{"id":1115967,"date":"2025-01-08T18:11:52","date_gmt":"2025-01-08T10:11:52","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1115967.html"},"modified":"2025-01-08T18:11:54","modified_gmt":"2025-01-08T10:11:54","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e6%9d%a5%e7%88%ac%e5%8f%96%e7%bd%91%e7%ab%99%e8%af%84%e4%bb%b7%e4%bf%a1%e6%81%af","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1115967.html","title":{"rendered":"\u5982\u4f55\u7528python\u6765\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25080506\/6d35866c-c76d-4b89-b15c-08b5b5a46505.webp\" alt=\"\u5982\u4f55\u7528python\u6765\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528Python\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f\u7684\u6b65\u9aa4\u5305\u62ec\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u5185\u5bb9\u3001\u5904\u7406\u6570\u636e\u3001\u4ee5\u53ca\u5b58\u50a8\u6570\u636e\u3002<\/strong>\u5176\u4e2d\uff0c\u9009\u62e9\u5408\u9002\u7684\u5e93\u5982BeautifulSoup\u3001Requests\u548cSelenium\u662f\u975e\u5e38\u91cd\u8981\u7684\u4e00\u6b65\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63a2\u8ba8\u5176\u4e2d\u7684\u6bcf\u4e2a\u6b65\u9aa4\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/p>\n<p>\u5728Python\u4e2d\uff0c\u722c\u53d6\u7f51\u7ad9\u6570\u636e\u901a\u5e38\u4f1a\u4f7f\u7528\u4e00\u4e9b\u4e13\u95e8\u7684\u5e93\u3002\u6700\u5e38\u89c1\u7684\u5e93\u5305\u62ecRequests\u3001BeautifulSoup\u548cSelenium\u3002\u6bcf\u4e2a\u5e93\u90fd\u6709\u5176\u7279\u5b9a\u7684\u7528\u9014\u548c\u4f18\u52bf\u3002<\/p>\n<\/p>\n<p><p>1\u3001Requests\u5e93<\/p>\n<p>Requests\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u3002\u5b83\u652f\u6301GET\u3001POST\u7b49\u591a\u79cdHTTP\u8bf7\u6c42\u65b9\u5f0f\uff0c\u5e76\u4e14\u6613\u4e8e\u5904\u7406\u54cd\u5e94\u5185\u5bb9\u3002<\/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.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>2\u3001BeautifulSoup\u5e93<\/p>\n<p>BeautifulSoup\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\u3002\u5b83\u80fd\u591f\u9ad8\u6548\u5730\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u63d0\u53d6\u9700\u8981\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p>print(soup.prettify())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>3\u3001Selenium\u5e93<\/p>\n<p>Selenium\u5e93\u4e3b\u8981\u7528\u4e8e\u81ea\u52a8\u5316\u6d4b\u8bd5\uff0c\u4f46\u4e5f\u53ef\u4ee5\u7528\u4e8e\u7f51\u9875\u722c\u53d6\u3002\u5b83\u80fd\u591f\u6a21\u62df\u7528\u6237\u64cd\u4f5c\uff0c\u5982\u70b9\u51fb\u6309\u94ae\u3001\u6eda\u52a8\u9875\u9762\u7b49\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>content = driver.page_source<\/p>\n<p>print(content)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/p>\n<p>\u9009\u62e9\u5408\u9002\u7684\u5e93\u540e\uff0c\u4e0b\u4e00\u6b65\u662f\u53d1\u9001HTTP\u8bf7\u6c42\u3002\u8fd9\u4e00\u6b65\u4e3b\u8981\u662f\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u89e3\u6790HTML\u5185\u5bb9<\/p>\n<p>\u83b7\u53d6\u5230\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u9700\u8981\u5bf9\u5176\u8fdb\u884c\u89e3\u6790\uff0c\u4ee5\u63d0\u53d6\u51fa\u9700\u8981\u7684\u8bc4\u4ef7\u4fe1\u606f\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>reviews = soup.find_all(&#39;div&#39;, class_=&#39;review&#39;)<\/p>\n<p>for review in reviews:<\/p>\n<p>    print(review.