Python爬虫

环境安装：

BeautifulSoup 是一个可以从 HTML 和 XML 文件中提取数据的 Python 库。

$ pip install beautifulsoup4

代码：

import requests
import bs4
import re

def open_url(url):
    # res = requests.get(url, headers=headers, proxies=proxies)
    res = requests.get(url, headers=headers)

    return res

def find_movies(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
 
    # 电影名
    movies = []
    targets = soup.find_all("div", class_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    # 评分
    ranks = []
    targets = soup.find_all("span", class_="rating_num")
    for each in targets:
        ranks.append(' 评分：%s ' % each.text)

    # 资料
    messages = []
    targets = soup.find_all("div", class_="bd")
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
        except:
            continue

    result = []
    length = len(movies)
    for i in range(length):
        result.append(movies[i] + ranks[i] + messages[i] + '\n')

    return result



def main():
    host = "https://movie.douban.com/top250"
    res = open_url(host)
    
    result = []
   
    result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
        for each in result:
            f.write(each)
    
if __name__ == "__main__":
    main()

• soup是BeautifulSoup的对象，将从网页拿到的html进行解析
• soup.find_all会找出满足条件的参数全部返回