# !/usr/bin/env python3
# -*- coding:utf-8 -*-
# @Time : 2020/9/20 21:26
# @Author : aslen168
# @File : 测试5.py
# @Software: PyCharm
import sys
from PyQt4 import QtCore, QtGui, QtWebKit
import requests
import bs4
import os
import pathlib
# 根据输入的小说主页,进入小说目录页,获取所有章节的网址。
url = input('请输入小说主页:')
# url = "https://aabook.cc/book.php?id=3100"
domain = url.split('book.php')[0]
# print(domain)
url2 = url.replace('book.php', 'archive.php')
# print(url2)
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}
res = requests.get(url=url2, headers=headers)
res.encoding = res.apparent_encoding # requests包get响应内容中文乱码解决方法
html = res.text
# print(html)
soup = bs4.BeautifulSoup(html, 'html.parser')
# print(soup)
chapters = soup.find(class_="section_list").find_all('a')
# print(chapters[0]['href'])
通过Python的PyQt4,实现对网页加载JS加密内容进行多个URL爬取,如何实现显示当前爬取进度?
最新推荐文章于 2021-08-01 23:13:27 发布