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u5904\u7406\u6570\u636e<\/p>\n<p>\u89e3\u6790\u51fa\u8bc4\u4ef7\u4fe1\u606f\u540e\uff0c\u53ef\u80fd\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u4e00\u4e9b\u5904\u7406\u3002\u4f8b\u5982\uff0c\u53bb\u9664\u591a\u4f59\u7684\u7a7a\u683c\u3001\u6362\u884c\u7b26\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5b57\u7b26\u4e32\u5904\u7406\u51fd\u6570\u6765\u5b8c\u6210\u8fd9\u4e9b\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for review in reviews:<\/p>\n<p>    review_text = review.text.strip()<\/p>\n<p>    print(review_text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u5b58\u50a8\u6570\u636e<\/p>\n<p>\u6700\u540e\uff0c\u5c06\u5904\u7406\u540e\u7684\u8bc4\u4ef7\u4fe1\u606f\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u3001JSON\u6587\u4ef6\u6216SQL\u6570\u636e\u5e93\u4e2d\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<p>with open(&#39;reviews.csv&#39;, &#39;w&#39;, newline=&#39;&#39;, encoding=&#39;utf-8&#39;) as csvfile:<\/p>\n<p>    writer = csv.writer(csvfile)<\/p>\n<p>    writer.writerow([&#39;Review&#39;])<\/p>\n<p>    for review in reviews:<\/p>\n<p>        review_text = review.text.strip()<\/p>\n<p>        writer.writerow([review_text])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\">import json<\/p>\n<p>reviews_list = [review.text.strip() for review in reviews]<\/p>\n<p>with open(&#39;reviews.json&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as jsonfile:<\/p>\n<p>    json.dump(reviews_list, jsonfile, ensure_ascii=False)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\">import sqlite3<\/p>\n<p>conn = sqlite3.connect(&#39;reviews.db&#39;)<\/p>\n<p>c = conn.cursor()<\/p>\n<p>c.execute(&#39;&#39;&#39;CREATE TABLE reviews (review TEXT)&#39;&#39;&#39;)<\/p>\n<p>for review in reviews:<\/p>\n<p>    review_text = review.text.strip()<\/p>\n<p>    c.execute(&quot;INSERT INTO reviews (review) VALUES (?)&quot;, (review_text,))<\/p>\n<p>conn.commit()<\/p>\n<p>conn.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u8be6\u7ec6\u6b65\u9aa4\u548c\u4ee3\u7801\u793a\u4f8b<\/h3>\n<\/p>\n<p><h4>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/h4>\n<\/p>\n<p><p>\u5728\u9009\u62e9\u5e93\u65f6\uff0c\u5e94\u6839\u636e\u5177\u4f53\u9700\u6c42\u548c\u7f51\u9875\u7ed3\u6784\u8fdb\u884c\u9009\u62e9\u3002\u5bf9\u4e8e\u9759\u6001\u7f51\u9875\uff0cRequests\u548cBeautifulSoup\u8db3\u4ee5\u5e94\u5bf9\uff1b\u5bf9\u4e8e\u52a8\u6001\u7f51\u9875\uff0cSelenium\u53ef\u80fd\u662f\u66f4\u597d\u7684\u9009\u62e9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u4f7f\u7528Requests\u5e93\u53d1\u9001\u8bf7\u6c42<\/p>\n<p>import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\"># \u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790HTML<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>reviews = soup.find_all(&#39;div&#39;, class_=&#39;review&#39;)<\/p>\n<p>for review in reviews:<\/p>\n<p>    print(review.