爬取猫眼电影

ideologism

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

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

def parse_page(html):
    res = re.findall('<dd>.*?"board-index.*?board-index.*?">(\d*)</i>.*?title="(.*?)".*?data-src="(.*?)".*?<p.*?"star">(.*?)</p>.*?"releasetime">(.*?)</p>.*?</dd>',html,re.S)
    # print(res)
    for result in res:
        yield {
            'index': result[0],
            'title':result[1],
            'url':result[2],
            'name':result[3].strip()[3:],
            'time':result[4].strip()[5:]
        }

def with_open(result):
    with open('爬猫影电影网top100.txt','a',encoding='utf8') as f:
        f.write(json.dumps(result,ensure_ascii=False)+'\n')
        f.close()

def main(i):
    url = 'https://maoyan.com/board/4?offset=' + str(i)
    html = get_url(url)
    # print(html)
    for result in parse_page(html):
        with_open(result)

if __name__ == '__main__':

    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])

犹豫的流星

可以可以        

ideologism

希望大佬们多提出些宝贵的建议

ideologism

这个是爬取猫眼电影top100的电影，做的不是太好