豆瓣电影TOP250爬取

import requests
from pyquery import PyQuery as pq

url = ‘https://movie.douban.com/top250?start=’
def get_onepage(url):
headers = {
‘user_agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36’
}
html = requests.get(url,headers = headers).text
doc = pq(html)
#print(doc(’.grid_view .item’))
iteams = doc(’.grid_view .item’).items()
for item in iteams:
title = item.find(’.title’).text()
actor = item.find(’.bd’).text()
file = open(‘doubanmovice.txt’,‘a’,encoding=‘utf-8’)
file.write(’\n’.join([title,actor]))
file.write(’\n’+ ‘=’ *50 + ‘\n’)
file.close()

def all_page():
for num in range(0,250,25):
get_onepage(url + str(num))

all_page()