FilesExpand file tree

 master

/

douban_movie.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

82 lines (71 loc) · 2.42 KB

 master

/

douban_movie.py

Copy path

Top

File metadata and controls

• Code
• Blame

82 lines (71 loc) · 2.42 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

#!/usr/bin/env python

# encoding=utf-8

import requests

import re

import codecs

from bs4 import BeautifulSoup

from openpyxl import Workbook

wb = Workbook()

dest_filename = '电影.xlsx'

ws1 = wb.active

ws1.title = "电影top250"

DOWNLOAD_URL = 'http://movie.douban.com/top250/'

def download_page(url):

"""获取url地址页面内容"""

headers = {

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'

}

data = requests.get(url, headers=headers).content

return data

def get_li(doc):

soup = BeautifulSoup(doc, 'html.parser')

ol = soup.find('ol', class_='grid_view')

name = [] # 名字

star_con = [] # 评价人数

score = [] # 评分

info_list = [] # 短评

for i in ol.find_all('li'):

detail = i.find('div', attrs={'class': 'hd'})

movie_name = detail.find(

'span', attrs={'class': 'title'}).get_text() # 电影名字

level_star = i.find(

'span', attrs={'class': 'rating_num'}).get_text() # 评分

star = i.find('div', attrs={'class': 'star'})

star_num = star.find(text=re.compile('评价')) # 评价

info = i.find('span', attrs={'class': 'inq'}) # 短评

if info: # 判断是否有短评

info_list.append(info.get_text())

else:

info_list.append('无')

score.append(level_star)

name.append(movie_name)

star_con.append(star_num)

page = soup.find('span', attrs={'class': 'next'}).find('a') # 获取下一页

if page:

return name, star_con, score, info_list, DOWNLOAD_URL + page['href']

return name, star_con, score, info_list, None

def main():

url = DOWNLOAD_URL

name = []

star_con = []

score = []

info = []

while url:

doc = download_page(url)

movie, star, level_num, info_list, url = get_li(doc)

name = name + movie

star_con = star_con + star

score = score + level_num

info = info + info_list

for (i, m, o, p) in zip(name, star_con, score, info):

col_A = 'A%s' % (name.index(i) + 1)

col_B = 'B%s' % (name.index(i) + 1)

col_C = 'C%s' % (name.index(i) + 1)

col_D = 'D%s' % (name.index(i) + 1)

ws1[col_A] = i

ws1[col_B] = m

ws1[col_C] = o

ws1[col_D] = p

wb.save(filename=dest_filename)

if __name__ == '__main__':

main()