黑马程序员Python爬虫基础，快速入门Scrapy爬虫框架

#拿到页面原地阿玛
#拿到所有ul上面得a标签

from lxml import etree
import re
import requests
import json
domain = 'https://desk.zol.com.cn'
url = 'https://desk.zol.com.cn/'
resp = requests.get(url)
resp.encoding = 'gbk'
# print(resp.text)
et = etree.HTML(resp.text)
result = et.xpath('//ul[@class="pic-list2 clearfix"]/li/a/@href')
# print(result)

for item in result:
    url = domain + item
    print(url)
    # url = 'https://desk.zol.com.cn/bizhi/10055_120350_2.html'
    resp = requests.get(url)
    # print(resp.text)
    obj = re.compile(r'var deskPicArr.*?=(?P<deskPicArr>.*?);',re.S)
    result = obj.search(resp.text)
    deskPicArr = result.group('deskPicArr')
    # print(deskPicArr)
    dic = json.loads(deskPicArr)
    # print(dic)
    for item in dic['list']:
        oriSize = item.get('oriSize')
        imgsrc = item.get('imgsrc')
        # print(oriSize,imgsrc)
        imgsrc = imgsrc.replace('##SIZE##',oriSize)
        print(imgsrc)
        #发送网络请求
        name = imgsrc.split('/')[-1]
        resp_img = requests.get(imgsrc)
        #此时拿到的不是resp.text, resp.content拿到的是字节
        with open(f"img/{name}",mode="wb") as f:
            f.write(resp_img.content)
            # print(f)