python爬取豆瓣读书top50（正则表达式）

以下是使用正则表达式爬取豆瓣读书Top50的示例代码：

import requests
import re

# 发送请求获取网页内容
url = 'https://book.douban.com/top250'
response = requests.get(url)
content = response.text

# 使用正则表达式提取书籍信息
pattern = r'<div class="pl2">.*?<a href="(.*?)" title="(.*?)".*?</div>'
results = re.findall(pattern, content, re.S)

# 打印书籍信息
for result in results:
    book_url = result[0]
    book_title = result[1]
    print("书籍链接：", book_url)
    print("书籍标题：", book_title)
    print("--")

相关问题

python爬虫爬取豆瓣电影top250使用正则表达式

以下是使用正则表达式爬取豆瓣电影top250的Python爬虫示例代码：

import re
import requests
from bs4 import BeautifulSoup

def get_movies():
    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'}
    movie_list = []
    for i in range(0, 10):
        link = 'https://movie.douban.com/top250?start=' + str(i * 25)
        r = requests.get(link, headers=headers, timeout=10)
        soup = BeautifulSoup(r.text, "html.parser")
        div_list = soup.find_all('div', class_='hd')
        for each in div_list:
            movie = each.a.span.text.strip()
            movie_list.append(movie)
    return movie_list

def main():
    movies = get_movies()
    for movie in movies:
        print(movie)

if __name__ == '__main__':
    main()

用python的requests和xpath和正则表达式爬取豆瓣电影top250详情页的代码

以下是用Python的requests和xpath和正则表达式爬取豆瓣电影top250详情页的代码：

import requests
from lxml import etree
import re

def get_movie_details(url):
    # 发送请求获取页面内容
    response = requests.get(url)
    html = response.content.decode('utf-8')
    # 解析页面内容
    selector = etree.HTML(html)
    # 获取电影名称
    movie_name = selector.xpath('//h1/span/text()')[0]
    # 获取导演和主演信息
    director_and_cast = selector.xpath('//div[@id="info"]/span[1]/span[@class="attrs"]/a/text()')
    director = director_and_cast[0]
    cast = director_and_cast[1:]
    # 获取上映年份、地区、类型
    year_country_type = selector.xpath('//div[@id="info"]/text()')
    year = re.findall('\d{4}', year_country_type[1])[0]
    country = year_country_type[2].strip().split('/')[0]
    type = year_country_type[2].strip().split('/')[-1]
    # 获取评分和评价人数
    rating = selector.xpath('//strong[@class="ll rating_num"]/text()')[0]
    rating_num = selector.xpath('//div[@class="rating_sum"]/a/span/text()')[0]
    # 获取电影简介
    summary = selector.xpath('//div[@class="indent"]/span[@class="all hidden"]/text()')[0]
    # 构造电影信息字典
    movie_info = {
        '名称': movie_name,
        '导演': director,
        '主演': cast,
        '年份': year,
        '地区': country,
        '类型': type,
        '评分': rating,
        '评价人数': rating_num,
        '简介': summary.strip(),
    }
    return movie_info

if __name__ == '__main__':
    urls = ['https://movie.douban.com/top250?start={}'.format(i) for i in range(0, 250, 25)]
    for url in urls:
        response = requests.get(url)
        html = response.content.decode('utf-8')
        selector = etree.HTML(html)
        # 获取电影详情页链接
        movie_links = selector.xpath('//div[@class="hd"]/a/@href')
        for link in movie_links:
            movie_info = get_movie_details(link)
            print(movie_info)

这段代码会爬取豆瓣电影top250列表页面中每部电影的详情页，并从详情页中提取电影名称、导演和主演、上映年份、地区、类型、评分、评价人数、电影简介等信息，并打印出来。