python爬虫-爬取豆瓣电影数据

#!/usr/bin/python
# coding=utf-8
# 作者      :Y0010026
# 创建时间  :2018/12/16 16:27
# 文件      :spider_05.py
# IDE       :PyCharm

import urllib2
import urllib

url = 'https://movie.douban.com/j/new_search_subjects?sort=T&range=0,10'

# 要传递的post方式的数据，有可能会有多组数据
submit_data = {
    'start': 20,
    'tags': '喜剧'
}

# 编码
data = urllib.urlencode(submit_data)

# 构造请求头，创建请求对象
headers = {
    "Accept": "application/json,text/plain,*/*",
    "User-Agent": "Mozilla/5.0(WindowsNT6.1;rv:2.0.1)Gecko/20100101Firefox/4.0.1",
    "Accept-Language": "zh-CN,zh;q=0.8"
}
requset = urllib2.Request(url, data=data, headers=headers)

# 发送请求，获取服务器响应数据
response = urllib2.urlopen(requset)

# 获取爬取到的数据
content = response.read()

# 保存数据
with open('movies.json', 'w') as f:
    f.write(content)