#请求页已经能够得到数据,但是自己整理下感觉会更好些
import requests, json
def main(page):
url = 'https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action=&start=' + str(page) + '&limit=20'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
html = requests.get(url, headers=headers)
print(html.status_code)
html = html.json() #html.json()的返回值类型是dict, 而html.text的返回值类型是str不便于索引
print(type(html))
for items in html:
item = {
'title': items['title'],
'rank': items['rank'],
'score': items['rating'],
'actors': items['actors']
}
print(item)
print('\n')
if __name__ == '__main__':
for i in range(10):
main(i*10)