异步多线程爬取表情包-01

# 导入相关的库
import requests
from lxml import etree
from urllib import request
import os
import re


# 页面解析
def parse_page(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 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")
    for img in imgs:
        # 获得图片的 URL
        img_url = img.get("data-original")
        # 获得图片的内涵名字
        alt = img.get("alt")
        # 利用正则表达式去除不符合命名规范的字符
        alt = re.sub(r'[?？!！@ ε=(´ο｀*)))]', '', alt)
        # 利用 OS模块儿获取图片后缀名
        after_name = os.path.splitext(img_url)[1]
        # 获取图片全名
        full_name = alt + after_name
        # 利用request方法下载图片并保存在 download 文件夹下面
        request.urlretrieve(img_url, 'download/'+full_name)


# 获取 URL
def main():
    # range(1, 101) 代表下载第1-100页的表情包
    for x in range(1, 101):
        url = "https://www.doutula.com/photo/list/?page=%d" % x
        parse_page(url)
        break


if __name__ == '__main__':
    main()