{"id":1179338,"date":"2025-01-15T18:22:15","date_gmt":"2025-01-15T10:22:15","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1179338.html"},"modified":"2025-01-15T18:22:18","modified_gmt":"2025-01-15T10:22:18","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%bc%96%e7%bd%91%e8%b7%af%e7%88%ac%e8%99%ab","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1179338.html","title":{"rendered":"\u5982\u4f55\u7528Python\u7f16\u7f51\u8def\u722c\u866b"},"content":{"rendered":"

\"\u5982\u4f55\u7528Python\u7f16\u7f51\u8def\u722c\u866b\"<\/p>\n

\u8981\u7528Python\u7f16\u5199\u7f51\u7edc\u722c\u866b\uff0c\u9996\u5148\u9700\u8981\u4e86\u89e3\u4e00\u4e9b\u6838\u5fc3\u5de5\u5177\u548c\u6b65\u9aa4\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u5229\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/strong>\uff0c\u5176\u4e2d\u5229\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/strong>\u662f\u6700\u57fa\u7840\u4e14\u91cd\u8981\u7684\u4e00\u6b65\u3002<\/p>\n<\/p>\n

\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n

requests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u5e93\u4e4b\u4e00\u3002\u901a\u8fc7\u5b83\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5411\u76ee\u6807\u7f51\u7ad9\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n

import requests<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
if response.status_code == 200:<\/p>\n
    print(response.text)<\/p>\n
else:<\/p>\n
    print('FAI<\/a>led to retrieve the webpage')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86requests\u5e93\uff0c\u7136\u540e\u5b9a\u4e49\u4e86\u76ee\u6807URL\u3002\u901a\u8fc7requests.get(url)<\/code>\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u4fdd\u5b58\u5230response<\/code>\u53d8\u91cf\u4e2d\u3002\u5982\u679c\u8bf7\u6c42\u6210\u529f\uff08\u5373\u72b6\u6001\u7801\u4e3a200\uff09\uff0c\u6211\u4eec\u5c06\u6253\u5370\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u4e00\u3001\u4e86\u89e3HTTP\u8bf7\u6c42\u548c\u54cd\u5e94<\/h3>\n<\/p>\n
\u5728\u7f16\u5199\u7f51\u7edc\u722c\u866b\u4e4b\u524d\uff0c\u4e86\u89e3HTTP\u8bf7\u6c42\u548c\u54cd\u5e94\u662f\u81f3\u5173\u91cd\u8981\u7684\u3002HTTP\u8bf7\u6c42\u901a\u5e38\u5305\u62ecGET\u3001POST\u3001PUT\u3001DELETE\u7b49\u65b9\u6cd5\u3002GET\u8bf7\u6c42\u7528\u4e8e\u83b7\u53d6\u8d44\u6e90\uff0c\u800cPOST\u8bf7\u6c42\u7528\u4e8e\u63d0\u4ea4\u6570\u636e\u3002\u6bcf\u4e2a\u8bf7\u6c42\u90fd\u4f1a\u8fd4\u56de\u4e00\u4e2aHTTP\u54cd\u5e94\uff0c\u5176\u4e2d\u5305\u542b\u72b6\u6001\u7801\u3001\u54cd\u5e94\u5934\u548c\u54cd\u5e94\u4f53\u3002<\/p>\n<\/p>\n
GET\u8bf7\u6c42<\/h4>\n<\/p>\n
GET\u8bf7\u6c42\u7528\u4e8e\u4ece\u670d\u52a1\u5668\u83b7\u53d6\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
print('Status Code:', response.status_code)<\/p>\n
print('Response Headers:', response.headers)<\/p>\n
print('Response Body:', response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
POST\u8bf7\u6c42<\/h4>\n<\/p>\n
POST\u8bf7\u6c42\u7528\u4e8e\u5411\u670d\u52a1\u5668\u63d0\u4ea4\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528requests\u5e93\u53d1\u9001POST\u8bf7\u6c42\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com\/login'<\/p>\n
data = {'username': 'user', 'password': 'pass'}<\/p>\n
response = requests.post(url, data=data)<\/p>\n
print('Status Code:', response.status_code)<\/p>\n
print('Response Headers:', response.headers)<\/p>\n
