[Python]豆瓣TOP250的简单爬虫

[Python]豆瓣TOP250的简单爬虫

---

豆瓣TOP250的电影网址是
https://movie.douban.com/top0?start=%d&filter=
其中TOP后面的数字代表当前显示的项目条数，25条一页，将改成25则显示第二页的25条信息。

利用Python的requests库进行请求和Beautifulsoup处理返回的信息，可以很快得到想要扒下来的结果。最后把结果用.txt文件保存下来
Python代码如下

import requests
import json
from bs4 import BeautifulSoup

Film={}
No = 1

def GrabOnePage(page):
    html = 'https://movie.douban.com/top250?start=%d&filter=' %((page - 1) * 25)
    headers = {
        'Host': 'movie.douban.com',
        'Referer': 'https://movie.douban.com/chart',
        'Upgrade-Insecure-Requests': '1',
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
    }
    result = requests.get(html, headers=headers)
    result.encoding = 'utf-8'
    soup = BeautifulSoup(result.text, 'lxml')
    all_list = soup.find('ol', class_='grid_view')
    item_list = all_list.find_all('li')

    for x in item_list:
        global No
        global Film
        pic = x.find('div', class_='pic')
        link = pic.find('a').get('href')
        name = pic.find('img').get('alt')
        grade = x.find('div', class_='star').find('span', class_='rating_num').text
        Film[str(No)] = dict(name=name, grade=grade, link=link)
        #print(Film[str(No)])
        No += 1

def main():
    for i in range(1,11):
        GrabOnePage(i)

    f=open('Douban.txt','w')
    for i in Film:
        f.write(str(i)+":"+str(Film[str(i)])+"\n")
        #print(str(i),end=":")
        #print(Film[str(i)])
    f.close()

if __name__ == '__main__':
    main()