第七周——数据分析、可视化 Day1 8.8

学习时间：9:00——11:00   14:30——16:30

今天先做了一个项目（爬取豆瓣电影top250信息，并保存数据到Excel）为下面的学习提供数据。以下是源代码：

#用的是xpath解析数据，个人认为xpath比bs4和re简便

import requests
import xlwt
from lxml import etree

baseurl = 'https://movie.douban.com/top250'
header = {
    'xxx'
}
data_list = []

for i in range(10):
    url = baseurl + '?start='+ str(i * 25) + '&filter='
    page_text = requests.get(url=url,headers=header).text
    tree = etree.HTML(page_text)
    movie_list = tree.xpath('//ol[@class="grid_view"]/li')

    for movie in movie_list:
        title = movie.xpath('./div/div[2]/div[1]/a/span[1]/text()')[0]

        author = movie.xpath('./div/div[2]/div[2]/p[1]/text()')[0].strip()

        score = movie.xpath('./div/div[2]/div[2]/div/span[2]/text()')[0]

        index = movie.xpath('./div/div[1]/em/text()')[0]

        inq = movie.xpath('./div/div[2]/div[2]/p[2]/span/text()')
        if inq:
            inq = inq[0]
        else:
            inq = ' '
        data_list.append([index,title,score,inq,author])

book = xlwt.Workbook(encoding='utf-8')
sheet = book.add_sheet('豆瓣top250')
col = ('排名', '电影名', '评分', '简介', '导演主演')
for i in range(0, 5):
    sheet.write(0, i, col[i])

for i in range(0, 250):
    data = data_list[i]
    for j in range(0, 5):
        sheet.write(i+1, j, data[j])

book.save('豆瓣top250.xls')