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\"># \u4f7f\u7528Selenium\u5e93\u83b7\u53d6\u52a8\u6001\u5185\u5bb9<\/p>\n<p>from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>content = driver.page_source<\/p>\n<p>print(content)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u53d1\u9001HTTP\u8bf7\u6c42\u662f\u722c\u53d6\u7f51\u9875\u7684\u7b2c\u4e00\u6b65\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u4e09\u3001\u89e3\u6790HTML\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u7f51\u9875\u7684HTML\u5185\u5bb9\u540e\uff0c\u9700\u8981\u5bf9\u5176\u8fdb\u884c\u89e3\u6790\uff0c\u4ee5\u63d0\u53d6\u51fa\u9700\u8981\u7684\u8bc4\u4ef7\u4fe1\u606f\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>reviews = soup.find_all(&#39;div&#39;, class_=&#39;review&#39;)<\/p>\n<p>for review in reviews:<\/p>\n<p>    print(review.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u56db\u3001\u5904\u7406\u6570\u636e<\/h4>\n<\/p>\n<p><p>\u89e3\u6790\u51fa\u8bc4\u4ef7\u4fe1\u606f\u540e\uff0c\u53ef\u80fd\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u4e00\u4e9b\u5904\u7406\u3002\u4f8b\u5982\uff0c\u53bb\u9664\u591a\u4f59\u7684\u7a7a\u683c\u3001\u6362\u884c\u7b26\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5b57\u7b26\u4e32\u5904\u7406\u51fd\u6570\u6765\u5b8c\u6210\u8fd9\u4e9b\u64cd\u4f5c\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for review in reviews:<\/p>\n<p>    review_text = review.text.strip()<\/p>\n<p>    print(review_text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>\u4e94\u3001\u5b58\u50a8\u6570\u636e<\/h4>\n<\/p>\n<p><p>\u6700\u540e\uff0c\u5c06\u5904\u7406\u540e\u7684\u8bc4\u4ef7\u4fe1\u606f\u5b58\u50a8\u5230\u6587\u4ef6\u6216\u6570\u636e\u5e93\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u3001JSON\u6587\u4ef6\u6216SQL\u6570\u636e\u5e93\u4e2d\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5b58\u50a8\u5230CSV\u6587\u4ef6<\/p>\n<p>import csv<\/p>\n<p>with open(&#39;reviews.csv&#39;, &#39;w&#39;, newline=&#39;&#39;, encoding=&#39;utf-8&#39;) as csvfile:<\/p>\n<p>    writer = csv.writer(csvfile)<\/p>\n<p>    writer.writerow([&#39;Review&#39;])<\/p>\n<p>    for review in reviews:<\/p>\n<p>        review_text = review.text.strip()<\/p>\n<p>        writer.writerow([review_text])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5b58\u50a8\u5230JSON\u6587\u4ef6<\/p>\n<p>import json<\/p>\n<p>reviews_list = [review.text.strip() for review in reviews]<\/p>\n<p>with open(&#39;reviews.json&#39;, &#39;w&#39;, encoding=&#39;utf-8&#39;) as jsonfile:<\/p>\n<p>    json.dump(reviews_list, jsonfile, ensure_ascii=False)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5b58\u50a8\u5230SQL\u6570\u636e\u5e93<\/p>\n<p>import sqlite3<\/p>\n<p>conn = sqlite3.connect(&#39;reviews.db&#39;)<\/p>\n<p>c = conn.cursor()<\/p>\n<p>c.execute(&#39;&#39;&#39;CREATE TABLE reviews (review TEXT)&#39;&#39;&#39;)<\/p>\n<p>for review in reviews:<\/p>\n<p>    review_text = review.text.strip()<\/p>\n<p>    c.execute(&quot;INSERT INTO reviews (review) VALUES (?)&quot;, (review_text,))<\/p>\n<p>conn.commit()<\/p>\n<p>conn.close()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u5904\u7406\u52a8\u6001\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u7684\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u4f7f\u7528Requests\u5e93\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u5185\u5bb9\u3002\u8fd9\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6765\u5904\u7406\u52a8\u6001\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\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.support.ui import WebDriverW<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>t<\/p>\n<p>from selenium.webdriver.support import expected_conditions as