现在的位置: 首页 > 综合 > 正文

python 登录微博、删除指定页微博

2017年01月10日 ⁄ 综合 ⁄ 共 6841字 ⁄ 字号 评论关闭

微博登录的js更新好快啊~之前有一次想登陆就没搞定,现在终于有时间弄弄这个小工具了,顺便练练手。

参考了几个前人的文章:

http://www.douban.com/note/201767245/

http://blog.csdn.net/monsion/article/details/8656690

http://blog.csdn.net/huyoo/article/details/11952603

通过这几篇文章,基本搞懂了登录过程~

通过http://login.sina.com.cn/,看源代码可以发现登录过程的js脚本文件为

Request URL:https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.15)&_=1399711215289

后面的最后一串是请求时间。原来时间的产生方式(v1.4.4)比现在的短了几位,所以还需要对time做个小修改,详见代码。

weiboLogin.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-

import sys
import urllib
import urllib2
import cookielib
import base64
import re
import json
import hashlib
import rsa
import binascii
import time

class weiboLogin:
	cj = cookielib.LWPCookieJar()
	cookie_support = urllib2.HTTPCookieProcessor(cj)
	opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
	urllib2.install_opener(opener)
	postdata = {
		'entry': 'weibo',
		'gateway': '1',
		'from': '',
		'savestate': '7',
		'userticket': '1',
		'ssosimplelogin': '1',
		'vsnf': '1',
		'vsnval': '',
		'su': '',
		'service': 'miniblog',
		'servertime': '',
		'nonce': '',
		'pwencode': 'rsa2',
		'sp': '',
		'encoding': 'UTF-8',
		'prelt': '115',
		'rsakv': '',
		'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
		'returntype': 'META'
	}

	def get_servertime(self,username):
		curtime=int(time.time()*1000)   
		url = r'http://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su=%s&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.15)&_=' %username +str(curtime)
		# print url
		data = urllib2.urlopen(url).read()
		p = re.compile('\((.*)\)')
		# print data
		try:
			json_data = p.search(data).group(1)
			data = json.loads(json_data)
			servertime = str(data['servertime'])
			nonce = data['nonce']
			pubkey = data['pubkey']
			rsakv = data['rsakv']
			return servertime, nonce, pubkey, rsakv
		except:
			print 'Get severtime error!'
			return None

	def get_pwd(self, password, servertime, nonce, pubkey):
		rsaPublickey = int(pubkey, 16)
		key = rsa.PublicKey(rsaPublickey, 65537) #创建公钥
		message = str(servertime) + '\t' + str(nonce) + '\n' + str(password) #拼接明文js加密文件中得到
		passwd = rsa.encrypt(message, key) #加密
		passwd = binascii.b2a_hex(passwd) #将加密信息转换为16进制。
		return passwd

	def get_user(self, username):
		username_ = urllib.quote(username)
		username = base64.encodestring(username_)[:-1]
		return username
	def get_account(self,filename):
		f=file(filename)
		flag = 0
		for line in f:
			if flag == 0:
				username = line.strip()
				flag +=1
			else:
				pwd = line.strip()
		f.close()
		# print username,' ',pwd
		return username,pwd
	def login(self,filename):
		username,pwd = self.get_account(filename)

		url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.15)'
		# try:
		servertime, nonce, pubkey, rsakv = self.get_servertime(username)
		print servertime
		print nonce
		print pubkey
		print rsakv
		# except:
		# 	print 'get servertime error!'
		# 	return
		weiboLogin.postdata['servertime'] = servertime
		weiboLogin.postdata['nonce'] = nonce
		weiboLogin.postdata['rsakv'] = rsakv
		weiboLogin.postdata['su'] = self.get_user(username)
		weiboLogin.postdata['sp'] = self.get_pwd(pwd, servertime, nonce, pubkey)
		weiboLogin.postdata = urllib.urlencode(weiboLogin.postdata)
		print self.get_user(username),self.get_pwd(pwd, servertime, nonce, pubkey)
		headers = {'User-Agent':'Mozilla/5.0 (X11; Linux i686; rv:8.0) Gecko/20100101 Firefox/8.0 Chrome/20.0.1132.57 Safari/536.11'}
		req  = urllib2.Request(
			url = url,
			data = weiboLogin.postdata,
			headers = headers
		)
		result = urllib2.urlopen(req)
		text = result.read()
		self.writefile('./output/textlogin',text)		
		self.writefile('./output/resultlogin',eval("u'''"+text+"'''"))
		p = re.compile('location\.replace\(\'(.*)\'\)')#这里博文用的是双引号,是错的,改成了单引号就好了!
		try:
			login_url = p.search(text).group(1)
			print login_url
			urllib2.urlopen(login_url)
			print "Login success!"
			return 1
		except:
			print 'Login error!'
			return 0

	def writefile(self,filename,content):
		fw = file(filename,'w')
		fw.write(content)
		fw.close()

