猫眼排名--（一页有10部电影）

https://maoyan.com/board/4

import json

import requests
from requests.exceptions import RequestException
import  re
import  time


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

def parse_one_page(html):
    pattern=re.compile('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                         + '.*?integer">(.*?).*?fraction">(.*?).*?
',re.S)
    items=re.findall(pattern,html)

    for item in items:
        print(items)
        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]
        }

def write_to_file(content):
    with open('MaoyanResult.txt','a',encoding='utf-8') as f:

        f.write(json.dumps(content,ensure_ascii=False)+'\n')


def main(offset):
    url="http://maoyan.com/board/4?offset="+str(offset)
    html=get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
if __name__=="__main__":
    for i in range(10):
        main(i*10)
        print(i)
        time.sleep(1)