单线程+多线程下载doutula.com图片

现在是2018年8月11日11:26:42，我挖的eth又降价了、、、、、

单线程

# -*- coding:utf-8 -*-

import re
import os
import urllib
import requests
from lxml import etree

def parse_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    text = response.text
    html = etree.HTML(text)
    imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']")
    for img in imgs:
        img_url = img.get('data-original')
        alt = img.get('alt')
        alt = re.sub(r'[\?？\.，。！!]','',alt)
        suffix = os.path.splitext(img_url)[1]
        filename = alt+suffix
        print filename
        urllib.urlretrieve(img_url,'images/'+filename)

def main():
    for x in range(1,101):
        url = "http://www.doutula.com/photo/list/?page=%d" % x
        parse_page(url=url)

if __name__ == '__main__':
    main()