关于php:python-采集斗图啦多线程

48次阅读

共计 1405 个字符，预计需要花费 4 分钟才能阅读完成。

import concurrent
import requests;
from concurrent.futures import ThreadPoolExecutor
import os;
import parsel;

def send_request(url):
    header = {"user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
    }
    requests.packages.urllib3.disable_warnings()
    response = requests.get(url,headers=header)
    return response
def pare_data(data):
     selector = parsel.Selector(data)
     result_list = selector.xpath('//a[@class="col-xs-6 col-sm-3"]')
     for result in result_list:
        title = result.xpath('./img/@alt').get()
        src_url = result.xpath('./img/@data-original'). get()

        all_title = title+'.'+src_url.split('.')[-1]
        yield all_title,src_url

def save_data(file_name,data):
    dir_name = 'doutu_list'
    if not os.path.exists(dir_name):
        os.mkdir(dir_name)
    with open(dir_name+'/'+file_name,'wb') as f:
        f.write(data)
        print("保留实现:",file_name)


def main(page):
    for page in range(1,page+1):
        print('######################## 以后为第 {} 页 ########################'.format(page))
        thread_pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
        res = send_request('https://www.doutula.com/photo/list/?page={}'.format(str(page)))
        src_url = pare_data(res.text)
        for file,url in src_url:
            print(file)
            print(url)
            image_response = send_request(url)
            thread_pool.submit(save_data,file,image_response.content)
        thread_pool.shutdown()

if __name__=='__main__':
    main(1)