一、構造一個訪問陽光電影網的請求(url,headers)
二、輸出請求的狀態碼
三、輸出請求的網頁源碼
四、將源碼保存成html文件(文件為'moive.html')
查找URL
找到URL
查看編碼方式
1.進去網頁源代碼
WX20170828-173354@2x.png
2.charset
WX20170828-173405@2x.png
import requests
url='http://www.ygdy8.com/'
headers= {
'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',
'Connection':'keep-alive',
'Cookie':'37cs_pidx=1; 37cs_user=37cs44901069952; UM_distinctid=15e28057c4a30f-02b42d1c91d0ef-31617c01-13c680-15e28057c4b997; CNZZDATA5783118=cnzz_eid%3D2068724491-1503909932-null%26ntime%3D1503909932; 37cs_show=69; cscpvrich4016_fidx=1',
'Host':'www.ygdy8.com',
'If-Modified-Since':'Mon, 28 Aug 2017 04:48:57 GMT',
'If-None-Match': "804213f5b81fd31:530",
'Referer' : 'https://www.baidu.com/link?url=utMdaXmlbTPNR8LWph_DbE_m09qwXW-0X52v5rstvIy&wd=&eqid=8aa7bb7d00010f010000000259a3d86e',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36',
}
#定義req為一個request請求的對象
req = requests.get(url,headers=headers)
#獲取請求的狀態碼
status_code = req.status_code
print(status_code)
#指定網頁編碼方式
req.encoding = 'gb2312'
#獲取網頁源碼 用html變量接收 text content方法靈活運用
#html = req.text
html = req.content
print(html)