最近有个小需求,爬取新浪微博的粉丝信息,弄了好几天,终于搞定,送上代码:
环境:
系统:windows 7
版本:python 3.3
IDE: PyCharm 4.0.4
参考:http://blog.csdn.net/crystal_zero/article/details/51154632
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import time
import base64
import rsa
import binascii
import requests
import re
import random
try:
import cookielib
except:
import http.cookiejar as cookielib
try:
from PIL import Image
except:
pass
try:
from urllib.parse import quote_plus
except:
from urllib import quote_plus
'''
如果没有开启登录保护,不用输入验证码就可以登录
如果开启登录保护,需要输入验证码
'''
# 构造 Request headers
agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0'
headers = {
# "Host": "www.weibo.com",
'User-Agent': agent
}
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename='cookies')
try:
session.cookies.load(ignore_discard=True)
except:
print("Cookie 未能加载")
# 访问 初始页面带上 cookie
index_url = "http://weibo.com/login.php"
try:
session.get(index_url, headers=headers, timeout=2)
except:
session.get(index_url, headers=headers)
try:
input = raw_input
except:
pass
def get_su(username):
"""
对 email 地址和手机号码 先 javascript 中 encodeURIComponent
对应 Python 3 中的是 urllib.parse.quote_plus
然后在 base64 加密后decode
"""
username_quote = quote_plus(username)
username_base64 = base64.b64encode(username_quote.encode("utf-8"))
return username_base64.decode("utf-8")
# 预登陆获得 servertime, nonce, pubkey, rsakv
def get_server_data(su):
pre_url = "http://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su="
pre_url = pre_url + su + "&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.18)&_="
pre_url = pre_url + str(int(time.time() * 1000))
pre_data_res = session.get(pre_url, headers=headers)
sever_data = eval(pre_data_res.content.decode("utf-8").replace("sinaSSOController.preloginCallBack", ''))
return sever_data
# print(sever_data)
def get_password(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
message = message.encode("utf-8")
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_cha(pcid):
cha_url = "http://login.sina.com.cn/cgi/pin.php?r="
cha_url = cha_url + str(int(random.random() * 100000000)) + "&s=0&p="
cha_url = cha_url + pcid
cha_page = session.get(cha_url, headers=headers)
with open("cha.jpg", 'wb') as f:
f.write(cha_page.content)
f.close()
try:
im = Image.open("cha.jpg")
im.show()
im.close()
except:
print(u"请到当前目录下,找到验证码后输入")
def login(username, password):
# su 是加密后的用户名
su = get_su(username)
sever_data = get_server_data(su)
servertime = sever_data["servertime"]
nonce = sever_data['nonce']
rsakv = sever_data["rsakv"]
pubkey = sever_data["pubkey"]
showpin = sever_data["showpin"]
password_secret = get_password(password, servertime, nonce, pubkey)
postdata = {
'entry': 'weibo',
'gateway': '1',
'from': '',
'savestate': '7',
'useticket': '1',
'pagerefer': "http://login.sina.com.cn/sso/logout.php?entry=miniblog&r=http%3A%2F%2Fweibo.com%2Flogout.php%3Fbackurl",
'vsnf': '1',
'su': su,
'service': 'miniblog',
'servertime': servertime,
'nonce': nonce,
'pwencode': 'rsa2',
'rsakv': rsakv,
'sp': password_secret,
'sr': '1366*768',
'encoding': 'UTF-8',
'prelt': '115',
'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
'returntype': 'META'
}
login_url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)'
if showpin == 0:
login_page = session.post(login_url, data=postdata, headers=headers)
else:
pcid = sever_data["pcid"]
get_cha(pcid)
postdata['door'] = input(u"请输入验证码")
login_page = session.post(login_url, data=postdata, headers=headers)
login_loop = (login_page.content.decode("GBK"))
# print(login_loop)
pa = r'location\.replace\([\'"](.*?)[\'"]\)'
loop_url = re.findall(pa, login_loop)[0]
# print(loop_url)
# 此出还可以加上一个是否登录成功的判断,下次改进的时候写上
login_index = session.get(loop_url, headers=headers)
uuid = login_index.text
uuid_pa = r'"uniqueid":"(.*?)"'
