requests+正则爬取猫眼电影前100

版权声明：版权所有，转载请注明出处 https://blog.csdn.net/weixin_41733260/article/details/88069933

最近复习功课，日常码农生活。

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

#requests.get()调用完记得抓异常
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):
    #re.S使.可以匹配换行符
    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:
        #利用yield生成器
        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:
        #json.dumps将字典转换为字符串 ,json.load()将json格式数据转换为字典
        f.write(json.dumps(content, ensure_ascii=False) + '\n')
        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__':
    #引入进程池，加快爬取速度
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])