描述:
在上一篇获取豆瓣图书Top250的基础上,获取豆瓣电影Top250的数据并将结果写入CSV文件中。
代码:
# -*- coding: UTF-8 -*-
import requests
from lxml import etree
import time
import csv
# 从网页上获取电影数据
moviedata = []
count = 0
for i in range(10):
url = 'https://movie.douban.com/top250?start=' + str(25*i)
data = requests.get(url).text
html = etree.HTML(data)
movies = html.xpath('//*[@id="content"]/div/div[1]/ol/li')
for movie in movies:
title = movie.xpath('./div/div[2]/div[1]/a/span[1]/text()')[0]
director_actor = movie.xpath('./div/div[2]/div[2]/p[1]/text()')[0].strip('\n').strip('\xa0')
type_region_year = movie.xpath('./div/div[2]/div[2]/p[1]/text()')[1].strip('\n').strip('\xa0')
score =