猫眼top100爬取（视频练习)

首先感谢崔庆才大神的课程，本文代码基本都是取之于他所授视频

import json
from multiprocessing import Pool
import requests
from requests.exceptions import RequestException
import re
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.*?>(.*?).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                        +'.*?integer">(.*?).*?fraction">(.*?).*?
',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 main():
    for offset in range(0,100,10):
        url = 'https://maoyan.com/board/4?offset='+str(offset)
        html = get_one_page(url)
        for item in parse_one_page(html):
            print(item)

if __name__ == '__main__':
    main()

运行截图：

image.png