Python爬虫requestions库和正则表达式的使用练习

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_28844767/article/details/80677840

from multiprocessing.dummy import Pool

import requests
from requests.exceptions import RequestException
import re
import json
def get_one_age(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
        }
        response = requests.get(url,headers = headers)
        if response.status_code == 200 :
            return response.text
        return None
    except RequestException:
        return None

def parse_one_age(html):
    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):
    with open("result.txt","a",encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+"\n")
        f.close()



def main(offset):
    url = "http://maoyan.com/board/4?offset=" + str(offset)
    html = get_one_age(url)
    for item  in parse_one_age(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)])