import requests,bs4,csv
#引入requests,bs4,csv库
csv_file = open('douban.csv','w',newline='')
#创建csv文件，并命名
write = csv.writer(csv_file)
#csv.writer函数创建writer对象
write.writerow(['序号','电影名称','豆瓣评分','推荐语','网址'])
#先创建表头
headers={'user-agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
for x in range(10):
url = 'https://movie.douban.com/top250?start=' + str(x*25) + '&filter='
res = requests.get(url, headers=headers)
bs = bs4.BeautifulSoup(res.text, 'html.parser')
bs = bs.find('ol', class_="grid_view")
for titles in bs.find_all('li'):
num = titles.find('em',class_="").text
title = titles.find('span', class_="title").text
comment = titles.find('span',class_="rating_num").text
url_movie = titles.find('a')['href']
if titles.find('span',class_="inq") != None:
tes = titles.find('span',class_="inq").text
else:
tes = '无'
write.writerow([num,title,comment,tes,url_movie])
#为write对象写入信息
csv_file.close()
#保存关闭文件
import requests,bs4,openpyxl
#引入requests,bs4,csv库
wb = openpyxl.Workbook()
sheet = wb.active
sheet.title = '豆瓣123'
sheet['A1'] = '序号'
sheet['B1'] = '电影名称'
sheet['C1'] = '评份'
sheet['D1'] = '推荐语'
sheet['A1'] = '网址'
headers={'user-agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
for x in range(10):
url = 'https://movie.douban.com/top250?start=' + str(x*25) + '&filter='
res = requests.get(url, headers=headers)
bs = bs4.BeautifulSoup(res.text, 'html.parser')
bs = bs.find('ol', class_="grid_view")
for titles in bs.find_all('li'):
num = titles.find('em',class_="").text
title = titles.find('span', class_="title").text
comment = titles.find('span',class_="rating_num").text
url_movie = titles.find('a')['href']
if titles.find('span',class_="inq") != None:
tes = titles.find('span',class_="inq").text
else:
tes = '无'
sheet.append([num,title,comment,tes,url_movie])
wb.save('douban123.xlsx')
