爬虫练习

有个网站特别宝藏，整理收集了很多木原音濑的作品。因为原网站的字体太小了，手机看实在费眼，所以写了个爬虫导成了txt文件。

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36

import  requests import threading from bs4 import BeautifulSoup import re import os import time import pdfkit   r=requests.get("") //原网站主页 soup=BeautifulSoup(r.text,"html.parser") contents = soup.find_all("p")   //转成txt格式 i = 0 err = [] for c in contents:     if c.a:         i += 1         series = c.strong.text         series = series.replace('/', ' ')         books = c.find_all("a")         j = 0         for b in books:             if b.attrs['href'].split('.')[-1] == "jpg":                 continue             else:                 j += 1                 filename = str(i)+"-"+series+'-'+str(j)+"-"+b.text+'.txt'                 res = requests.get(b.attrs['href'])                 res.encoding = 'gb18030' //这里乱码搞了好久                 soup = BeautifulSoup(res.text,'html.parser',from_encoding='gb18030')                 for body in soup.find_all('body'):                     s = body.get_text()                     print(s)                     with open(filename,'w',1,'utf-8') as f:                         f.write(s)