豆瓣电影Top250——电影详细

 闲得无聊去爬了一下豆瓣的Top250电影信息

代码如下，直接可以运行，

import requests
from lxml import etree
from bs4 import BeautifulSoup
s = requests.Session()
for id in range(0, 251, 25): 
    url = 'https://movie.douban.com/top250/?start=' + str(id)+ '&filter='
    r = s.get(url)
    r.encoding = 'utf-8'
    # print(r.content)
    root = etree.HTML(r.content)       #解析为HTML文档
    items = root.xpath('//ol/li/div[@class="item"]')      #主要信息的xpath路径

    for item in items:
        title = item.xpath('./div[@class="info"]//a/span[@class="title"]/text()')

        name = title[0].encode('gb2312', 'ignore').decode('gb2312')
        try:            #为了解决中文名，不合编码continue跳过
            english = title[1]
        except:
            continue
        other = item.xpath('./div[@class="info"]//a/span[@class="other"]/text()')
        author = other[0].encode('gb2312', 'ignore').decode('gb2312')
        # rank = item.xpath('./div[@class="pic"]/em/text()')[0]
        rating = item.xpath('.//div[@class="bd"]//span[@class="rating_num"]/text()')[0]
        direct = item.xpath('./div[@class="info"]/div[2]/p/text()')[0]
        direcs = str(direct)
        dire = direcs.lstrip()
        print(name,english,author,rating)
        print(dire)
        print('\n')