爬虫

# -*- coding: utf-8 -*-
# @Time    : 2019/5/31 19:33
# @Author  : zejin
# @File    : pachong.py

from urllib import request
import re

class Analysis():
    url = 'https://book.douban.com/'
    root_patten = '<div class="cover">([\s\S]*?)</div>'
    name_patten = 'alt="([\s\S]*?)">'
    adress_patten = 'href="([\s\S]*?)" title'

    def __face_connect(self):
        r = request.urlopen(self.url)
        htmls = r.read()
        htmls = str(htmls, encoding='utf-8')
        return htmls

    def __analysis(self,htmls):
        root_htmls = re.findall(self.root_patten, htmls)
        # print(root_htmls)
        ancors = []
        for html in root_htmls:
            name = re.findall(self.name_patten, html)
            adress = re.findall(self.adress_patten, html)
            ancor = {"name":name, "adress":adress}
            ancors.append(ancor)
        # print(ancors)
        return ancors

    def __refine(self, ancors):
        pass

    def go(self):
        htmls = self.__face_connect()
        ancors = self.__analysis(htmls)
        # self.__refine(ancors)
        # ancors = self.__refine(ancors)
        print(ancors)

analysis = Analysis()
analysis.go()

转载于:https://www.cnblogs.com/jinbaobao/p/10959606.html