{"id":1171316,"date":"2025-01-15T16:33:48","date_gmt":"2025-01-15T08:33:48","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1171316.html"},"modified":"2025-01-15T16:33:53","modified_gmt":"2025-01-15T08:33:53","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%81%9a%e7%bd%91%e7%bb%9c%e7%88%ac%e8%99%ab","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1171316.html","title":{"rendered":"\u5982\u4f55\u7528python\u505a\u7f51\u7edc\u722c\u866b"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u505a\u7f51\u7edc\u722c\u866b\"<\/p>\n

\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u4e2a\u6838\u5fc3\u6b65\u9aa4\uff1a\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u5904\u7406\u6570\u636e\u5b58\u50a8\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/strong>\u3002\u5176\u4e2d\uff0c\u9009\u62e9\u5408\u9002\u7684\u5e93\u662f\u4e00\u4e2a\u5173\u952e\u6b65\u9aa4\uff0c\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4e0b\uff1a<\/p>\n<\/p>\n

\u5728Python\u4e2d\uff0c\u7528\u4e8e\u7f51\u7edc\u722c\u866b\u7684\u5e93\u4e3b\u8981\u6709requests\u548cBeautifulSoup\u3002requests<\/strong>\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u83b7\u53d6\u7f51\u9875\u7684\u6e90\u4ee3\u7801\uff0c\u800cBeautifulSoup<\/strong>\u5e93\u5219\u7528\u4e8e\u89e3\u6790\u548c\u63d0\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u901a\u8fc7\u8fd9\u4e24\u4e2a\u5e93\u7684\u7ed3\u5408\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u5b8c\u6210\u5927\u90e8\u5206\u7684\u722c\u866b\u4efb\u52a1\u3002\u6b64\u5916\uff0cScrapy\u4e5f\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u7f51\u7edc\u722c\u866b\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/h3>\n<\/p>\n

1. Requests\u5e93<\/h4>\n<\/p>\n

Requests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u5e93\u4e4b\u4e00\u3002\u5b83\u53ef\u4ee5\u5f88\u65b9\u4fbf\u5730\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u4e14\u5904\u7406\u590d\u6742\u7684HTTP\u8bf7\u6c42\u548c\u54cd\u5e94\u3002\u4f7f\u7528Requests\u5e93\uff0c\u4f60\u53ef\u4ee5\u7b80\u5355\u5730\u83b7\u53d6\u7f51\u9875\u7684HTML\u6e90\u4ee3\u7801\u3002<\/p>\n<\/p>\n

import requests<\/p>\n
response = requests.get('https:\/\/example.com')<\/p>\n
print(response.text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. BeautifulSoup\u5e93<\/h4>\n<\/p>\n
BeautifulSoup\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u7684\u5e93\u3002\u5b83\u53ef\u4ee5\u5e2e\u52a9\u4f60\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6709\u7528\u7684\u4fe1\u606f\uff0c\u6bd4\u5982\u6807\u9898\u3001\u56fe\u7247\u3001\u94fe\u63a5\u7b49\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
html = response.text<\/p>\n
soup = BeautifulSoup(html, 'html.parser')<\/p>\n
title = soup.find('title').text<\/p>\n
print(title)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. Scrapy\u6846\u67b6<\/h4>\n<\/p>\n
Scrapy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u7f51\u7edc\u722c\u866b\u6846\u67b6\uff0c\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684\u722c\u866b\u9879\u76ee\u3002Scrapy\u63d0\u4f9b\u4e86\u5b8c\u6574\u7684\u722c\u866b\u5f00\u53d1\u5de5\u5177\uff0c\u5305\u62ec\u4e0b\u8f7d\u5668\u3001\u4e2d\u95f4\u4ef6\u3001\u7ba1\u9053\u7b49\u3002<\/p>\n<\/p>\n
import scrapy<\/p>\n
class ExampleSpider(scrapy.Spider):<\/p>\n
    name = 'example'<\/p>\n