print('Response Body:', response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u89e3\u6790HTML\u5185\u5bb9<\/h3>\n<\/p>\n
\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u4e0b\u4e00\u6b65\u662f\u89e3\u6790HTML\u5185\u5bb9\u3002BeautifulSoup\u662f\u4e00\u4e2a\u6d41\u884c\u7684Python\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u7b80\u5355\u7684API\u6765\u89e3\u6790\u548c\u904d\u5386HTML\u6587\u6863\u3002<\/p>\n<\/p>\n
\u5b89\u88c5BeautifulSoup<\/h4>\n<\/p>\n
\u4f7f\u7528pip\u5b89\u88c5BeautifulSoup\uff1a<\/p>\n<\/p>\n
pip install beautifulsoup4<\/p>\n
pip install lxml<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5e76\u63d0\u53d6\u6240\u6709\u94fe\u63a5\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
links = soup.find_all('a')<\/p>\n
for link in links:<\/p>\n
    print(link.get('href'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u53d1\u9001GET\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u7136\u540e\uff0c\u6211\u4eec\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\uff0c\u5e76\u63d0\u53d6\u6240\u6709\u7684\u94fe\u63a5\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n
\u8bb8\u591a\u7f51\u7ad9\u90fd\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u4ee5\u9632\u6b62\u5927\u91cf\u81ea\u52a8\u5316\u8bf7\u6c42\u3002\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u4e9b\u673a\u5236\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u6280\u5de7\uff0c\u5982\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u6dfb\u52a0\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406<\/strong>\u7b49\u3002<\/p>\n<\/p>\n
\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/h4>\n<\/p>\n
\u901a\u8fc7\u6dfb\u52a0User-Agent\u8bf7\u6c42\u5934\uff0c\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
headers = {'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
print(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n
\u4f7f\u7528\u4ee3\u7406\u53ef\u4ee5\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\uff0c\u4ece\u800c\u907f\u514d\u88ab\u7f51\u7ad9\u5c01\u7981\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
proxies = {'http': 'http:\/\/10.10.1.10:3128', 'https': 'http:\/\/10.10.1.10:1080'}<\/p>\n
response = requests.get(url, proxies=proxies)<\/p>\n
print(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5b58\u50a8\u6570\u636e<\/h3>\n<\/p>\n
\u722c\u53d6\u7684\u6570\u636e\u901a\u5e38\u9700\u8981\u5b58\u50a8\u5230\u672c\u5730\u6216\u6570\u636e\u5e93\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u7684\u5185\u7f6e\u6587\u4ef6\u64cd\u4f5c\u51fd\u6570\u3001SQLite\u3001MySQL\u7b49\u6765\u5b58\u50a8\u6570\u636e\u3002<\/p>\n<\/p>\n
\u5b58\u50a8\u5230\u672c\u5730\u6587\u4ef6<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5c06\u6570\u636e\u5b58\u50a8\u5230\u672c\u5730\u6587\u4ef6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
links = soup.find_all('a')<\/p>\n
with open('links.txt', 'w') as file:<\/p>\n
    for link in links:<\/p>\n
        file.write(link.get('href') + '\\n')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b58\u50a8\u5230SQLite\u6570\u636e\u5e93<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5c06\u6570\u636e\u5b58\u50a8\u5230SQLite\u6570\u636e\u5e93\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import sqlite3<\/p>\n
\u521b\u5efaSQLite\u6570\u636e\u5e93\u548c\u8868<\/strong><\/h2>\n
conn = sqlite3.connect('data.db')<\/p>\n
c = conn.cursor()<\/p>\n
