爬虫求助
import requestsfrom bs4 import BeautifulSoup
if __name__ == '__main__':
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
}
url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
page_text=requests.get(url=url,headers=headers).text.encode('iso-8859-1')
page_soup=BeautifulSoup(page_text,'lxml')
page_tage=page_soup.select('.book-mulu>ul>li')
for li in page_tage:
path=r'https://m.shicimingju.com/'+li.a['href']
title=li.string
detail_text=requests.get(url=path,headers=headers).text.encode('iso-8859-1')
detail_soup=BeautifulSoup(detail_text,'lxml')
content=detail_soup.find('div',class_='chapter_content')
content=content.text
print(title)
print(content)
为什么要用encode('iso-8859-1')才能不显示乱码啊？还有这个'iso-8859-1'是怎么知道该用他不用utf-8
https://www.cnblogs.com/huangchenggener/p/10983866.html
页:
[1]