python 爬虫超级课程表话题时出错，请问各位大神如何解决

Posted 2023-03-21

# -*- coding: utf8 -*-
import urllib2
from cookielib import CookieJar
import json

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

def load(timestamp, headers, url):
headers['Content-Length'] = '155'
loadData ='platform=1&phoneVersion=23&phoneBrand=Xiaomi×tamp=0&versionNumber=7.5.0&selectType=0&phoneModel=MI+4LTE&channel=XiaoMiMarket&topicId=13&genderType=-1&'
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=
'Accept-Encoding': 'gzip',
'User-Agent': 'Dalvik/2.1.0 (Linux; U; android 6.0.1; MI 4LTE MIUI/6.6.16)',
'Content-Length': '215',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Connection': 'Keep-Alive',
'Host': '120.55.151.61',

loginData = 'platform=1&password=2564677763D413C3FF12B347528A8226&phoneVersion=23&phoneBrand=Xiaomi&account=2FEB8EB9AE2A2ABF8B8A6726BE1760BF&versionNumber=7.5.0&phoneModel=MI+4LTE&deviceCode=865372021434169&channel=XiaoMiMarket&'
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

topicData ='platform=1&phoneVersion=23&phoneBrand=Xiaomi×tamp=0&versionNumber=7.5.0&selectType=0&phoneModel=MI+4LTE&channel=XiaoMiMarket&topicId=13&genderType=-1&'
headers['Content-Length'] = '155'
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)

报错信息

参考技术A 这个有主要有两种可能：
你生成的url不正确，这个你可以打印一下，找一个报503的url直接在url里访问，看看是否有问题。
亚马逊判断出你是爬虫，给禁止返回数据了，这个就需要伪装一下你的爬虫，比如修改爬取间隔，随机使用http header，或者使用代理ip。

import urllib
if __name__ == '__main__':
enc = r"%C0%FA%CA%B7%C9%CF%C4%C7%D0%A9%C5%A3%C8%CB%C3%C7.PDF"
string = urllib.unquote(enc).decode('gb2312')
print type(string), string

这是python2的，简单点。只能帮这么多了。 参考技术B 　if (myreader.HasRows)
　　
　　MessageBox.Show(myreader.GetString("email") );
　　
　　
　　myreader.Close();
　　mycon.Close();

Python爬虫：抓取手机APP的数据

摘要: 大多数APP里面返回的是json格式数据，或者一堆加密过的数据 。这里以超级课程表APP为例，抓取超级课程表里用户发的话题。

1、抓取APP数据包

    方法详细可以参考这篇博文：http://my.oschina.net/jhao104/blog/605963

    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。

 

---

2、登录

登录代码：

#python学习交流群：125240963
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

 

---

3、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。详见：http://my.oschina.net/jhao104/blog/547311

    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：

python学习交流群：125240963

转载请注明来源：http://my.oschina.net/jhao104/blog/606922