requests 抓取网站

 1 import requests
 2 from requests.exceptions import RequestException
 3 import re
 4 import json
 5 
 6 def get_one_page(url):
 7     try:
 8         headers = {
 9             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/'
10                 + '535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1'
11         }
12         response = requests.get(url, headers=headers)
13         response.encoding = 'gb2312'
14         if response.status_code == 200:
15             return response.text
16         return None
17     except RequestException:
18         return None
19 
20 def parse_one_page(html):
21     pattern = re.compile(
22         '
.*?target.*?src="(.*?)".*?
.*?title.*?>(.*?)'
23         + '
.*?(.*?).*?>(.*?)
.*?', re.S)
24     items = re.findall(pattern, html)
25     #print(items)
26     for item in items:
27         yield {
28             'image': item[0],
29             'title': item[1],
30             'type': item[2],
31             'introduction': item[3]
32         }
33 
34 def write_to_file(content):
35     with open('Yinghua.json', 'a', encoding='utf-8') as f:
36         f.write(json.dumps(content, ensure_ascii=False) + '\n')
37 
38 def main(page):
39     num = (page - 1) * 12 + 1
40     url = '×××page=' + str(page) + '×××'
41     html = get_one_page(url)    
42     #print(html)
43     for item in parse_one_page(html):
44         print(num)
45         print(str(item) + '\n')
46         item = str(num) + str(item)
47         write_to_file(item)
48         num += 1
49 
50 if __name__ == '__main__':
51     for i in range(1, 398):
52         main(page=i)