    start_urls = ['https:\/\/example.com']<\/p>\n
    def parse(self, response):<\/p>\n
        title = response.xpath('\/\/title\/text()').get()<\/p>\n
        print(title)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n
1. \u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/h4>\n<\/p>\n
BeautifulSoup\u53ef\u4ee5\u89e3\u6790HTML\u548cXML\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a\u4e00\u4e2a\u53ef\u4ee5\u65b9\u4fbf\u64cd\u4f5c\u7684BeautifulSoup\u5bf9\u8c61\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u7684\u5404\u79cd\u65b9\u6cd5\u6765\u67e5\u627e\u548c\u63d0\u53d6\u4f60\u9700\u8981\u7684\u4fe1\u606f\u3002<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
html = response.text<\/p>\n
soup = BeautifulSoup(html, 'html.parser')<\/p>\n
\u67e5\u627e\u6240\u6709\u7684\u94fe\u63a5<\/strong><\/h2>\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
2. \u4f7f\u7528XPath\u89e3\u6790HTML<\/h4>\n<\/p>\n
XPath\u662f\u4e00\u79cd\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u4fe1\u606f\u7684\u8bed\u8a00\u3002Scrapy\u6846\u67b6\u652f\u6301\u4f7f\u7528XPath\u6765\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n
import scrapy<\/p>\n
class ExampleSpider(scrapy.Spider):<\/p>\n
    name = 'example'<\/p>\n
    start_urls = ['https:\/\/example.com']<\/p>\n
    def parse(self, response):<\/p>\n
        links = response.xpath('\/\/a\/@href').getall()<\/p>\n
        for link in links:<\/p>\n
            print(link)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5904\u7406\u6570\u636e\u5b58\u50a8<\/h3>\n<\/p>\n
\u5728\u83b7\u53d6\u5e76\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u4e0b\u4e00\u6b65\u5c31\u662f\u5904\u7406\u6570\u636e\u5b58\u50a8\u3002\u4f60\u53ef\u4ee5\u5c06\u6570\u636e\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u3001\u6570\u636e\u5e93\u6216\u5176\u4ed6\u5b58\u50a8\u7cfb\u7edf\u4e2d\u3002<\/p>\n<\/p>\n
1. \u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6<\/h4>\n<\/p>\n
\u4f60\u53ef\u4ee5\u5c06\u722c\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230\u672c\u5730\u6587\u4ef6\u4e2d\uff0c\u6bd4\u5982CSV\u3001JSON\u7b49\u683c\u5f0f\u3002<\/p>\n<\/p>\n
import csv<\/p>\n
data = [{'title': 'Example 1', 'link': 'https:\/\/example.com\/1'},<\/p>\n
        {'title': 'Example 2', 'link': 'https:\/\/example.com\/2'}]<\/p>\n
with open('data.csv', 'w', newline='') as csvfile:<\/p>\n
    fieldnames = ['title', 'link']<\/p>\n
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)<\/p>\n
    writer.writeheader()<\/p>\n
    for item in data:<\/p>\n
        writer.writerow(item)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4fdd\u5b58\u5230\u6570\u636e\u5e93<\/h4>\n<\/p>\n
\u4f60\u53ef\u4ee5\u5c06\u722c\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230\u6570\u636e\u5e93\u4e2d\uff0c\u6bd4\u5982MySQL\u3001MongoDB\u7b49\u3002<\/p>\n<\/p>\n
import pymysql<\/p>\n
connection = pymysql.connect(host='localhost',<\/p>\n
                             user='user',<\/p>\n
                             password='passwd',<\/p>\n
                             database='db')<\/p>\n
cursor = connection.cursor()<\/p>\n
cursor.execute('INSERT INTO table (title, link) VALUES (%s, %s)', ('Example', 'https:\/\/example.com'))<\/p>\n
connection.commit()<\/p>\n
cursor.close()<\/p>\n
connection.close()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5904\u7406\u53cd\u722c\u673a\u5236<\/h3>\n<\/p>\n
