0
点赞
收藏
分享

微信扫一扫

网络小说下载python爬虫记录

小迁不秃头 2023-03-07 阅读 86


# -*- coding:gbk -*-
import requests
from bs4 import BeautifulSoup
import urllib.parse
import codecs
import time

def write_txt(title, content):
f = codecs.open('D:\\wushangshenwang.txt', 'a+')
f.write(title)
f.write('\n') # 换行
f.write('\n') # 换行
content = content.replace('\xa0','')
f.write(content)
f.write('\n') # 换行
f.write('\n') # 换行
f.close()

def proc_single_html(prefix,url):
response = requests.get(prefix+url)
print(prefix + url)
response.encoding = 'gbk'
bs_response = BeautifulSoup(response.text,'html.parser')
title = bs_response.find(class_='book reader').find('h1').text
content = bs_response.find(class_="showtxt").text
write_txt(title, content)
next_chapter = bs_response.find(class_='page_chapter')
uls = next_chapter.ul
lis = uls.findAll('li')

for li in lis:
if li.text == '下一章':
a = li.find('a')
if a != None:
proc_single_html(prefix, a['href'])

time.sleep(5)


proc_single_html('https://www.xxxx.lu','/book/61/11749.html')

 

举报

相关推荐

0 条评论