import requests,re,jsonfrom lxml import etreefrom openpyxl import Workbookwb = Workbook()ws = wb.activews.append(['电影名称'])headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'}base_url = '/chart'movies_count_url= '/j/chart/top_list_count?type={}&interval_id=100%3A90'movies_url = '/j/chart/top_list?type={}&interval_id=100%3A90&action=&start=0&limit={}'response = requests.get(url=base_url,headers=headers)html = etree.HTML(response.text)span_list = html.xpath('//div[@class="types"]/span')for span in span_list:big_title = span.xpath('./a/text()')[0]types_id = span.xpath('./a/@href')[0]type_id = re.findall('.*?type=(\d+).*?',types_id)[0]# print(big_title,type_id)resp = requests.get(url=movies_count_url.format(type_id),headers=headers)dict_data = json.loads(resp.text)movies_count = dict_data['total']# print(movies_count)res = requests.get(url=movies_url.format(type_id,movies_count),headers=headers)movies_list = json.loads(res.text)print(big_title)for movies in movies_list:lis = []movies_name = movies['title']lis.append(movies_name)ws.append(lis)wb.save('./data/豆瓣电影大全.xlsx')
