【Python爬虫】第三周练习(13)
2018-01-12 本文已影响10人
Doggy米
一、构造一个访问阳光电影网的请求(url,headers)
二、输出请求的状态码
三、输出请求的网页源码
四、将源码保存成html文件(文件为'moive.html')
import requests
url = "http://www.ygdy8.com/"
header_str = '''
Accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8
Accept-Encoding:gzip, deflate
Accept-Language:zh-CN,zh;q=0.8
Cache-Control:max-age=0
Cookie:37cs_pidx=1; 37cs_user=37cs96544059545; UM_distinctid=160e80f56031c9-0c9b01c124c227-6d1b117c-1fa400-160e80f5607f4; CNZZDATA5783118=cnzz_eid%3D2025418817-1515716500-null%26ntime%3D1515716500; 37cs_show=69; cscpvrich4016_fidx=1
Host:www.ygdy8.com
If-Modified-Since:Thu, 11 Jan 2018 15:12:16 GMT
If-None-Match:"0c8cb90ee8ad31:54c"
Proxy-Connection:keep-alive
Referer:https://www.google.co.uk/
Upgrade-Insecure-Requests:1
User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.79 Safari/537.36
'''
header_list = header_str.strip().split('\n')
headers_dict = {x.split(':')[0]: x.split(':')[1] for x in header_list}
req = requests.get(url,headers_dict)
req.encoding = "gb2312"
print(req.status_code)
print(req.text)
with open('moive.html', "w", encoding="gb2312") as target_file:
target_file.write(req.text)
