python 我爱爬虫 爬虫爱我

使用的 pyquery  这个库  看个人喜好也可以使用BeautifulSoup  只不过爬虫方法不一样

from pyquery import PyQuery as pq
import urllib.request
import urllib.parse

# from bs4 import BeautifulSoup

url = 'https://www.douban.com/tag/%E5%B0%8F%E8%AF%B4/book?start=0'

response = urllib.request.urlopen(url)
html = response.read()

doc = pq(html)
booklist=doc.find('.mod.book-list')
books=booklist('dd')
for info in books.items():
    print(info.find('.title').text())
    print(info.find('.desc').text())
    print('---')
#
#

爬的漂亮的呢