Python爬虫類

毎日寝る前のエピソード、Pythonは自動的にデータを取り、自動的にメールを送信します!爱する彼(彼女)に早く一通送ってください.

# -*- coding: utf-8 -*-
"""
Created on Mon Apr 1 21:25:45 2019
@author: Administrator
"""

import requests
from bs4 import BeautifulSoup
import smtplib
from email.mime.text import MIMEText
import random


def getHTMLText(url,headers):
    try:
        r=requests.get(url,headers=headers,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        #print(r.text)
        return r.text

    except:
        return "    "

def parsehtml(namelist,urllist,html):
    url='http://www.tom61.com/'
    soup=BeautifulSoup(html,'html.parser')
    t=soup.find('dl',attrs={'class':'txt_box'})
    #print(t)
    i=t.find_all('a')
    #print(i)
    for link in i:
        urllist.append(url+link.get('href'))
        namelist.append(link.get('title'))


def parsehtml2(html):
    text=[]
    soup=BeautifulSoup(html,'html.parser')
    t=soup.find('div',class_='t_news_txt')
    for i in t.findAll('p'):
        text.append(i.text)
    #print(text)
    return "
".join(text)

def sendemail(url,headers):

    msg_from='[email protected]'           #     
    passwd='      '             #           
    receivers=['[email protected]']         #     

    subject='         '             #  
    html=getHTMLText(url,headers)
    content=parsehtml2(html)               #  
    msg = MIMEText(content)
    msg['Subject'] = subject
    msg['From'] = msg_from
    msg['To'] = ','.join(receivers)
    try:
        s=smtplib.SMTP_SSL("smtp.qq.com",465) #         
        s.login(msg_from, passwd)
        s.sendmail(msg_from, msg['To'].split(','), msg.as_string())
        print("      ")
    except:
        print("    ")
    finally:
        s.quit()

def main():


    headers = {'User-Agent':'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',
               }

    urllist=[]
    namelist=[]
    for i in range(1,11):
        if i==1:
            url='http://www.tom61.com/ertongwenxue/shuiqiangushi/index.html'
        else:
            url='http://www.tom61.com/ertongwenxue/shuiqiangushi/index_'+str(i)+'.html'
        print ("     %s      ：" % (i))
        print (url+'
')
        html=getHTMLText(url,headers)
        parsehtml(namelist,urllist,html)
    print("      ")
    '''
    for i in urllist:
        html=getHTMLText(i,headers)
        parsehtml2(html)
    '''
    sendemail(random.choice(urllist),headers)
if __name__=='__main__':
    main()