Delete 'movie_charts.py'

movie_charts.py

@@ -1,116 +0,0 @@
-# -*- coding: utf-8 -*-
-import requests
-from lxml import etree
-import xlwt
-import pandas as pd
-
-def main():
-    a = 1
-    j = 1
-    infos_list = []
-    for i in range(0, 14):
-        page = str(i * 25)
-        url = r'https://www.douban.com/doulist/119166792/?start={}&sort=seq&playable=0&sub_type='.format(page)
-        headers = {
-            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36',
-        }
-        response = requests.get(url,headers = headers)
-        content = response.content.decode('utf8')
-        html = etree.HTML(content)
-
-        # 获取电影名
-        movies = html.xpath('//div[@class="doulist-item"]/div/div[2]/div[4]/a/text()')
-        movie_name_list = []
-        for movie in movies:
-            movie_name_list.append(movie.strip())
-        movie_name_list = list(filter(None, movie_name_list))
-
-        # 获取电影票房
-        Box_office = html.xpath('//div[@class="doulist-item"]/div/div[3]/div/blockquote/text()')
-        Box_office_list = []
-        for Boxs in Box_office:
-            Box_office_list.append(Boxs.strip())
-        Box_office_list = list(filter(None, Box_office_list))
-        # print(Box_office_list)
-
-        # 获取评分
-        score_list = html.xpath('//div[@class="doulist-item"]/div/div[2]/div[5]/span[2]/text()')
-        # print(score)
-
-        # 获取导演以及主演
-        infos = html.xpath('//div[@class="doulist-item"]/div/div[2]/div[6]/text()')
-        director_list = []
-        actor_list = []
-        type_list = []
-        area_list = []
-        year_list = []
-        for info in infos:
-            if info.strip().startswith('导演:'):
-                directors = parse_title(info, '导演:')
-                director_list.append(directors)
-            elif info.strip().startswith('主演:'):
-                actors = parse_title(info, '主演:')
-                actor_list.append(actors)
-            elif info.strip().startswith('类型:'):
-                types = parse_title(info, '类型:')
-                type_list.append(types)
-            elif info.strip().startswith('制片国家/地区:'):
-                areas = parse_title(info, '制片国家/地区:')
-                area_list.append(areas)
-            elif info.strip().startswith('年份:'):
-                years = parse_title(info, '年份:')
-                year_list.append(years)
-
-        for movie_name, Box, score, director, actor, type, area, year in zip(movie_name_list, Box_office_list,
-                                                                             score_list, director_list, actor_list,
-                                                                             type_list, area_list, year_list):
-            dic = {
-                '排名':j,
-                '电影名称': movie_name,
-                '票房': Box,
-                '评分': score,
-                '导演': director,
-                '主演': actor,
-                '类型': type,
-                '地区': area,
-                '上映年份': year,
-            }
-            print(dic)
-            infos_list.append(dic)
-            j += 1
-        print(f'已下载完第{a}页数据！！！！！')
-        a += 1
-
-    save_excel(infos_list)
-
-
-
-def parse_title(title,rule):
-
-    return title.replace(rule,'').strip()
-
-def save_excel(infos_list):
-
-    gushi = infos_list
-    workbook = xlwt.Workbook(encoding='utf8')
-    sheet = workbook.add_sheet('古诗文')
-    keys = list(gushi[0].keys())
-
-    for i, key in zip(range(len(keys)), keys):
-        sheet.write(0, i, key)
-
-    for row in range(1, len(gushi) + 1):
-        for col, key in zip(range(len(keys)), keys):
-            sheet.write(row, col, gushi[row - 1][key])
-
-    workbook.save(r"./电影票房排行榜.xls")
-
-
-def xls_to_csv_pd():
-    data_xls = pd.read_excel('电影票房排行榜.xls',index_col=0)
-    data_xls.to_csv('data.csv',encoding='utf8')
-
-if __name__ == '__main__':
-    main()
-    xls_to_csv_pd()
-