Requests+Xpath(爬取豆瓣書評)
import requests
from lxml import etree
for i in range(1,9):
r=requests.get('https://book.douban.com/subject/26829016/comments/hot?p=%d'%i).text
comments=etree.HTML(r)
coms=comments.xpath('//*[@id="comments"]/ul/li/div[2]/p/text()')
for com in coms:
print(com)