1. 程式人生 > >crawler碎碎念6 豆瓣爬取操作之獲取資料

crawler碎碎念6 豆瓣爬取操作之獲取資料

import requests

from lxml import etree

 

s = requests.Session()

for id in range(0,251,25):

  url ='https://movie.douban.com/top250/?start-'+str(id)

  r = s.get(url)

  r.encoding = 'utf-8'

  root = etree.HTML(r.content)

  items = root.xpath('                          ')

  #print(len(items))

  for item in items:

    title = item.xpath('                      ')                 #/text加在最後就是找它的文字內容

    print(title)