手写爬虫之糗事百科段子及神回复

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/10/11 16:35
# @Author  : yuantup
# @Site    : 
# @File    : jokes_.py
# @Software: PyCharm


import urllib.request
import re
import os


def open_url(url):
    head = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/5'
                          '37.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
    req = urllib.request.Request(url, headers=head)
    response = urllib.request.urlopen(req)
    html = response.read()
    return html


def get_content(html):
    text1 = html.decode('utf-8')
    text2 = text1.replace('\n', '')
    text3 = text2.replace('<br>', '\n')
    text = text3.replace('<br/>', '\n')
    pattern = '<h2>(.*?)</h2>.*?<div class="content">.*?span>(.*?)</span>.*?<span class="stats-vote"><i class="number">(.*?)</i> 好笑</span>.*?<span class="cmt-name">(.*?)</span><div class="main-text">(.*?)<div class="likenum">.*?(\d*?)</div>'
    all_content_list = re.findall(pattern, text, re.S)
    print(all_content_list)

    for i in range(len(all_content_list)):
        with open('jokes_plus.txt', 'a', encoding='utf-8') as f:
            author = all_content_list[i][0]
            joker_content = all_content_list[i][1]
            fun_num = all_content_list[i][2]
            commentator = all_content_list[i][3]
            comment = all_content_list[i][4]
            dianzan_num = all_content_list[i][5]
            f.write('******这不是一条分界线*****\n\n')
            f.write(author + ':')
            print('1')
            f.write(':\n')
            f.write(joker_content)
            print('2')
            f.write('\n')
            f.write('有')
            f.write(fun_num)
            print('3')
            f.write('人觉得这个段子很好笑，你觉得呢？')
            f.write('\n')
            f.write('神评：')
            f.write('\n')
            f.write(commentator + ':')
            f.write(comment)
            f.write('    点赞数：')
            f.write(dianzan_num)
            f.write('\n\n')


def main():
    path = 'E:\spiser_sons\jokes'
    a = os.getcwd()
    print(a)
    if os.path.exists(path):
        os.chdir(path)
        print(os.getcwd())
    else:
        os.mkdir(path)
        os.chdir(path)

    for i in range(1, 21):
        url = 'https://www.qiushibaike.com/text/page/' + str(i) + '/'
        html = open_url(url)
        get_content(html)


if __name__ == '__main__':
    main()

'<h2>(.*?)</h2>.*?<div class="content">.*?span>(.*?)</span>.*?<span class="stats-vote"><i class="number">(.*?)</i> 好笑</span>.*?<span class="cmt-name">(.*?)</span><div class="main-text">(.*?)<div class="likenum">.*?(\d*?)</div>'

author,  # 段子的作者名

joker_content,  # 段子的内容

fun_num,   # 觉得段子好笑的人数

commentator,  # 神评的作者名

comment, # 神评的内容

dianzan_num  # 神评点赞人数