requests 抓取网站

 import requests
 from requests.exceptions import RequestException
 import re
 import json

 def get_one_page(url):
     try:
         headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/'
                 + '535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1'
         }
         response = requests.get(url, headers=headers)
         response.encoding = 'gb2312'
         if response.status_code == 200:
             return response.text
         return None
     except RequestException:
         return None

 def parse_one_page(html):
     pattern = re.compile(
         '<li>.*?target.*?src="(.*?)".*?<h2>.*?title.*?>(.*?)</a>'
         + '</h2>.*?</span><span>(.*?)</span>.*?>(.*?)</p>.*?</li>', re.S)
     items = re.findall(pattern, html)
     #print(items)
     for item in items:
         yield {
             'image': item[0],
             'title': item[1],
             'type': item[2],
             'introduction': item[3]
         }

 def write_to_file(content):
     with open('Yinghua.json', 'a', encoding='utf-8') as f:
         f.write(json.dumps(content, ensure_ascii=False) + '\n')

 def main(page):
     num = (page - 1) * 12 + 1
     url = '×××page=' + str(page) + '×××'
     html = get_one_page(url)
     #print(html)
     for item in parse_one_page(html):
         print(num)
         print(str(item) + '\n')
         item = str(num) + str(item)
         write_to_file(item)
         num += 1

 if __name__ == '__main__':
     for i in range(1, 398):
         main(page=i)