import requests,re,csv

from bs4 import BeautifulSoup

url = "https://movie.douban.com/top250"

headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}

reponse = requests.get(url,headers = headers)

html = reponse.text

obj = re.compile(r'<li>.*?<div class="item">.*?<div class="pic">.*?<em class="">(?P<number>.*?)</em>'

r'.*?<span class="title">(?P<name>.*?)</span>'

r'.*?<div class="bd".*?<p class="">.*?<br>.*?(?P<year>.*?)&nbsp'

r'.*?<div class="star">.*?<span class="rating_num" property="v:average">(?P<grade>.*?)</span>'

r'.*?<span>(?P<comments>.*?)人评价</span>'

,re.S)

res = obj.finditer(html)

f= open('data.csv','w',encoding='utf-8')

csv = csv.writer(f)

for i in res:

# print(i.group('number'.strip()))

# print(i.group('name').strip())

# print(i.group('year').strip()+"年")

# print("评分\00"+ i.group('grade').strip())

# print("评论数\00"+ i.group('comments').strip())

dict = i.groupdict()

dict['year'] = dict['year'].strip() +"年"

dict['grade'] ="评分:"+ dict['grade']

dict['comments'] = "评论数:"+dict['comments']

csv.writerow(dict.values())

print(dict)

f.close()

print('over')