6b65\u9aa4\uff1a\u4f7f\u7528requests\u6a21\u5757\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875HT […]","protected":false},"author":3,"featured_media":1049408,"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\/1049397"}],"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=1049397"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1049397\/revisions"}],"predecessor-version":[{"id":1049412,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1049397\/revisions\/1049412"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1049408"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1049397"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1049397"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1049397"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}