c.execute('''CREATE TABLE IF NOT EXISTS links (url TEXT)''')<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
response = requests.get(url)<\/p>\n
soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
links = soup.find_all('a')<\/p>\n
for link in links:<\/p>\n
    c.execute('INSERT INTO links (url) VALUES (?)', (link.get('href'),))<\/p>\n
conn.commit()<\/p>\n
conn.close()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5904\u7406\u591a\u9875\u9762\u722c\u53d6<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u5f80\u5f80\u9700\u8981\u722c\u53d6\u591a\u4e2a\u9875\u9762\u7684\u6570\u636e\u3002\u8fd9\u65f6\u53ef\u4ee5\u4f7f\u7528\u5faa\u73af\u6216\u9012\u5f52\u6765\u904d\u5386\u6240\u6709\u9875\u9762\u3002<\/p>\n<\/p>\n
\u4f7f\u7528\u5faa\u73af\u904d\u5386\u9875\u9762<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528\u5faa\u73af\u904d\u5386\u9875\u9762\u5e76\u722c\u53d6\u6570\u636e\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
base_url = 'http:\/\/example.com\/page\/'<\/p>\n
for i in range(1, 11):<\/p>\n
    url = base_url + str(i)<\/p>\n
    response = requests.get(url)<\/p>\n
    soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
    links = soup.find_all('a')<\/p>\n
    for link in links:<\/p>\n
        print(link.get('href'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528\u9012\u5f52\u904d\u5386\u9875\u9762<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528\u9012\u5f52\u904d\u5386\u9875\u9762\u5e76\u722c\u53d6\u6570\u636e\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
def crawl_page(url, page):<\/p>\n
    full_url = url + str(page)<\/p>\n
    response = requests.get(full_url)<\/p>\n
    soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
    links = soup.find_all('a')<\/p>\n
    for link in links:<\/p>\n
        print(link.get('href'))<\/p>\n
    # \u5047\u8bbe\u5b58\u5728"Next"\u6309\u94ae\u94fe\u63a5\u5230\u4e0b\u4e00\u9875<\/p>\n
    next_page = soup.find('a', text='Next')<\/p>\n
    if next_page:<\/p>\n
        crawl_page(url, page + 1)<\/p>\n
base_url = 'http:\/\/example.com\/page\/'<\/p>\n
crawl_page(base_url, 1)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u5904\u7406\u52a8\u6001\u5185\u5bb9<\/h3>\n<\/p>\n
\u6709\u4e9b\u7f51\u7ad9\u4f7f\u7528JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u3002\u5bf9\u4e8e\u8fd9\u79cd\u60c5\u51b5\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u6267\u884cJavaScript\u5e76\u83b7\u53d6\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n
\u5b89\u88c5Selenium<\/h4>\n<\/p>\n
\u4f7f\u7528pip\u5b89\u88c5Selenium\uff1a<\/p>\n<\/p>\n
pip install selenium<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd8\u9700\u8981\u4e0b\u8f7d\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5982ChromeDriver\u3002<\/p>\n<\/p>\n
\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u5185\u5bb9<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u5185\u5bb9\u7684\u793a\u4f8b\uff1a<\/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 webdriver_manager.chrome import ChromeDriverManager<\/p>\n
\u8bbe\u7f6eChrome\u9009\u9879<\/strong><\/h2>\n
options = webdriver.ChromeOptions()<\/p>\n
options.add_argument('--headless')  # \u65e0\u5934\u6a21\u5f0f<\/p>\n
\u542f\u52a8Chrome\u6d4f\u89c8\u5668<\/strong><\/h2>\n
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
driver.get(url)<\/p>\n
\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n
driver.implicitly_wait(10)<\/p>\n
