6-豆瓣剧情排行爬虫

爬去豆瓣排行

#_*_ coding: utf-8 _*_

'''
Created on 2018年7月13日
@author: sss
功能：爬取豆瓣剧情排行榜的json数据

'''

import urllib.request
import urllib.response
import urllib.parse
import random

url = "https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90"

#user-agent列表，每次请求随机选一个：
ua_list = [
    "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36",
    "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko",
    "Mozilla/5.0 (X11; CrOS i686 2268.111.0)like Gecko",
    "Mozilla/5.0 (Macintosh; U; PPC Mac OS X ",
    "Mozilla/5.0 (Macintosh; Intel Mac OS "
]

user_agnet = random.choice(ua_list)

headers = {
        'User_Agnet': user_agnet
    }

formdata = {
        "action" : "",
        "start" : "0",    #起始的电影编号
        "limit" : "3",    #从起始开始计数的数量
    }
 
data = urllib.parse.urlencode(formdata).encode(encoding='utf_8')
 
request = urllib.request.Request(url, headers = headers, data = data)
 
response = urllib.request.urlopen(request)

html = response.read()

print(html)

with open('douban.html', 'wb+') as f:
    f.write(html)

print('finish!')