当前位置:天才代写 > tutorial > Python教程 > Python爬虫-抓取手机APP数据

Python爬虫-抓取手机APP数据

2018-05-17 08:00 星期四 所属: Python教程 浏览:516

抓取超级课程表话题数据。
博文:http://my.oschina.net/jhao104/blog/606922“` python

!/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)
data = load(timestamp, headers, topicUrl)
if data:
timestamp, topicList = fetch_data(data)
“`

标签:python

 

    关键字:

天才代写-代写联系方式