\u83b7\u53d6\u52a8\u6001\u5185\u5bb9<\/strong><\/h2>\n
content = driver.page_source<\/p>\n
print(content)<\/p>\n
\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u63d0\u9ad8\u722c\u53d6\u6548\u7387<\/h3>\n<\/p>\n
\u5728\u5927\u89c4\u6a21\u722c\u53d6\u65f6\uff0c\u6548\u7387\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u8003\u8651\u56e0\u7d20\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65\u7f16\u7a0b\u6765\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u3002<\/p>\n<\/p>\n
\u4f7f\u7528\u591a\u7ebf\u7a0b<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528\u591a\u7ebf\u7a0b\u722c\u53d6\u6570\u636e\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
from concurrent.futures import ThreadPoolExecutor<\/p>\n
def fetch_url(url):<\/p>\n
    response = requests.get(url)<\/p>\n
    soup = BeautifulSoup(response.text, 'lxml')<\/p>\n
    links = soup.find_all('a')<\/p>\n
    for link in links:<\/p>\n
        print(link.get('href'))<\/p>\n
base_url = 'http:\/\/example.com\/page\/'<\/p>\n
urls = [base_url + str(i) for i in range(1, 11)]<\/p>\n
with ThreadPoolExecutor(max_workers=5) as executor:<\/p>\n
    executor.map(fetch_url, urls)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4f7f\u7528\u5f02\u6b65\u7f16\u7a0b<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528aiohttp\u548casyncio\u8fdb\u884c\u5f02\u6b65\u722c\u53d6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import aiohttp<\/p>\n
import asyncio<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
async def fetch_url(session, url):<\/p>\n
    async with session.get(url) as response:<\/p>\n
        text = await response.text()<\/p>\n
        soup = BeautifulSoup(text, 'lxml')<\/p>\n
        links = soup.find_all('a')<\/p>\n
        for link in links:<\/p>\n
            print(link.get('href'))<\/p>\n
async def main():<\/p>\n
    base_url = 'http:\/\/example.com\/page\/'<\/p>\n
    urls = [base_url + str(i) for i in range(1, 11)]<\/p>\n
    async with aiohttp.ClientSession() as session:<\/p>\n
        tasks = [fetch_url(session, url) for url in urls]<\/p>\n
        await asyncio.gather(*tasks)<\/p>\n
asyncio.run(main())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u722c\u866b\u7b56\u7565\u4e0e\u9053\u5fb7\u89c4\u8303<\/h3>\n<\/p>\n
\u5728\u7f16\u5199\u548c\u8fd0\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u9700\u8981\u9075\u5b88\u4e00\u4e9b\u7b56\u7565\u548c\u9053\u5fb7\u89c4\u8303\uff0c\u5982\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u3001\u63a7\u5236\u722c\u53d6\u9891\u7387\u3001\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u538b\u529b\u7b49\u3002<\/p>\n<\/p>\n
\u9075\u5b88robots.txt<\/h4>\n<\/p>\n
robots.txt\u662f\u7f51\u7ad9\u7ba1\u7406\u5458\u7528\u6765\u544a\u8bc9\u722c\u866b\u54ea\u4e9b\u9875\u9762\u53ef\u4ee5\u722c\u53d6\u3001\u54ea\u4e9b\u4e0d\u53ef\u4ee5\u722c\u53d6\u7684\u6587\u4ef6\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528robots.txt\u6765\u786e\u5b9a\u722c\u53d6\u7b56\u7565\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
from urllib.robotparser import RobotFileParser<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
robots_url = url + '\/robots.txt'<\/p>\n
response = requests.get(robots_url)<\/p>\n
robots_parser = RobotFileParser()<\/p>\n
robots_parser.parse(response.text.split('\\n'))<\/p>\n
if robots_parser.can_fetch('*', url):<\/p>\n
    print('Allowed to fetch the URL')<\/p>\n
else:<\/p>\n
