豆瓣电影TOP250数据

from lxml import etree
import time, random
import requests

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                         "Chrome/56.0.2924.87 Safari/537.36"}

# proxies = {
#     'http://217.23.73.172',
#     'http://222.186.45.14',
#     '222.186.45.145'
# }


def crow():
    try:       # 简单的容错处理
        for i in range(11):
            url = 'https://movie.douban.com/top250?start='+str(25*i)
            html = requests.get(url, headers=headers).text

            html = etree.HTML(html)
            datas = html.xpath('//ol[@class="grid_view"]/li')
            a = 0
            for data in datas:
                title = data.xpath('//div/div[2]/div[@class="hd"]/a/span[@class="title"]/text()')
                infor = data.xpath('//div/div[2]/div[@class="bd"]/p/text()')
                numbers = data.xpath('//div/div[2]/div[@class="bd"]/div/span[4]/text()')
                quote = data.xpath('//div/div[2]/div[@class="bd"]/p/span[@class="inq"]/text()')
                rating_num = data.xpath('//div/div[2]/div[@class="bd"]/div/span[@class="rating_num"]/text()')
            for item in range(25):
                print(a)
                a += 1
                print("\n~~~正在打印第%d条数据~~~\n" % (25*i+item))
                time.sleep(random.random()*3)
                print(title[item])
                print('\n')
                print(infor[item])
                print(rating_num[item])
                print(quote[item])
                print(numbers[item])

    except():
        print('Error~')


if __name__ == '__main__':
    crow()