抓取猫眼电影排行榜前100

抓取电影前一百并写入txt中

#encoding = utf-8
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool

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(r'<dd>.*?board-index.*?">(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         r'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?'
                         r'integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    items = re.findall(pattern, html)
    for item in 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_flie(content):
    with open('res.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')
        f.close()

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


if __name__ == '__main__':
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])