    print('Not allowed to fetch the URL')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u63a7\u5236\u722c\u53d6\u9891\u7387<\/h4>\n<\/p>\n
\u4e3a\u4e86\u907f\u514d\u5bf9\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u538b\u529b\uff0c\u6211\u4eec\u9700\u8981\u63a7\u5236\u722c\u53d6\u9891\u7387\u3002\u53ef\u4ee5\u4f7f\u7528time.sleep()\u51fd\u6570\u6765\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u3002<\/p>\n<\/p>\n
import time<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com\/page\/'<\/p>\n
for i in range(1, 11):<\/p>\n
    response = requests.get(url + str(i))<\/p>\n
    print(response.status_code)<\/p>\n
    time.sleep(1)  # \u95f4\u96941\u79d2<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e5d\u3001\u5904\u7406\u5f02\u5e38<\/h3>\n<\/p>\n
\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\uff0c\u5982\u8bf7\u6c42\u8d85\u65f6\u3001\u8fde\u63a5\u9519\u8bef\u7b49\u3002\u9700\u8981\u5bf9\u8fd9\u4e9b\u5f02\u5e38\u8fdb\u884c\u5904\u7406\uff0c\u4ee5\u4fdd\u8bc1\u722c\u866b\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n
\u6355\u83b7\u8bf7\u6c42\u5f02\u5e38<\/h4>\n<\/p>\n
\u4ee5\u4e0b\u662f\u4e00\u4e2a\u6355\u83b7\u8bf7\u6c42\u5f02\u5e38\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
try:<\/p>\n
    response = requests.get(url)<\/p>\n
    response.raise_for_status()<\/p>\n
except requests.exceptions.RequestException as e:<\/p>\n
    print(f'Request failed: {e}')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8bbe\u7f6e\u91cd\u8bd5\u673a\u5236<\/h4>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528retrying\u5e93\u6765\u8bbe\u7f6e\u91cd\u8bd5\u673a\u5236\uff0c\u4ee5\u5e94\u5bf9\u4e34\u65f6\u6027\u9519\u8bef\u3002<\/p>\n<\/p>\n
from retrying import retry<\/p>\n
import requests<\/p>\n
@retry(stop_max_attempt_number=3, wait_fixed=2000)<\/p>\n
def fetch_url(url):<\/p>\n
    response = requests.get(url)<\/p>\n
    response.raise_for_status()<\/p>\n
    return response.text<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
try:<\/p>\n
    content = fetch_url(url)<\/p>\n
    print(content)<\/p>\n
except requests.exceptions.RequestException as e:<\/p>\n
    print(f'Failed to fetch the URL after retries: {e}')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u672c\u6587\uff0c\u6211\u4eec\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528Python\u7f16\u5199\u7f51\u7edc\u722c\u866b\uff0c\u4ece\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u5185\u5bb9\u5230\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\u3001\u5b58\u50a8\u6570\u636e\u7b49\u5404\u4e2a\u65b9\u9762\u8fdb\u884c\u4e86\u8be6\u7ec6\u8bf4\u660e\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u5229\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/strong>\u662f\u7f16\u5199\u7f51\u7edc\u722c\u866b\u7684\u6838\u5fc3\u6b65\u9aa4\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u5b9e\u73b0\u7f51\u7edc\u722c\u866b\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u4f7f\u7528Python\u7f16\u5199\u7f51\u7edc\u722c\u866b\u9700\u8981\u54ea\u4e9b\u57fa\u672c\u77e5\u8bc6\uff1f<\/strong>
