多线程爬取都挺好链接并保存到mongodb

Posted 2021-02-15

• 一个比较简单，python3多线程使用requests库爬取都挺好，并使用正则提取下载链接，保存到mongodb

#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
@author:Aiker Zhao
@file:doutinghao.py
@time:下午8:18
"""
import requests
import re
import pymongo
from multiprocessing import Pool

MONGO_URL = ‘localhost:27017‘
MONGO_DB = ‘doutinghao‘
MONGO_TABLE = ‘doutinghao‘
client = pymongo.MongoClient(MONGO_URL, connect=False)
db = client[MONGO_DB]

def get_result(url):
    response = requests.get(url).text
    # print(reponse.text)
    pattern = re.compile(‘<a href="(ed2k.*?)"srel.*?title="(.*?.mp4).*?".*?>‘, re.S)
    result = re.findall(pattern, response)
    if result:
        for i in result:
            url, name = i
            yield {
                "name": name,
                ‘url‘: url
            }

def save_to_mongo(result):
    if db[MONGO_TABLE].insert(result):
        print(‘存储到MongoDB成功‘, result)
        return True
    return False

def main(result):
    # result = get_result(url)
    save_to_mongo(result)

if __name__ == ‘__main__‘:
    pool = Pool()
    url = "https://www.xl720.com/thunder/34283.html"
    item = [item for item in get_result(url)]
    # print(item)
    pool.map(main, item)
    pool.close()
    pool.join()