\u5f88\u591a\u7f51\u7ad9\u90fd\u6709\u53cd\u722c\u673a\u5236\uff0c\u9632\u6b62\u7528\u6237\u8fc7\u4e8e\u9891\u7e41\u5730\u8bbf\u95ee\u3002\u4e3a\u4e86\u907f\u514d\u88ab\u5c01\u7981\uff0c\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
1. \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n
\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u53ef\u4ee5\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u8bbf\u95ee\u7f51\u9875\uff0c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002<\/p>\n<\/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
}<\/p>\n
response = requests.get('https:\/\/example.com', headers=headers)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bbe\u7f6e\u5ef6\u65f6<\/h4>\n<\/p>\n
\u901a\u8fc7\u8bbe\u7f6e\u5ef6\u65f6\uff0c\u53ef\u4ee5\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u5730\u8bbf\u95ee\u7f51\u9875\uff0c\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002<\/p>\n<\/p>\n
import time<\/p>\n
for url in urls:<\/p>\n
    response = requests.get(url)<\/p>\n
    time.sleep(1)  # \u5ef6\u65f61\u79d2<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n
\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406\uff0c\u53ef\u4ee5\u9690\u85cf\u771f\u5b9e\u7684IP\u5730\u5740\uff0c\u907f\u514d\u88ab\u5c01\u7981\u3002<\/p>\n<\/p>\n
proxies = {<\/p>\n
    'http': 'http:\/\/10.10.1.10:3128',<\/p>\n
    'https': 'http:\/\/10.10.1.10:1080',<\/p>\n
}<\/p>\n
response = requests.get('https:\/\/example.com', proxies=proxies)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u7efc\u5408\u5b9e\u4f8b<\/h3>\n<\/p>\n
\u7ed3\u5408\u4e0a\u9762\u7684\u5185\u5bb9\uff0c\u6211\u4eec\u53ef\u4ee5\u5b9e\u73b0\u4e00\u4e2a\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff0c\u722c\u53d6\u4e00\u4e2a\u65b0\u95fb\u7f51\u7ad9\u7684\u6807\u9898\u548c\u94fe\u63a5\uff0c\u5e76\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import csv<\/p>\n
import time<\/p>\n
def get_html(url, headers=None):<\/p>\n
    response = requests.get(url, headers=headers)<\/p>\n
    return response.text<\/p>\n
def parse_html(html):<\/p>\n
    soup = BeautifulSoup(html, 'html.parser')<\/p>\n
    articles = soup.find_all('article')<\/p>\n
    data = []<\/p>\n
    for article in articles:<\/p>\n
        title = article.find('h2').text<\/p>\n
        link = article.find('a').get('href')<\/p>\n
        data.append({'title': title, 'link': link})<\/p>\n
    return data<\/p>\n
def save_to_csv(data, filename):<\/p>\n
    with open(filename, 'w', newline='') as csvfile:<\/p>\n
        fieldnames = ['title', 'link']<\/p>\n
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)<\/p>\n
        writer.writeheader()<\/p>\n
        for item in data:<\/p>\n
            writer.writerow(item)<\/p>\n
def mAI<\/a>n():<\/p>\n
    url = 'https:\/\/example.com\/news'<\/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
    }<\/p>\n
    html = get_html(url, headers=headers)<\/p>\n
    data = parse_html(html)<\/p>\n
    save_to_csv(data, 'news.csv')<\/p>\n
    # \u5ef6\u65f61\u79d2\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u5730\u8bbf\u95ee\u7f51\u9875<\/p>\n
    time.sleep(1)<\/p>\n
if __name__ == '__main__':<\/p>\n
