Python学习之路-爬虫提高:框架功能完善

import requests
from bs4 import BeautifulSoup
import re
import os
 
class DoubanCrawler:
    def __init__(self, start_url):
        self.start_url = start_url
        self.headers = {
            'User-Agent': 'Mozilla/5.0',
            'Cookie': 'your_cookie_here'  # 替换为你的cookie
        }
        self.movie_details_urls = []
        self.movies = []
 
    def get_page_content(self, url):
        response = requests.get(url, headers=self.headers)
        if response.status_code == 200:
            return response.text
        return None
 
    def parse_index_page(self, content):
        soup = BeautifulSoup(content, 'html.parser')
        movie_divs = soup.find_all('div', class_='item')
        for movie_div in movie_divs:
            movie_details_url = movie_div.find('a')['href']
            self.movie_details_urls.append(movie_details_url)
 
    def parse_detail_page(self, content):
        soup = BeautifulSoup(content, 'html.parser')
        movie_title = soup.find('span', property='v:itemreviewed').text
        movie_rating_score = float(soup.find('strong', class_='ll rating_num').text)
        movie_rating_people = int(re.findall('\d+', soup.find('div', class_='rating').text)[0])
        movie_quote = soup.find('span', property='v:summary').text
        self.movies.append({
            'title': movie_title,
            'rating_score': movie_rating_score,
            'rating_people': movie_rating_people,
            'quote': movie_quote
        })
 
    def run(self):
        index_content = self.get_page_content(self.start_url)
        if index_content:
            self.parse_index_page(index_content)
            for url in self.movie_details_urls:
                detail_content = self.get_page_content(url)
                if detail_content:
                    self.parse_detail_page(detail_content)
        return self.movies
 
if __name__ == '__main__':
    crawler = DoubanCrawler('https://movie.douban.com/top250')
    movies = crawler.run()
    print(movies)

这段代码实现了一个简单的基于Python的豆瓣电影TOP250爬虫。它首先通过请求库获取电影TOP250列表页的内容，然后使用BeautifulSoup进行页面解析以提取电影详情页的URL。接着，它遍历这些URL并获取每部电影的详细信息，包括电影名称、评分、评分人数和引言，最后将这些信息存储在一个列表中。这