|
|
发表于 2019-7-13 06:46:59
|
显示全部楼层
- import bs4
- import requests
- import re
- def open_url(url):
- headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'}
-
- res = requests.get(url, headers = headers)
- return res
- def find_food(res):
-
- soup = bs4.BeautifulSoup(res.text,'html.parser')
- #店
- dian = []
- targets = soup.find_all('div',class_ = 'tit')
- for each in targets:
- dian.append(each.a.h4.text)
- #分数
- ranks = []
- targets = soup.find_all('span',class_ = 'comment-list')
- for each in targets:
- ranks.append('评分:%s'%each.span.b.text)
- #推荐菜
- dish = []
- targets = soup.find_all('div',class_ = 'recommend')
- for each in targets:
- dish.append(each.a.recommend-click.text)
- result = []
- length = len(dian)
- for i in range(length):
- result.append(dian[i] + ranks[i] + dish[i] + '\n')
- return result
- with open ('大众点评餐厅.txt', 'w', encoding = 'utf-8')as f:
- for each in result:
- f.write(each)
- def main():
- host = 'http://www.dianping.com/search/keyword/10/10_%E8%81%9A%E9%A4%90/o2'
- res = open_url(host)
- find_food(res)
- if __name__ == '__main__':
- main()
复制代码 |
|