平時關注比較多的知乎話題，上網的狀態下看著會容易走神，所以寫了個python指令碼用來抓取自己喜歡的問題，然後推送到自己kinle看。

http://www.30daydo.com/article/7

from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from bs4 import BeautifulSoup
from email.MIMEBase import MIMEBase
from email import Encoders
import smtplib
from email import Encoders,Utils
from email.Header import Header
import urllib2,urllib,time,datetime,codecs,sys,re,sys,os
reload(sys)
sys.setdefaultencoding('utf-8')

def save2file(filename,content):
	#儲存為電子書檔案
	filename=filename+".txt"
	f=open(filename,'a')
	f.write(content)
	f.close()


def getAnswer(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)"
	#構造header 偽裝一下
	header={"User-Agent":user_agent}
	req=urllib2.Request(url,headers=header)
	resp=urllib2.urlopen(req)
	
	#這裡已經獲取了 網頁的程式碼，接下來就是提取你想要的內容。 使用beautifulSoup 來處理，很方便
	
	bs=BeautifulSoup(resp,"html.parser")
	title=bs.title
	#獲取的標題

	filename_old=title.string.strip()
	print filename_old
	filename = re.sub('[
 
\/:*?"<>|]','-',filename_old)
	#用來儲存內容的檔名，因為檔名不能有一些特殊符號，所以使用正則表示式過濾掉
	
	save2file(filename,title.string)
	title_content=title.string
	
	answer=
	
	detail=bs.find("div",class_="zm-editable-content")
	user_ids=bs.find_all("a",class_="author-link")

	
	save2file(filename,"\n\n\n\n--------------------Detail----------------------\n\n")
	#獲取問題的補充內容
	
	for i in detail.strings:

		save2file(filename,unicode(i))
	
	answer=bs.find_all("div",class_="zm-editable-content clearfix")
	k=0
	index=0
	for each_answer in answer:
	
		save2file(filename,"\n\n-------------------------answer %s via  -------------------------\n\n" %k)
		
		for a in each_answer.strings:
			#迴圈獲取每一個答案的內容，然後儲存到檔案中
			save2file(filename,unicode(a))
		k+=1
		index=index+1
	
	smtp_server='smtp.126.com'
	from_mail='
 
[email protected]'
	password='yourpassword'
	to_mail='[email protected]'
	send_kindle=MailAtt(smtp_server,from_mail,password,to_mail)
	send_kindle.send_txt(filename)
	#呼叫傳送郵件函式，把電子書傳送到你的kindle使用者的郵箱賬號，這樣你的kindle就可以收到電子書啦
	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
		#初始化郵箱設定
		
	def send_txt(self,filename):
		#這裡傳送附件尤其要注意字元編碼，當時除錯了挺久的，因為收到的檔案總是亂碼
		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()