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
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