    main()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u7efc\u5408\u5b9e\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528Requests\u5e93\u83b7\u53d6\u7f51\u9875HTML\u6e90\u4ee3\u7801\uff0c\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5c06\u722c\u53d6\u7684\u6570\u636e\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u4e2d\u3002\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\u548c\u5ef6\u65f6\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u5e76\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002<\/p>\n<\/p>\n
\u516d\u3001\u8fdb\u9636\u5185\u5bb9<\/h3>\n<\/p>\n
1. \u5f02\u6b65\u722c\u866b<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u5927\u89c4\u6a21\u7684\u6570\u636e\u722c\u53d6\uff0c\u5f02\u6b65\u722c\u866b\u53ef\u4ee5\u663e\u8457\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u3002Python\u7684aiohttp\u548casyncio\u5e93\u53ef\u4ee5\u7528\u4e8e\u5b9e\u73b0\u5f02\u6b65\u722c\u866b\u3002<\/p>\n<\/p>\n
import aiohttp<\/p>\n
import asyncio<\/p>\n
async def fetch(session, url):<\/p>\n
    async with session.get(url) as response:<\/p>\n
        return await response.text()<\/p>\n
async def main():<\/p>\n
    async with aiohttp.ClientSession() as session:<\/p>\n
        html = await fetch(session, 'https:\/\/example.com')<\/p>\n
        print(html)<\/p>\n
loop = asyncio.get_event_loop()<\/p>\n
loop.run_until_complete(main())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u722c\u53d6\u52a8\u6001\u7f51\u9875<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u4f7f\u7528JavaScript\u52a0\u8f7d\u5185\u5bb9\u7684\u52a8\u6001\u7f51\u9875\uff0c\u4f20\u7edf\u7684Requests\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002\u6b64\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u6216Playwright\u7b49\u5de5\u5177\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002<\/p>\n<\/p>\n
from selenium import webdriver<\/p>\n
driver = webdriver.Chrome()<\/p>\n
driver.get('https:\/\/example.com')<\/p>\n
html = driver.page_source<\/p>\n
print(html)<\/p>\n
driver.quit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u5206\u5e03\u5f0f\u722c\u866b<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u66f4\u5927\u89c4\u6a21\u7684\u722c\u53d6\u4efb\u52a1\uff0c\u53ef\u4ee5\u4f7f\u7528\u5206\u5e03\u5f0f\u722c\u866b\u67b6\u6784\uff0c\u6bd4\u5982Scrapy-Redis\u3002\u5b83\u53ef\u4ee5\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u53d6\uff0c\u591a\u4e2a\u722c\u866b\u8282\u70b9\u534f\u540c\u5de5\u4f5c\uff0c\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u3002<\/p>\n<\/p>\n
# Scrapy-Redis\u7684\u4f7f\u7528\u793a\u4f8b<\/p>\n
\u5728settings.py\u4e2d\u914d\u7f6e<\/strong><\/h2>\n
SCHEDULER = "scrapy_redis.scheduler.Scheduler"<\/p>\n
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"<\/p>\n
SCHEDULER_PERSIST = True<\/p>\n
REDIS_URL = 'redis:\/\/localhost:6379'<\/p>\n
\u5728\u722c\u866b\u4ee3\u7801\u4e2d<\/strong><\/h2>\n
import scrapy<\/p>\n
from scrapy_redis.spiders import RedisSpider<\/p>\n
class ExampleSpider(RedisSpider):<\/p>\n
    name = 'example'<\/p>\n
    redis_key = 'example:start_urls'<\/p>\n
    def parse(self, response):<\/p>\n
        title = response.xpath('\/\/title\/text()').get()<\/p>\n
        yield {'title': title}<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u6700\u4f73\u5b9e\u8df5<\/h3>\n<\/p>\n
