爬取抽屉

import requests
import re

class chouti:
    def __init__(self):
        self.agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36"
        self.host = "dig.chouti.com"
        self.headers = {
            'Host':self.host,
            'User-Agent':self.agent
        }
        self.session = requests.session()
        self.pageIndex = 1

    def getPage(self,pageIndex):
        url = "http://dig.chouti.com/all/hot/recent/" + str(pageIndex)
        response = self.session.get(url)
        pattern = re.compile('<div class="news.*?>.*?<a href=(.*?) class="show.*?>.*?<div class="part2" share-pic=(.*?) share-title=.*?>.*?<span class="hand-icon .*?</span>.*?<b>(.*?)</b>',re.S)
        items = re.findall(pattern, response.text)
        for item in items:
            print(item[0] + '\n' + item[1] + '\n'+item[3])


ct = chouti()
chouti.getPage(ct, ct.pageIndex)

import requests
import re

class chouti:
    def __init__(self):
        self.agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36"
        self.host = "dig.chouti.com"
        self.headers = {
            'Host':self.host,
            'User-Agent':self.agent
        }
        self.session = requests.session()
        self.pageIndex = 1
        self.news = []

    def getPage(self,pageIndex):
        url = "http://dig.chouti.com/all/hot/recent/" + str(pageIndex)
        response = self.session.get(url)
        pattern = re.compile('<div class="news.*?>.*?<a href=(.*?) class="show.*?>.*?<div class="part2" share-pic=(.*?) share-title=.*?>.*?<span class="hand-icon .*?</span>.*?<b>(.*?)</b>',re.S)
        # pattern = re.compile('<div class="news.*?>.*?<a href=(.*?) class="show.*?>.*?<div class="part2" share-pic=(.*?) share-title=.*?>.*?<span class="hand-icon .*?</span>.*?<b>(.*?)</b>',
        #     re.S)
        items = re.findall(pattern, response.text)
        for item in items:
            print(item[0] + '\n' + item[1] + '\n'+item[2])
            self.news.append(item)

    def getRefreshen(self):
        page = 1
        while page <= 5:
            self.getPage(page)
            page+=1
        self.downLoad()

    def downLoad(self):
        f = open('chouti.txt', 'a')
        for item in self.news:
            f.write(item[0] + '\n' + item[1] + '\n' + item[2] + '\n\n')
        f.close()

    def start(self):
        self.getRefreshen()
ct = chouti()
ct.start()

import re
import requests

session = requests.session()
index = 1
try:
    f = open('chouti.txt','r')
    txt = f.read()
    pattern = re.compile('http://(.*?).jpg|http://(.*?).png',re.S)
    items = re.findall(pattern, txt)
    for item in items:
        url = "http://" + item + ".jpg"
        respone = session.get(url)
        f1 = open(str(index)+".jpg", 'wb')
        f1.write()
        f1.close()

finally:
    f.close()