requests爬取中国天气网深圳七日天气

 1 # conding=utf-8
 2 import json
 3 import re
 4 import requests
 5 
 6 def get_data(url):
 7     response = requests.get(url)
 8     response.encoding = ‘utf-8‘
 9     if response.status_code == 200:
10 
11         return response.text
12     return None
13 
14 def parse_data(html):
15     pattern = re.compile(‘<li.*?skyid.*?h1>(.*?)</h1>.*?wea">(.*?)</p>.*?pan>(\d+)</span>.*?i>(.*?)</i>.*?i>(.*?)</i>.*?</li>‘, re.S)
16     items = re.findall(pattern, html)
17     for item in items:
18         yield{
19             ‘data‘:item[0],
20             ‘weather‘:item[1],
21             ‘T‘:item[2]+‘/‘+item[3],
22             ‘wind‘:item[4]
23         }
24 
25 def write_to_file(content):
26     with open(‘result.txt‘, ‘a‘, encoding=‘utf-8‘) as f:
27         f.write(json.dumps(content, ensure_ascii=False) + ‘\n‘)
28         f.close()
29 
30 def main():
31     url = ‘http://www.weather.com.cn/weather/101280601.shtml‘
32     html = get_data(url)
33     for item in parse_data(html):
34         print(item)
35         write_to_file(item)
36 
37 if __name__ == ‘__main__‘:
38     main()