uuid_res = re.findall(uuid_pa, uuid, re.S)[0]
web_weibo_url = "http://weibo.com/%s/profile?topnav=1&wvr=6&is_all=1" % uuid_res
weibo_page = session.get(web_weibo_url, headers=headers)
weibo_pa = r'<title>(.*?)</title>'
# print(weibo_page.content.decode("utf-8"))
contents = re.findall(weibo_pa, weibo_page.content.decode("utf-8", 'ignore'), re.S)
if len(contents):
userID = contents[0]
print(u"欢迎你 %s, 你在正在使用 xchaoinfo 写的模拟登录微博" % userID)
session.cookies.save()
return True
else:
return False
def getWeiboPageContent(url):
import requests
from selenium import webdriver
import time
# webdriver.DesiredCapabilities.PHANTOMJS['phantomjs.page.customHeaders.Cookie'] = 'SINAGLOBAL=3955422793326.2764.1451802953297; wb_publish_vip_1888964862=2; YF-Page-G0=9a31b867b34a0b4839fa27a4ab6ec79f; _s_tentry=123.sogou.com; Apache=3233757158741.355.1460597853009; ULV=1460597853022:23:7:4:3233757158741.355.1460597853009:1460533608651; YF-V5-G0=24e0459613d3bbdec61239bc81c89e13; YF-Ugrow-G0=3a02f95fa8b3c9dc73c74bc9f2ca4fc6; login_sid_t=9c9ff740ffffbdf23415b871aa319ec0; TC-Ugrow-G0=e66b2e50a7e7f417f6cc12eec600f517; TC-V5-G0=7e5b74ea4beaaa98b5f592db11c2eeb9; myuid=5898063885; TC-Page-G0=1e758cd0025b6b0d876f76c087f85f2c; wvr=6; SSOLoginState=1460604791; un=1654916845@qq.com; user_active=201604141220; user_unver=b37741d33507619aa07b6d512be0dd67; SUS=SID-5898063885-1460616073-XD-a0vlz-c7f218016d290c52b4297371d3942ce7; SUE=es%3D5ec8e6a39470b9d75e4cf930977a7449%26ev%3Dv1%26es2%3D2b500477fcc5dc1560b4aee4d5ca9be5%26rs0%3Daeb6LPcKR9mfwMB31yJquO6NSXgRd9BpSLAcKEdCQjtUOM7pIzDblRVIOOItI22Uc6pLjTxUc6k7s0zIgIxar9JlVdPjOiHEGijE2ucUP6GjFv%252BJWntWR7szF3qcWknPBJzemeHiThBGRF0bAcNFHcH%252BY9VfrTaIVjXCUsO93B8%253D%26rv%3D0; SUP=cv%3D1%26bt%3D1460616073%26et%3D1460702473%26d%3Dc909%26i%3D2ce7%26us%3D1%26vf%3D0%26vt%3D0%26ac%3D27%26st%3D0%26uid%3D5898063885%26name%3D1654916845%2540qq.com%26nick%3Dforfun2016%26fmp%3D%26lcp%3D; SUB=_2A256C0vZDeTxGeNG4loR9i3EwzmIHXVZYToRrDV8PUJbvNAPLXX2kW9LHet_3CJqcXTqa57ddP1X0MxCpd6bSA..; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WhFdfTB9.lOPTcSpGQskYri5JpX5K-t; SUHB=0z1QUpglvHBm_i; ALF=1492143611; UOR=far.tooold.cn,widget.weibo.com,login.sina.com.cn; WBtopGlobal_register_version=ab9111fb56d70a2b'
#这个地方可以设置 header, 代理等一些参数
cap = webdriver.DesiredCapabilities.PHANTOMJS
cap["phantomjs.page.settings.resourceTimeout"] = 1000
cap["phantomjs.page.settings.loadImages"] = False
cap["phantomjs.page.settings.disk-cache"] = True
cap["phantomjs.page.customHeaders.Cookie"] = 'SINAGLOBAL=1090764576516.7528.1472895523482;' \
'ULV=1473054803412:3:3:2:8569250075753.363.1473054803408:1472968709618;' \
'SCF=AsEbWSFBj4yI1a200LCVvAmkggqyRCHJ705_J2slnQgOZiIr6H6PjN2HTWiP8y_wK4rtnl9XPpwDIkzi3Do0iHg.;' \
'SUHB=0wn1u-A905WJz_;' \
'un=18704027874;' \
'UOR=,,www.baidu.com;' \
'wvr=6;' \
'SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WFwo9sl7cB8PE.FyBvPnqYc5JpX5K2hUgL.Foq7eKe0S0.7SKz2dJLoIEBLxK-LBo2LBK5LxK.L1KzL1-qLxK-LB.eL1heLxK-LBo2LBK5t;' \
'YF-Ugrow-G0=1eba44dbebf62c27ae66e16d40e02964;' \
'YF-V5-G0=5f9bd778c31f9e6f413e97a1d464047a;' \
'YF-Page-G0=8ec35b246bb5b68c13549804abd380dc;' \
'WBtopGlobal_register_version=370d73e0c771001f;' \
'login_sid_t=1a1f99aaff13878558a61d66c6b9c0a4;' \
'_s_tentry=www.baidu.com;' \
'Apache=8569250075753.363.1473054803408;' \
'SSOLoginState=1473054827;' \
'SUB=_2A256yvvYDeTxGeBO6lES9yfMzj6IHXVZvmoQrDV8PUJbmtBeLWyjkW8OibLNYiqudnUDwBp6GgtGcUnFuQ..' #我删掉了一大部分
driver = webdriver.PhantomJS(executable_path="D:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe", desired_capabilities=cap)
driver.set_window_size(1120, 1100)
# print(url)
driver.get(url)
page_source = driver.page_source
# print(t)
#
# contents = driver.find_elements_by_tag_name("<a>")
#
# for content in contents:
# print(content.text)
return page_source