EC<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>try:<\/p>\n<p>    WebDriverWait(driver, 10).until(<\/p>\n<p>        EC.presence_of_element_located((By.CLASS_NAME, &#39;review&#39;))<\/p>\n<p>    )<\/p>\n<p>    content = driver.page_source<\/p>\n<p>    soup = BeautifulSoup(content, &#39;html.parser&#39;)<\/p>\n<p>    reviews = soup.find_all(&#39;div&#39;, class_=&#39;review&#39;)<\/p>\n<p>    for review in reviews:<\/p>\n<p>        print(review.text)<\/p>\n<p>finally:<\/p>\n<p>    driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u4f7f\u7528\u53cd\u722c\u866b\u673a\u5236\u6765\u963b\u6b62\u81ea\u52a8\u5316\u8bbf\u95ee\u3002\u8fd9\u4e9b\u673a\u5236\u53ef\u80fd\u5305\u62ec\u9a8c\u8bc1\u7801\u3001IP\u5c01\u9501\u3001\u8bf7\u6c42\u9891\u7387\u9650\u5236\u7b49\u3002\u4e3a\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9b\u7b56\u7565\uff1a<\/p>\n<\/p>\n<p><p>1\u3001\u4f7f\u7528\u4ee3\u7406<\/p>\n<p>\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406\uff0c\u53ef\u4ee5\u9690\u85cf\u771f\u5b9e\u7684IP\u5730\u5740\uff0c\u907f\u514dIP\u5c01\u9501\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/10.10.1.10:3128&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/10.10.1.10:1080&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>2\u3001\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/p>\n<p>\u901a\u8fc7\u8bbe\u7f6eUser-Agent\u7b49\u8bf7\u6c42\u5934\uff0c\u53ef\u4ee5\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u8bbf\u95ee\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><p>3\u3001\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694<\/p>\n<p>\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4IP\u88ab\u5c01\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import time<\/p>\n<p>time.sleep(2)<\/p>\n<p>response = requests.get(url)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u5904\u7406\u590d\u6742\u7f51\u9875\u7ed3\u6784<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u7684\u7ed3\u6784\u53ef\u80fd\u6bd4\u8f83\u590d\u6742\uff0c\u8bc4\u4ef7\u4fe1\u606f\u5d4c\u5957\u5728\u591a\u4e2a\u6807\u7b7e\u4e2d\u3002\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684\u5d4c\u5957\u67e5\u627e\u529f\u80fd\u6765\u5904\u7406\u590d\u6742\u7684\u7f51\u9875\u7ed3\u6784\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>review_sections = soup.find_all(&#39;div&#39;, class_=&#39;review-section&#39;)<\/p>\n<p>for section in review_sections:<\/p>\n<p>    reviews = section.find_all(&#39;div&#39;, class_=&#39;review&#39;)<\/p>\n<p>    for review in reviews:<\/p>\n<p>        print(review.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u5185\u5bb9\u3001\u5904\u7406\u6570\u636e\u548c\u5b58\u50a8\u6570\u636e\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u9ad8\u6548\u5730\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f\u3002\u540c\u65f6\uff0c\u5904\u7406\u52a8\u6001\u5185\u5bb9\u548c\u53cd\u722c\u866b\u673a\u5236\u4e5f\u662f\u722c\u866b\u5f00\u53d1\u4e2d\u7684\u91cd\u8981\u90e8\u5206\u3002\u901a\u8fc7\u5408\u7406\u7684\u7b56\u7565\u548c\u5de5\u5177\uff0c\u53ef\u4ee5\u6210\u529f\u5730\u83b7\u53d6\u5230\u9700\u8981\u7684\u8bc4\u4ef7\u4fe1\u606f\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u786e\u5b9a\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f\u7684\u5408\u6cd5\u6027\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u7f51\u9875\u722c