猫眼top100

# coding=utf-8
import json
import re

import requests

def get_one_page(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3409.2 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None

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

def write_to_file(content):
    with open('top100.txt', 'a', encoding='utf-8') as f:
        # print(type(json.dumps(content)))
        f.write(json.dumps(content, ensure_ascii=False) + '\n')

def main(offset):
    url = "https://maoyan.com/board/4?offset=" + str(offset)
    # get_one_page(url)
    html = get_one_page(url)
    # parse_one_page(html)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)