1. \u5408\u6cd5\u6027\u548c\u4f26\u7406\u9053\u5fb7<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u4e4b\u524d\uff0c\u8bf7\u786e\u4fdd\u4f60\u6709\u6743\u8bbf\u95ee\u5e76\u722c\u53d6\u76ee\u6807\u7f51\u7ad9\u7684\u6570\u636e\u3002\u9075\u5b88\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u548c\u76f8\u5173\u6cd5\u5f8b\u6cd5\u89c4\uff0c\u907f\u514d\u7ed9\u7f51\u7ad9\u5e26\u6765\u8d1f\u62c5\u548c\u635f\u5bb3\u3002<\/p>\n<\/p>\n
2. \u4ee3\u7801\u7ec4\u7ec7<\/h4>\n<\/p>\n
\u5c06\u722c\u866b\u4ee3\u7801\u7ec4\u7ec7\u6210\u6a21\u5757\u5316\u3001\u53ef\u91cd\u7528\u7684\u7ec4\u4ef6\uff0c\u53ef\u4ee5\u63d0\u9ad8\u4ee3\u7801\u7684\u53ef\u7ef4\u62a4\u6027\u548c\u53ef\u6269\u5c55\u6027\u3002\u4f7f\u7528\u9762\u5411\u5bf9\u8c61\u7f16\u7a0b\uff08OOP\uff09\u548c\u8bbe\u8ba1\u6a21\u5f0f\uff0c\u53ef\u4ee5\u4f7f\u4ee3\u7801\u66f4\u52a0\u6e05\u6670\u548c\u6613\u4e8e\u7406\u89e3\u3002<\/p>\n<\/p>\n
3. \u9519\u8bef\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u7f51\u7edc\u722c\u866b\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u9519\u8bef\u548c\u5f02\u5e38\u60c5\u51b5\uff0c\u6bd4\u5982\u7f51\u7edc\u8fde\u63a5\u9519\u8bef\u3001\u89e3\u6790\u9519\u8bef\u7b49\u3002\u9700\u8981\u7f16\u5199\u5065\u58ee\u7684\u9519\u8bef\u5904\u7406\u673a\u5236\uff0c\u4ee5\u786e\u4fdd\u722c\u866b\u80fd\u591f\u7a33\u5b9a\u8fd0\u884c\u3002<\/p>\n<\/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"Error: {e}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
4. \u6570\u636e\u6e05\u6d17\u548c\u9884\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u6570\u636e\u5b58\u50a8\u4e4b\u524d\uff0c\u8fdb\u884c\u5fc5\u8981\u7684\u6570\u636e\u6e05\u6d17\u548c\u9884\u5904\u7406\uff0c\u53ef\u4ee5\u63d0\u9ad8\u6570\u636e\u7684\u8d28\u91cf\u548c\u4e00\u81f4\u6027\u3002\u6bd4\u5982\uff0c\u53bb\u9664\u91cd\u590d\u6570\u636e\u3001\u5904\u7406\u7f3a\u5931\u503c\u3001\u683c\u5f0f\u5316\u6570\u636e\u7b49\u3002<\/p>\n<\/p>\n
5. \u76d1\u63a7\u548c\u65e5\u5fd7<\/h4>\n<\/p>\n
\u5728\u5927\u89c4\u6a21\u722c\u866b\u9879\u76ee\u4e2d\uff0c\u4f7f\u7528\u76d1\u63a7\u548c\u65e5\u5fd7\u8bb0\u5f55\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u4e86\u89e3\u722c\u866b\u7684\u8fd0\u884c\u72b6\u6001\uff0c\u53ca\u65f6\u53d1\u73b0\u548c\u89e3\u51b3\u95ee\u9898\u3002\u4f7f\u7528\u65e5\u5fd7\u5e93\uff08\u6bd4\u5982logging\uff09\u8bb0\u5f55\u5173\u952e\u64cd\u4f5c\u548c\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n
import logging<\/p>\n
logging.basicConfig(level=logging.INFO)<\/p>\n
logger = logging.getLogger(__name__)<\/p>\n
logger.info('Starting spider...')<\/p>\n
logger.error('Error occurred: %s', error)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u5185\u5bb9\uff0c\u4f60\u53ef\u4ee5\u4e86\u89e3\u5230\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u7684\u57fa\u672c\u65b9\u6cd5\u548c\u6b65\u9aa4\u3002\u9009\u62e9\u5408\u9002\u7684\u5e93\u548c\u6846\u67b6\uff0c\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u5904\u7406\u6570\u636e\u5b58\u50a8\uff0c\u5e76\u5e94\u5bf9\u53cd\u722c\u673a\u5236\uff0c\u662f\u5b9e\u73b0\u4e00\u4e2a\u6210\u529f\u722c\u866b\u9879\u76ee\u7684\u5173\u952e\u3002\u5e0c\u671b\u8fd9\u4e9b\u5185\u5bb9\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff0c\u795d\u4f60\u5728\u722c\u866b\u5f00\u53d1\u4e2d\u53d6\u5f97\u6210\u529f\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5f00\u59cb\u5b66\u4e60Python\u7f51\u7edc\u722c\u866b\u7684\u57fa\u7840\u77e5\u8bc6\uff1f<\/strong>