\u53d6\u4e4b\u524d\uff0c\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u548c\u6761\u4ef6\u662f\u81f3\u5173\u91cd\u8981\u7684\u3002\u8bb8\u591a\u7f51\u7ad9\u5728\u5176robots.txt\u6587\u4ef6\u4e2d\u5217\u51fa\u4e86\u5141\u8bb8\u548c\u7981\u6b62\u722c\u53d6\u7684\u5185\u5bb9\u3002\u901a\u8fc7\u68c0\u67e5\u8fd9\u4e9b\u4fe1\u606f\uff0c\u4f60\u53ef\u4ee5\u5224\u65ad\u662f\u5426\u53ef\u4ee5\u5408\u6cd5\u5730\u722c\u53d6\u8be5\u7f51\u7ad9\u7684\u8bc4\u4ef7\u4fe1\u606f\u3002\u6b64\u5916\uff0c\u9075\u5faa\u7f51\u7ad9\u7684\u53cd\u722c\u866b\u653f\u7b56\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\uff0c\u786e\u4fdd\u4e0d\u4f1a\u5bf9\u7f51\u7ad9\u7684\u6b63\u5e38\u8fd0\u884c\u9020\u6210\u5f71\u54cd\u3002<\/p>\n<p><strong>\u4f7f\u7528Python\u722c\u53d6\u8bc4\u4ef7\u4fe1\u606f\u9700\u8981\u54ea\u4e9b\u5e93\u548c\u5de5\u5177\uff1f<\/strong><br \/>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5e93\u6765\u652f\u6301\u7f51\u9875\u722c\u53d6\uff0c\u5e38\u7528\u7684\u5305\u62ecRequests\u548cBeautiful Soup\u3002Requests\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautiful Soup\u5219\u7528\u4e8e\u89e3\u6790\u548c\u63d0\u53d6HTML\u6587\u6863\u4e2d\u7684\u6570\u636e\u3002\u6b64\u5916\uff0cScrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u8fdb\u884c\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002\u5982\u679c\u76ee\u6807\u7f51\u7ad9\u4f7f\u7528Ajax\u52a0\u8f7d\u6570\u636e\uff0c\u53ef\u80fd\u8fd8\u9700\u8981\u4f7f\u7528Selenium\u6216Playwright\u6765\u5904\u7406\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u722c\u53d6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u5b9e\u65bd\u53cd\u722c\u866b\u673a\u5236\u6765\u9632\u6b62\u673a\u5668\u4eba\u83b7\u53d6\u5176\u6570\u636e\u3002\u5982\u679c\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\u906d\u9047\u9650\u5236\uff0c\u53ef\u4ee5\u5c1d\u8bd5\u968f\u673a\u66f4\u6539\u8bf7\u6c42\u5934\uff08\u5982User-Agent\uff09\uff0c\u4f7f\u7528\u4ee3\u7406IP\u6765\u5206\u6563\u8bf7\u6c42\uff0c\u6216\u8005\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u65f6\u95f4\u3002\u6b64\u5916\uff0c\u8003\u8651\u4f7f\u7528\u9a8c\u8bc1\u7801\u8bc6\u522b\u670d\u52a1\uff0c\u5904\u7406\u9700\u8981\u4eba\u673a\u9a8c\u8bc1\u7684\u60c5\u51b5\u3002\u9002\u5f53\u7684\u7b56\u7565\u548c\u5de5\u5177\u53ef\u4ee5\u5e2e\u52a9\u4f60\u514b\u670d\u8fd9\u4e9b\u6311\u6218\uff0c\u987a\u5229\u83b7\u53d6\u8bc4\u4ef7\u4fe1\u606f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u722c\u53d6\u7f51\u7ad9\u8bc4\u4ef7\u4fe1\u606f\u7684\u6b65\u9aa4\u5305\u62ec\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u5185\u5bb9\u3001\u5904\u7406\u6570\u636e\u3001\u4ee5\u53ca\u5b58\u50a8 [&hellip;]","protected":false},"author":3,"featured_media":1115972,"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\/1115967"}],"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=1115967"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1115967\/revisions"}],"predecessor-version":[{"id":1115973,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1115967\/revisions\/1115973"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1115972"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1115967"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1115967"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1115967"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}