Python爬虫:抓取手机APP的数据

网络爬虫

浏览数:685

2018-2-3

AD:资源代下载服务

抓取APP数据包

得到超级课程表登录的地址:http://120.55.151.61/V2/StudentSkip/loginCheckV4.action

表单:

表单中包括了用户名和密码,当然都是加密过了的,还有一个设备信息,直接post过去就是。

另外必须加header,一开始我没有加header得到的是登录错误,所以要带上header信息。

登录

登录代码:

import urllib2
from cookielib import CookieJar
loginUrl = 'http://120.55.151.61/V2/StudentSkip/loginCheckV4.action'
headers = {
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'User-Agent': 'Dalvik/1.6.0 (Linux; U; Android 4.1.1; M040 Build/JRO03H)',
    'Host': '120.55.151.61',
    'Connection': 'Keep-Alive',
    'Accept-Encoding': 'gzip',
    'Content-Length': '207',
    }
loginData = 'phoneBrand=Meizu&platform=1&deviceCode=868033014919494&account=FCF030E1F2F6341C1C93BE5BBC422A3D&phoneVersion=16&password=A55B48BB75C79200379D82A18C5F47D6&channel=MXMarket&phoneModel=M040&versionNumber=7.2.1&'cookieJar = CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookieJar))
req = urllib2.Request(loginUrl, loginData, headers)
loginResult = opener.open(req).read()
print loginResult

登录成功 会返回一串账号信息的json数据

和抓包时返回数据一样,证明登录成功

抓取数据

用同样方法得到话题的url和post参数

做法就和模拟登录网站一样。

下见最终代码,有主页获取和下拉加载更新。可以无限加载话题内容。

#!/usr/local/bin/python2.7
# -*- coding: utf8 -*-
"""
  超级课程表话题抓取
"""
import urllib2
from cookielib import CookieJar
import json

''' 读Json数据 '''
def fetch_data(json_data):  
   data = json_data['data']
   timestampLong = data['timestampLong']
   messageBO = data['messageBOs']
   topicList = []
   for each in messageBO:
     topicDict = {}
     if each.get('content', False):
       topicDict['content'] = each['content']
       topicDict['schoolName'] = each['schoolName']
       topicDict['messageId'] = each['messageId']
       topicDict['gender'] = each['studentBO']['gender']
       topicDict['time'] = each['issueTime']
       print each['schoolName'],each['content']
       topicList.append(topicDict)
    return timestampLong, topicList
   
''' 加载更多 '''
def load(timestamp, headers, url):
  headers['Content-Length'] = '159'  
  loadData = 'timestamp=%s&phoneBrand=Meizu&platform=1&genderType=-1&topicId=19&phoneVersion=16&selectType=3&channel=MXMarket&phoneModel=M040&versionNumber=7.2.1&' % timestamp
  req = urllib2.Request(url, loadData, headers)
  loadResult = opener.open(req).read()
  loginStatus = json.loads(loadResult).get('status', False)
  if loginStatus == 1:
     print 'load successful!'        
       timestamp, topicList = fetch_data(json.loads(loadResult))
     load(timestamp, headers, url)
  else:
     print 'load fail'        
       print loadResult
     return False

loginUrl = 'http://120.55.151.61/V2/StudentSkip/loginCheckV4.action'
topicUrl = 'http://120.55.151.61/V2/Treehole/Message/getMessageByTopicIdV3.action'
headers = {
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'User-Agent': 'Dalvik/1.6.0 (Linux; U; Android 4.1.1; M040 Build/JRO03H)',
    'Host': '120.55.151.61',
    'Connection': 'Keep-Alive',
    'Accept-Encoding': 'gzip',
    'Content-Length': '207',
    }
''' ---登录部分--- '''
loginData = 'phoneBrand=Meizu&platform=1&deviceCode=868033014919494&account=FCF030E1F2F6341C1C93BE5BBC422A3D&phoneVersion=16&password=A55B48BB75C79200379D82A18C5F47D6&channel=MXMarket&phoneModel=M040&versionNumber=7.2.1&'cookieJar = CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookieJar))
req = urllib2.Request(loginUrl, loginData, headers)
loginResult = opener.open(req).read()
loginStatus = json.loads(loginResult).get('data', False)
if loginResult:
    print 'login successful!'
else:
    print 'login fail'
    print loginResult

''' ---获取话题--- '''
topicData = 'timestamp=0&phoneBrand=Meizu&platform=1&genderType=-1&topicId=19&phoneVersion=16&selectType=3&channel=MXMarket&phoneModel=M040&versionNumber=7.2.1&'
headers['Content-Length'] = '147'
topicRequest = urllib2.Request(topicUrl, topicData, headers)
topicHtml = opener.open(topicRequest).read()
topicJson = json.loads(topicHtml)
topicStatus = topicJson.get('status', False)
print topicJson
if topicStatus == 1:
    print 'fetch topic success!'
    timestamp, topicList = fetch_data(topicJson)
    load(timestamp, headers, topicUrl)

结果

来自:开源中国-j_hao104
https://my.oschina.net/jhao104/blog/606922