Python 抓取豆瓣电影放入表格中__一蓑烟雨任平生

关注

原创最新推荐文章于 2026-01-19 21:47:55 发布 460 阅读 AI 写同款· GEO 优化 ›

对豆瓣电影Top250榜单的一些探索性分析业余打发时间看电影是个不错的选择，但是如果看了一部无聊糟心的电影就得不偿失了，所以一些电影方面的榜单就出现了，可以为这些选择困难患者提供一个不错的指南，那些是经典是值得看的，而那些电影不值得你浪费一两个小时的时间。在电影榜单方面，国外最出名的自然是IMDB Top250，这个榜单收集了全球观众评选出的最好看的250部电影，国内最知名的榜单应该是豆瓣电影Top250，主要反映了国内观众的观影品味(... 阅读详情

# -*- coding: utf-8 -*-
"""
@Time ： 2021/1/19 14:14
@Auth ： 张张呀
@File ：laoshi.py
@IDE ：PyCharm
@Motto：ABC(Always Be Coding)
"""
import xlwt
import requests


# 储存到excel表格中
def saveDate(sheet, all_list, book, savepath, page):
    col = ("ID", "标题", "封面图片地址", "电影类型", "电影国别", "电影地址", "电影评分", "上映时间")
    for i2 in range(0, 8):
        sheet.write(0, i2, col[i2])  # 列名
    for i3 in range(0, page):
        b = (all_list[0])[i3]
        c = (all_list[1])[i3]
        d = (all_list[2])[i3]
        e = (all_list[3])[i3]
        f = (all_list[4])[i3]
        g = (all_list[5])[i3]
        h = (all_list[6])[i3]
        j = (all_list[7])[i3]

        print("第%d条输入完成" % (i3 + 1))
        sheet.write((i3 + 1), 0, b)
        sheet.write((i3 + 1), 1, c)
        sheet.write((i3 + 1), 2, d)
        sheet.write((i3 + 1), 3, e)
        sheet.write((i3 + 1), 4, f)
        sheet.write((i3 + 1), 5, g)
        sheet.write((i3 + 1), 6, h)
        sheet.write((i3 + 1), 7, j)

    book.save(savepath)


if __name__ == '__main__':
    savepath = "豆瓣电影.xls"  # 定义保存路径
    book = xlwt.Workbook(encoding="utf-8", style_compression=0)  # 创建workbook对象
    sheet = book.add_sheet('豆瓣电影', cell_overwrite_ok=True)  # 创建工作表
    # url = 'https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action='

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}

    movie_id = []
    movie_name = []
    movie_pic_url = []
    movie_types = []
    movie_regions = []
    movie_url = []
    movie_score = []
    movie_release_date = []
    n = 0
    for pp in range(10):
        url = f'https://movie.douban.com/j/chart/top_list?type=17&interval_id=100%3A90&action=&start={pp}&limit=300'
        response = requests.get(url, headers=headers).json()

        for movie in response:
            movie_id.append(movie['id'])
            movie_name.append(movie['title'])
            movie_pic_url.append(movie['cover_url'])
            movie_types.append(movie['types'])
            movie_regions.append(movie['regions'])
            movie_url.append(movie['url'])
            movie_score.append(movie['score'])
            movie_release_date.append(movie['release_date'])
            n += 1
    all_list = [movie_id, movie_name, movie_pic_url, movie_types, movie_regions,
                movie_url, movie_score, movie_release_date]
    print(n)
    saveDate(sheet, all_list, book, savepath, n)