import requests
from bs4 import BeautifulSoup
def get_book():
re=requests.get(url,headers=headers)
soup=BeautifulSoup(re.text,'html.parser')
for i in range(1,21):
title=soup.select(f'#book-img-text > ul > li:nth-child({i}) > div.book-mid-info > h2 > a')[0].text
introduction=soup.select(f'#book-img-text > ul > li:nth-child({i}) > div.book-mid-info > p.intro')[0].text
author=soup.select(f'#book-img-text > ul > li:nth-child({i}) > div.book-mid-info > p.author > a.name')[0].text
category=soup.select(f'#book-img-text > ul > li:nth-child({i}) > div.book-mid-info > p.author > a.go-sub-type')[0].text
print(f'{i+num}. {title}\t作者:{author}\t{category}\n{introduction}')
print('----------------------------------')
if __name__ == '__main__':
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36"
}
for j in range(1,11):
url = f'https://www.qidian.com/rank/recom/datetype3/page{j}/'
num=(j-1)*20
get_book()
先爬取源码,再用beautifulsoup解析,读者也可以用lxml里的etree来解析,不过在新版本中,etree模块被整合到html里面去了,所以要这么导入:
from lxml import html
etree=html.etree
下方的html里面的etree也许会高亮,但是是没有关系的。