用python爬取app照片

首先下载一个斗鱼（不下载也可以，url都在这了对吧）

　　通过抓包，抓取到一个json的数据包，得到下面的地址

　　观察测试可知，通过修改offset值就是相当于app的翻页

　　访问这个url，返回得到的是一个大字典，字典里面两个索引，一个error，一个data。而data又是一个长度为20的数组，每个数组又是一个字典。每个字典中又有一个索引，vertical_src。

　　我们的目标就是它了！

 import urllib.parse
 import urllib
 import json
 import urllib.request
 data_info={}
 data_info['type']='AUTO'
 data_info['doctype']='json'
 data_info['xmlVersion']='1.6'
 data_info['ue']='UTF-8'
 data_info['typoResult']='true'
 head_info={}
 head_info['User-Agent']='DYZB/2.271 (iphone; iOS 9.3.2; Scale/3.00)'
 url='http://capi.douyucdn.cn/api/v1/getVerticalRoom?aid=ios&client_sys=ios&limit=20&offset=20'
 data_info=urllib.parse.urlencode(data_info).encode('utf-8')
 print(data_info)
 requ=urllib.request.Request(url,data_info)
 requ.add_header('Referer','http://capi.douyucdn.cn')
 requ.add_header('User-Agent','DYZB/2.271 (iphone; iOS 9.3.2; Scale/3.00)')
 response=urllib.request.urlopen(requ)
 print(response)
 html=response.read().decode('utf-8')

这短短20多行代码就能返回得到json数据了。然后再通过对这json代码的切片，分离得到每个主播照片的url地址。

然后得到这一页的照片

 import json
 import urllib.request
 data_info={}
 data_info['type']='AUTO'
 data_info['doctype']='json'
 data_info['xmlVersion']='1.6'
 data_info['ue']='UTF-8'
 data_info['typoResult']='true'

 url+str(i)='http://capi.douyucdn.cn/api/v1/getVerticalRoom?aid=ios&client_sys=ios&limit=20&offset='+str(x)
 data_info=urllib.parse.urlencode(data_info).encode('utf-8')
 print(data_info)
 requ=urllib.request.Request(url,data_info)
 requ.add_header('Referer','http://capi.douyucdn.cn')
 requ.add_header('User-Agent','DYZB/2.271 (iphone; iOS 9.3.2; Scale/3.00)')
 response=urllib.request.urlopen(requ)
 print(response)
 html=response.read().decode('utf-8')
 '''
  print(type(dictionary))
 print(type(dictionary[data]))
 '''
 dictionary=json.loads(html)
 data_arr=dictionary["data"]
 for i in range(0,19):
     name=data_arr[i]["nickname"]
     img_url=data_arr[i]["vertical_src"]
29     print(type(img_url))
     respon_tem=urllib.request.urlopen(img_url)
31     anchor_img=respon_tem.read()
     with open('../photos/'+name+'.jpg','wb') as f:
         f.write(anchor_img)

然后修改一下，让它有了翻页的功能

 import urllib.parse
 import urllib
 import json
 import urllib.request
 data_info={}
 data_info['type']='AUTO'
 data_info['doctype']='json'
 data_info['xmlVersion']='1.6'
 data_info['ue']='UTF-8'
 data_info['typoResult']='true'
 data_info=urllib.parse.urlencode(data_info).encode('utf-8')

 for x in range(0,195):
     url='http://capi.douyucdn.cn/api/v1/getVerticalRoom?aid=ios&client_sys=ios&limit=20&offset='+str(x)
     print(data_info)
     requ=urllib.request.Request(url,data_info)
     requ.add_header('Referer','http://capi.douyucdn.cn')
     requ.add_header('User-Agent','DYZB/2.271 (iphone; iOS 9.3.2; Scale/3.00)')
     response=urllib.request.urlopen(requ)
     print(response)
     html=response.read().decode('utf-8')
     dictionary=json.loads(html)
     data_arr=dictionary["data"]
     for i in range(0,19):
         name=data_arr[i]["nickname"]
         img_url=data_arr[i]["vertical_src"]
         print(type(img_url))
         respon_tem=urllib.request.urlopen(img_url)
         anchor_img=respon_tem.read()
         with open('../photos/'+name+'.jpg','wb') as f:
             f.write(anchor_img)

然后就等着吧~~

最好设置一下时间，每隔多久爬一次，或者每隔多久更换一次ip。就行了