import requests
from bs4 import BeautifulSoup
headers={
'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'
}
url='http://www.doupoxs.com/doupocangqiong/'
res=requests.get(url,headers=headers)
res.encoding='utf-8'#乱码
soup=BeautifulSoup(res.text,'html.parser')
linkk=soup.select('a')
link1=list(map(lambda x:x['href'],linkk))#提取网址
for link in link1:
link2='http://www.doupoxs.com'+link
res1=requests.get(link2,headers=headers)
res1.encoding='utf-8'#乱码
soup1=BeautifulSoup(res1.text,'html.parser')
article_p=soup1.select('.read_chapterDetail p')
ar=list(map(lambda x:x.text.lstrip('天才一秒记住本站网站 www.doupoxs.com 中间是斗破 拼音+小说 首字母 连起来就是斗破小说,喜欢我就记住我吧!').strip(),article_p))
arr='\n'.join(ar)#正文,字符串
print(arr)
with open('doupocangqiong1.txt','a+') as f:
f.write(arr)
f.close()#存储
爬取斗破苍穹整本小说
最新推荐文章于 2023-11-03 14:41:03 发布