Python获取网页数据的五种方法

import requests
from bs4 import BeautifulSoup
 
# 发送 HTTP 请求
url = "https://example.com"
response = requests.get(url)
 
# 确保请求成功
if response.status_code == 200:
    # 使用 BeautifulSoup 解析网页
    soup = BeautifulSoup(response.content, 'html.parser')
    
    # 提取网页中的标题
    title = soup.title.string
    print(f"网页标题：{title}")
    
    # 提取网页中的所有链接
    for link in soup.find_all('a'):
        print(f"链接：{link.get('href')}")
else:
    print("网页请求失败")

import requests
from lxml import html
 
# 发送 HTTP 请求
url = "https://example.com"
response = requests.get(url)
 
# 确保请求成功
if response.status_code == 200:
    # 使用 lxml 解析网页
    tree = html.fromstring(response.content)
    
    # 提取网页中的标题
    title = tree.xpath('//title/text()')
    print(f"网页标题：{title[0] if title else '无标题'}")
    
    # 提取所有链接
    links = tree.xpath('//a/@href')
    for link in links:
        print(f"链接：{link}")
else:
    print("网页请求失败")

from selenium import webdriver
from bs4 import BeautifulSoup
import time
 
# 启动 WebDriver
driver = webdriver.Chrome(executable_path="path/to/chromedriver")
 
# 访问网页
url = "https://example.com"
driver.get(url)
 
# 等待页面加载
time.sleep(3)
 
# 获取页面源代码
html = driver.page_source
 
# 使用 BeautifulSoup 解析网页
soup = BeautifulSoup(html, 'html.parser')
 
# 提取网页中的标题
title = soup.title.string
print(f"网页标题：{title}")
 
# 提取网页中的所有链接
for link in soup.find_all('a'):
    print(f"链接：{link.get('href')}")
 
# 关闭浏览器
driver.quit()

scrapy startproject myproject

cd myproject
scrapy genspider example_spider example.com

import scrapy
 
class ExampleSpider(scrapy.Spider):
    name = 'example_spider'
    start_urls = ['https://example.com']
 
    def parse(self, response):
        # 提取网页标题
        title = response.css('title::text').get()
        print(f"网页标题：{title}")
 
        # 提取所有链接
        links = response.css('a::attr(href)').getall()
        for link in links:
            print(f"链接：{link}")

scrapy crawl example_spider

from pyquery import PyQuery as pq
import requests
 
# 发送 HTTP 请求
url = "https://example.com"
response = requests.get(url)
 
# 使用 PyQuery 解析网页
doc = pq(response.content)
 
# 提取网页标题
title = doc('title').text()
print(f"网页标题：{title}")
 
# 提取网页中的所有链接
for link in doc('a').items():
    print(f"链接：{link.attr('href')}")