\u5b66\u4e60Python\u7f51\u7edc\u722c\u866b\u7684\u7b2c\u4e00\u6b65\u662f\u638c\u63e1Python\u8bed\u8a00\u7684\u57fa\u672c\u8bed\u6cd5\u548c\u6570\u636e\u7ed3\u6784\u3002\u4e86\u89e3HTTP\u534f\u8bae\u3001\u7f51\u9875\u7ed3\u6784\uff08\u5982HTML\u3001CSS\uff09\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u53ef\u4ee5\u901a\u8fc7\u5728\u7ebf\u8bfe\u7a0b\u3001\u4e66\u7c4d\u6216\u89c6\u9891\u6559\u7a0b\u6765\u83b7\u53d6\u8fd9\u4e9b\u77e5\u8bc6\u3002\u6b64\u5916\uff0c\u719f\u6089\u4e00\u4e9b\u722c\u866b\u76f8\u5173\u7684\u5e93\u5982Requests\u548cBeautifulSoup\uff0c\u5c06\u5e2e\u52a9\u4f60\u5728\u5b9e\u9645\u64cd\u4f5c\u4e2d\u66f4\u52a0\u5f97\u5fc3\u5e94\u624b\u3002<\/p>\n
\u5728\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u65f6\uff0c\u5982\u4f55\u5904\u7406\u7f51\u7ad9\u7684\u53cd\u722c\u866b\u63aa\u65bd\uff1f<\/strong>
\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\u6765\u4fdd\u62a4\u5176\u6570\u636e\u3002\u4e3a\u4e86\u6709\u6548\u5e94\u5bf9\u8fd9\u4e9b\u63aa\u65bd\uff0c\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u7b56\u7565\u3002\u4f7f\u7528\u968f\u673a\u7684\u7528\u6237\u4ee3\u7406\uff08User-Agent\uff09\u53ef\u4ee5\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\uff1b\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u95f4\u9694\u6765\u6a21\u4eff\u4eba\u7c7b\u7528\u6237\u7684\u884c\u4e3a\uff1b\u8fd8\u53ef\u4ee5\u5229\u7528\u4ee3\u7406IP\u6765\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\u3002\u8fd9\u4e9b\u65b9\u6cd5\u53ef\u4ee5\u63d0\u9ad8\u722c\u866b\u7684\u6210\u529f\u7387\u3002<\/p>\n
\u5982\u4f55\u5b58\u50a8\u722c\u53d6\u5230\u7684\u6570\u636e\u4ee5\u4fbf\u540e\u7eed\u5206\u6790\uff1f<\/strong>
\u722c\u53d6\u5230\u7684\u6570\u636e\u53ef\u4ee5\u6839\u636e\u9700\u6c42\u5b58\u50a8\u5728\u591a\u79cd\u683c\u5f0f\u4e2d\u3002\u5e38\u89c1\u7684\u5b58\u50a8\u65b9\u5f0f\u5305\u62ecCSV\u6587\u4ef6\u3001JSON\u6587\u4ef6\u548c\u6570\u636e\u5e93\uff08\u5982SQLite\u3001MySQL\u7b49\uff09\u3002\u9009\u62e9\u5408\u9002\u7684\u5b58\u50a8\u65b9\u5f0f\u4e0d\u4ec5\u53ef\u4ee5\u65b9\u4fbf\u540e\u7eed\u7684\u6570\u636e\u5206\u6790\uff0c\u8fd8\u80fd\u63d0\u9ad8\u6570\u636e\u7684\u53ef\u8bbf\u95ee\u6027\u3002\u6839\u636e\u6570\u636e\u7684\u590d\u6742\u6027\u548c\u4f7f\u7528\u9891\u7387\uff0c\u5408\u7406\u9009\u62e9\u5b58\u50a8\u683c\u5f0f\u975e\u5e38\u91cd\u8981\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u8fdb\u884c\u7f51\u7edc\u722c\u866b\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u4e2a\u6838\u5fc3\u6b65\u9aa4\uff1a\u9009\u62e9\u5408\u9002\u7684\u5e93\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u5904\u7406\u6570\u636e\u5b58\u50a8\u3001\u5904\u7406\u53cd\u722c\u673a\u5236\u3002 […]","protected":false},"author":3,"featured_media":1171327,"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\/1171316"}],"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=1171316"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1171316\/revisions"}],"predecessor-version":[{"id":1171330,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1171316\/revisions\/1171330"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1171327"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1171316"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1171316"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1171316"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}