\u8981\u6210\u529f\u7f16\u5199\u7f51\u7edc\u722c\u866b\uff0c\u9996\u5148\u9700\u8981\u638c\u63e1Python\u7f16\u7a0b\u8bed\u8a00\u7684\u57fa\u7840\u77e5\u8bc6\uff0c\u5305\u62ec\u6570\u636e\u7ed3\u6784\u3001\u63a7\u5236\u6d41\u548c\u51fd\u6570\u7b49\u3002\u4e86\u89e3HTTP\u534f\u8bae\u7684\u57fa\u672c\u539f\u7406\u4e5f\u662f\u5fc5\u4e0d\u53ef\u5c11\u7684\uff0c\u56e0\u5176\u662f\u7f51\u7edc\u722c\u866b\u4e0e\u7f51\u9875\u4ea4\u4e92\u7684\u57fa\u7840\u3002\u6b64\u5916\uff0c\u719f\u6089\u4f7f\u7528\u5e38\u89c1\u7684\u5e93\u5982Requests\uff08\u7528\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff09\u548cBeautiful Soup\uff08\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\uff09\u5c06\u5927\u5927\u63d0\u9ad8\u4f60\u7684\u722c\u866b\u6548\u7387\u3002\u5b66\u4e60\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u5904\u7406\u548c\u63d0\u53d6\u6570\u636e\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u7f51\u7edc\u722c\u866b\u4e2d\u7684\u53cd\u722c\u673a\u5236\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4e3a\u4e86\u4fdd\u62a4\u5176\u6570\u636e\uff0c\u4f1a\u5b9e\u65bd\u53cd\u722c\u673a\u5236\u3002\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\u7684\u7b56\u7565\u5305\u62ec\u4f7f\u7528\u968f\u673a\u7684User-Agent\u5934\u90e8\u6765\u4f2a\u88c5\u8bf7\u6c42\u3001\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u95f4\u9694\u4ee5\u907f\u514d\u9891\u7e41\u8bbf\u95ee\u3001\u4f7f\u7528\u4ee3\u7406IP\u6c60\u6765\u9690\u85cf\u771f\u5b9eIP\u7b49\u3002\u8fd8\u53ef\u4ee5\u4f7f\u7528\u52a8\u6001\u8bf7\u6c42\u5e93\u5982Selenium\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u4ece\u800c\u7ed5\u8fc7\u67d0\u4e9b\u7b80\u5355\u7684\u53cd\u722c\u63aa\u65bd\u3002\u6b64\u5916\uff0c\u4fdd\u6301\u5bf9\u76ee\u6807\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u7684\u5c0a\u91cd\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\uff0c\u4ee5\u514d\u88ab\u5c01\u7981\u3002<\/p>\n
Python\u7f51\u7edc\u722c\u866b\u7684\u5e38\u89c1\u5e94\u7528\u573a\u666f\u6709\u54ea\u4e9b\uff1f<\/strong>
Python\u7f51\u7edc\u722c\u866b\u5e7f\u6cdb\u5e94\u7528\u4e8e\u6570\u636e\u91c7\u96c6\u548c\u5206\u6790\u3002\u6bd4\u5982\uff0c\u53ef\u4ee5\u7528\u4e8e\u6293\u53d6\u7535\u5546\u7f51\u7ad9\u4e0a\u7684\u5546\u54c1\u4fe1\u606f\u548c\u4ef7\u683c\u6ce2\u52a8\uff0c\u4ee5\u4fbf\u8fdb\u884c\u5e02\u573a\u5206\u6790\u3002\u4e5f\u53ef\u4ee5\u7528\u6765\u6536\u96c6\u793e\u4ea4\u5a92\u4f53\u4e0a\u7684\u7528\u6237\u8bc4\u8bba\u548c\u4e92\u52a8\u6570\u636e\uff0c\u5e2e\u52a9\u4f01\u4e1a\u8fdb\u884c\u54c1\u724c\u76d1\u6d4b\u548c\u8206\u60c5\u5206\u6790\u3002\u6b64\u5916\uff0c\u722c\u866b\u8fd8\u53ef\u4ee5\u7528\u4e8e\u65b0\u95fb\u7f51\u7ad9\u7684\u5185\u5bb9\u805a\u5408\uff0c\u6216\u662f\u83b7\u53d6\u5b66\u672f\u8bba\u6587\u548c\u6280\u672f\u6587\u6863\uff0c\u4ee5\u4fbf\u4e8e\u8fdb\u884c\u4fe1\u606f\u6316\u6398\u548c\u7814\u7a76\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u7528Python\u7f16\u5199\u7f51\u7edc\u722c\u866b\uff0c\u9996\u5148\u9700\u8981\u4e86\u89e3\u4e00\u4e9b\u6838\u5fc3\u5de5\u5177\u548c\u6b65\u9aa4\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u5229\u7528Be […]","protected":false},"author":3,"featured_media":1179343,"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\/1179338"}],"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=1179338"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179338\/revisions"}],"predecessor-version":[{"id":1179344,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179338\/revisions\/1179344"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1179343"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1179338"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1179338"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1179338"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}