正则爬取天堂图片网并存储在自动生成文件夹中

 

# -*- coding: utf-8 -*-
__author__ = '木之易'
__date__ = '2018/8/7 20:17'

import os
import re

from urllib import request


class WeddingImageSpider(object):

    def __init__(self, t_id):
        # 拼接完整地址
        self.url = 'http://www.ivsky.com'+t_id
        self.title = 'images'
        self.html = ''
        self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0'}
        self.create_directry()
        self.count = 0

    def create_directry(self):
        """
        创建存放图片的文件夹
        :return:
        """
        # 获取源代码
        self.get_html(self.url)
        # 2.获取帖子标题
        pattern = re.compile(r'', re.S)
        # print(pattern)
        rs = re.search(pattern, self.html)
        # 3.提取帖子标题，并赋值给self.title
        if rs:
            self.title = rs.group(1)
        # 4.判断文件/目录是否存在
        if not os.path.exists(self.title):
            # 没有self.title这个文件夹，创建这个文件夹
            # mkdir() 创建文件夹
            os.mkdir(self.title)

    def get_total(self):
        """获取下一页"""
        self.get_html(self.url)
        pattern = re.compile(r'
(.*?)
', re.S)
        res = re.search(pattern, self.html)
        # 若找到
        if res:
            ul_html = res.group()
            # 找到含图片网址和关键字的标签
            # links = re.findall(re.compile(r"