主程序main.py

# -*- coding: utf-8 -*-

import weiboLogin
import urllib
import urllib2
import time
import getWeiboPage

filename = './config/account'#保存微博账号的用户名和密码,第一行为用户名,第二行为密码,没有空行

WBLogin = weiboLogin.weiboLogin()
if WBLogin.login(filename)==1:
	print 'Login success!'
else:
	print 'Login error!'
	exit()


WBmsg = getWeiboPage.getWeiboPage()
url = 'http://weibo.com/p/1005051447378675/weibo?from=page_100505&mod=TAB#place'
# 'http://weibo.com/274891787?from=otherprofile&wvr=3.6&loc=tagweibo'


WBmsg.get_firstpage(url)
WBmsg.get_secondpage(url)
WBmsg.get_thirdpage(url)

登陆后保存页面的,因为主页有lazy load机制,所以要分三次保存

getWeiboPage.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import urllib
import urllib2
import sys
import time

reload(sys)
sys.setdefaultencoding('utf-8')

class getWeiboPage:
	body = {
		'__rnd':'',
		'_k':'',
		'_t':'0',
		'count':'50',
		'end_id':'',
		'max_id':'',
		'page':1,
		'pagebar':'',
		'pre_page':'0',
		'uid':''
	}
	uid_list = []
	charset = 'utf8'

	def get_msg(self,uid):
		getWeiboPage.body['uid'] = uid
		url = self.get_url(uid)
		self.get_firstpage(url)
		self.get_secondpage(url)
		self.get_thirdpage(url)
	def get_firstpage(self,url):
		getWeiboPage.body['pre_page'] = getWeiboPage.body['page']-1
		url = url +urllib.urlencode(getWeiboPage.body)
		req = urllib2.Request(url)
		result = urllib2.urlopen(req)
		text = result.read()
		self.writefile('./output/text1',text)		
		self.writefile('./output/result1',eval("u'''"+text+"'''"))
		
	def get_secondpage(self,url):
		getWeiboPage.body['count'] = '15'
	#	getWeiboPage.body['end_id'] = '3490160379905732'
	#	getWeiboPage.body['max_id'] = '3487344294660278'
		getWeiboPage.body['pagebar'] = '0'
		getWeiboPage.body['pre_page'] = getWeiboPage.body['page']

		url = url +urllib.urlencode(getWeiboPage.body)
		req = urllib2.Request(url)
		result = urllib2.urlopen(req)
		text = result.read()
		self.writefile('./output/text2',text)		
		self.writefile('./output/result2',eval("u'''"+text+"'''"))
	def get_thirdpage(self,url):
		getWeiboPage.body['count'] = '15'
		getWeiboPage.body['pagebar'] = '1'
		getWeiboPage.body['pre_page'] = getWeiboPage.body['page']

		url = url +urllib.urlencode(getWeiboPage.body)
		req = urllib2.Request(url)
		result = urllib2.urlopen(req)
		text = result.read()
		self.writefile('./output/text3',text)		
		self.writefile('./output/result3',eval("u'''"+text+"'''"))
	def get_url(self,uid):
		url = 'http://weibo.com/' + uid + '?from=otherprofile&wvr=3.6&loc=tagweibo'
		return url
	def get_uid(self,filename):
		fread = file(filename)
		for line in fread:
			getWeiboPage.uid_list.append(line)
			print line
			time.sleep(1)
	def writefile(self,filename,content):
		fw = file(filename,'w')
		fw.write(content)
		fw.close()

删除机制测试了一下,请求返回的是错误页面。。求帮忙~谢谢!

替换getWeiboPage.py里的对应函数~

def get_firstpage(self,url):
		getWeiboPage.body['pre_page'] = getWeiboPage.body['page']-1
		url = url +urllib.urlencode(getWeiboPage.body)
		req = urllib2.Request(url)
		result = urllib2.urlopen(req)
		text = result.read()
		self.writefile('./output/text1.html',text)		
		p = re.compile('{\"ns\":\"pl\.content\.homeFeed\.index\"(.*)"html":"(.*)}')
		try:
			feeds = p.search(text).group(2)
			self.writefile('./output/result1.html',feeds)
			# print feeds,'FEEDS ok'
			eachFeed = re.compile(r'action-data=\\"mid=(\d*)')
			# pp = re.compile(r'mid=(\d+)')
			nodes=eachFeed.findall(feeds)
			middict={}
			print nodes
			for node in nodes:
				middict[node]=1
			for (key,x) in middict.items():
				print "deleting key:"+key
				urldel = 'http://weibo.com/aj/mblog/del?_wv=5'
				postdata = {'mid':key}
				postdata = urllib.urlencode(postdata)
				req  = urllib2.Request(url,postdata)
				result = urllib2.urlopen(req)
				time.sleep(4)
				delresult = result.read()
				print delresult

		except:
			print 'get feed error'

还是有错~求帮忙~

【上篇】
【下篇】

抱歉!评论已关闭.