Python爬取猫眼top100排行榜数据含多线程

Posted 2020-10-02

# -*- coding: utf-8 -*-
import requests
from multiprocessing import Pool
from requests.exceptions import RequestException
import re
import json


def get_one_page(url):
    """
    爬取每个页面
    :param url: 爬取url地址
    :return: 返回网页内容
    """
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def parse_one_page(html):
    """
    处理筛选网页内容中需要的信息
    :param html: 网页内容
    :return: 字典
    """
    pattern = re.compile(‘<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a‘
                         + ‘.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>‘
                         + ‘.*?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_file(content):
    """
    将结果数据写入文件
    :param content: 需要写入文件的内容
    :return: 
    """
    with open(‘result.txt‘, ‘a‘, encoding=‘utf-8‘) as f:
        f.write(json.dumps(content, ensure_ascii=False) + "\n")
        f.close()


def main(offset):
    """
    主函数
    :param offset: offset值，用于构造url
    :return: 
    """
    url = "http://maoyan.com/board/4?offset=" + str(offset)
    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(i*10)
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])

 

【来自天善智能】：https://edu.hellobi.com/course/156/play/lesson/2453

 

崔大师的代码看着就是舒服。。。。