|
|

楼主 |
发表于 2019-9-6 16:02:44
|
显示全部楼层
import requests
import bs4
import re
def open_url(url):
headers = {'user-agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'}
res = requests.get(url,headers=headers)
return res
def find_books(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
#书名
books = []
targets = soup.find_all('div', class_='p12')
for each in targets:
books.append(each.a.span.text)
#评分
ranks = []
targets = soup.find_all('span', class_='rating num')
for each in targets:
ranks.append('评分:%s' % each.text)
#评价
messages = []
targets = soup.find_all('span', class_='inq')
for each in targets:
try:
messages.append(each.p.text.split('\n')[1].strip() + \
each.parent.text.split('\n')[2].strip())
except:
continue
result = []
length = len(books)
for i in range(length):
result.append(books[i] + ranks[i] + messages[i] + '\n')
return result
#找出一共有多少个页面
def find_depth(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
return int(depth)
def main():
host = 'https://book.douban.com/top250'
res = open_url(host)
depth = find_depth(res)
result = []
for i in range(depth):
url = host + '/start=' + str(25*i)
res = open_url(url)
result.extend(find_movies(res))
with open('豆瓣TOP250电影.txt','w', encoding ='utf-8') as f:
for each in result:
f.write(each)
if __name__ == '__main__':
main()
|
|