菜鸟教程python爬虫小说_【python】新手写的一个小说爬虫【天籁小说】

[Python] 纯文本查看 复制代码import requests

from bs4 import BeautifulSoup

import lxml

import re

#爬取天籁小说网小说

#url = 'https://www.23txt.com/files/article/html/60/60792/'

url = input('网址URL：\n本脚本仅支持天籁小说 \n类型：https://www.23txt.com/files/article/html/**/*****/ \n')

url_fix = input('类型：**/******/ \n')

req = requests.get (url)

req.encoding = 'GBK'

text = req.text

bf = BeautifulSoup (text,'lxml')

title = bf.find_all('div',id = 'info')

title = bf.find_all('h1')

title = title[0].text.replace ('h1',' ')

text_info = re.findall(r'

.*?

',text,re.S)[0]

text_info_list = re.findall (r'

(.*?)'% url_fix ,text_info)

for book in text_info_list:

text_url = book[0]

text_name = book[1]

text_download = url + text_url

reqs = requests.get(text_download)

reqs.encoding = 'GBK'

texts = reqs.text

texts_info = re.findall(r'

(.*?)

',texts,re.S)[0]

texts_info = texts_info.replace (' ',' ')

texts_info = texts_info.replace (';',' \n')

texts_info = texts_info.replace ('
',' ')

with open ('%s.txt'% title,'a+',encoding = 'GBK')as f:

f.write ('\n\n')

f.write (text_name)

f.write (texts_info)

f.write ('\n')

print (text_name)

print ('下载完成')