@H_301_2@import json
@H_301_2@import requests
@H_301_2@from requests.exceptions @H_301_2@import RequestException
@H_301_2@import re
@H_301_2@import time

@H_301_2@def get_one_page(url):
    @H_301_2@try:
        response = requests.get(url)
        @H_301_2@if response.status_code == 200:
            @H_301_2@return response.text
        @H_301_2@return @H_301_2@None
    @H_301_2@except RequestException:
        @H_301_2@return @H_301_2@None

@H_301_2@def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    @H_301_2@for item @H_301_2@in items:
        @H_301_2@yield {
            'index': item[0],'image': item[1],'title': item[2],'actor': item[3].strip()[3:],'time': item[4].strip()[5:],'score': item[5] + item[6]
        }

@H_301_2@def write_to_file(content):
    @H_301_2@with open('result.txt','a',encoding='utf-8') @H_301_2@as f:
        f.write(json.dumps(content,ensure_ascii=@H_301_2@False) + '\n')

@H_301_2@def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    @H_301_2@for item @H_301_2@in parse_one_page(html):
        print(item)
        write_to_file(item)

@H_301_2@if __name__ == '__main__':
    @H_301_2@for i @H_301_2@in range(10):
        main(offset=i * 10)
        time.sleep(1)

转自:http://cuiqingcai.com/