from lib3 import spider
from lib3 import fileWriter
import os
import sys
class weiboSpider:
def __init__(self,userAgent,userName,password):
self.sp = spider.Spider(userAgent)
self.loginStatus = login(userName, password)
def go(self,url):
status = True
pageIndex = 1
while status == True:
fix = str(pageIndex)+"#Pl_Official_HisRelation__63"
curUrl = url+fix
print(curUrl)
status = self.parse(curUrl)
pageIndex += 1
def cur_file_dir(self):
#获取脚本路径
path = sys.path[0]
#判断为脚本文件还是py2exe编译后的文件,如果是脚本文件,则返回的是脚本的目录,如果是py2exe编译后的文件,则返回的是编译后的文件路径
if os.path.isdir(path):
return path
elif os.path.isfile(path):
return os.path.dirname(path)
def saveData(self,fansUrl,fansId):
fHandle = fileWriter.FileWriter(self.cur_file_dir(),'zhiHuData.txt','a')
fHandle.write(fansUrl+'\t'+fansId+'\r\n')
fHandle.close()
def parse(self,url):
if self.loginStatus == True:
content = getWeiboPageContent(url)
strPattern = '''<a class="S_txt1" target="_blank" usercard=".*?" href="(.*?)">(.*?)</a>'''
resultsList = self.sp.parseReg(content,strPattern,2)
if len(resultsList):
for i in range(0,len(resultsList)):
fansUrl = "http://wei.com"+resultsList[i][0]
fansId = resultsList[i][1]
self.saveData(fansUrl,fansId)
print(fansUrl,fansId)
return True
else:
print("no data")
return False
else:
print("sorry,can not login weibo")
if __name__ == "__main__":
demo = weiboSpider('Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko','在此填写用户名','密码')
demo.go('http://weibo.com/p/1005053810677006/follow?relate=fans&page=')
上面引用的lib3是我自己写的一个http接口
fileWriter.py
__author__ = 'zhengjinwei'
#coding=utf-8
import os
class FileWriter:
def __init__(self,fileDir,fileName,format):
self.mkDir(fileDir)
self.f = open(fileDir+u"/"+fileName,format)
def mkDir(self,path):
isExists = os.path.exists(path)
if not isExists:
os.makedirs(path)
def write(self,contents):
return self.f.write(contents)
def close(self):
self.f.close()
#coding:utf-8
__author__ = 'zhengjinwei'
import re
import requests
try:
import cookielib
except:
import http.cookiejar as cookielib
class Spider:
def __init__(self,userAgent):
self.user_agent = userAgent
self.headers = {
'User-Agent' : self.user_agent
}
def getHttp(self,url,param=None):
return requests.get(url,param,headers=self.headers)
def postHttp(self,url,postData=None):
return requests.post(url, data=postData,headers=self.headers)
def sessionPostHttp(self,url,param=None):
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename='cookies')
try:
session.cookies.load(ignore_discard=True)
print(url,param)
return session.post(url,data=param,json=None,headers=self.headers)
except:
print("Cookie 未能加载")
return None
def sessionGetHttp(self,url,param=None):
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename='cookies')
try:
session.cookies.load(ignore_discard=True)
return session.get(url, headers=self.headers, allow_redirects=False)
except:
print("Cookie 未能加载")
return None
def parseReg(self,content,strPattern,count):
pattern = re.compile(strPattern,re.S)
items = re.findall(pattern,content)
contents=[]
for item in items:
temArr = []
for i in range(0,count):
temArr.append(item[i])
contents.append(temArr)
return contents
def getContents(self,url,strPattern,count,method="get",param=None):
page = ""
if method == "get":
page = self.getHttp(url,param).text
else:
page = self.postHttp(url,param).text
pattern = re.compile(strPattern,re.S)
items = re.findall(pattern,page)
contents=[]
for item in items:
temArr = []
for i in range(0,count):
temArr.append(item[i])
contents.append(temArr)
return contents
# demo = Spider("Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko")
#
# t = demo.getHttp("https://www.baidu.com/index.php?tn=02049043_23_pg")
效果图:
注意事项:
1,新浪微博本身有查看限制,只能查看到前5页的数据
2,爬虫工具可以使用火狐浏览器,装上fireDebug 插件用于拦截消息,获取cookie和其他参数