python爬取猫眼电影评分

最新推荐文章于 2023-02-17 08:59:02 发布

AlexWong2526

最新推荐文章于 2023-02-17 08:59:02 发布

阅读量1.1k

点赞数

分类专栏： python 文章标签： python 爬虫

本文链接：https://blog.csdn.net/u010024991/article/details/95312690

版权

python 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

直接上代码

import datetime
import json
from multiprocessing.dummy import Pool
from time import localtime, strftime

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
        else:
            return None
    except RequestException:
        return None

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

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

if __name__ == '__main__':
    # for i in range(10):
    #     main(i*10)
    start = datetime.datetime.now()
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])
    end = datetime.datetime.now()
    print(end - start)