import  requests
import parsel
for page in range(1,5):
        print(f'============第{page}页===========')
        headers = {
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36"
        }
        url = f'https://www.hexuexiao.cn/meinv/guzhuang/list-{page}.html'
        response = requests.get(url=url, headers=headers)
        text = response.text
        #print(text)
        selector = parsel.Selector(text)
        href_list = selector.xpath('//div[@class="waterfall_1box"]/dl/dd/a/@href').getall()
        #print(href_list)
        for href in href_list:
                href_data = requests.get(url=href, headers=headers).text
                selector_2 = parsel.Selector(href_data)
                img_url = selector_2.xpath('//a[@class="btn btn-default btn-xs"]/@href').get()
                #print(img_url)
                img_data = requests.get(url=img_url, headers=headers).content
                filename = img_url.split('/')[-1]
                #print(filename)
                with open('img\\' + filename, mode='wb') as f:
                        f.write(img_data)
                        print(filename)

import requests
import parsel
headers = {
        'Cookie': 't=f8e5c504a4e96b4ddcd519559ac24870; r=1066; XSRF-TOKEN=eyJpdiI6IkdLWWRpRVlmUzk2RVNIWVVENms0V2c9PSIsInZhbHVlIjoiVDcwbjlCNEVnUFZHdG5XREJ1VWIxZWlNN2dPTG5XSEh4UTIycTdaQ2V2aWF1UkpPU2dpeEU0Z3lQaVZJazhscWt1XC80cEt0eVJcL2doaXVlZXZBaWh3U2hGNlU2VXlSQzRrY3lcL1BjdkV3b2dMUFR2MTk1UHhcL0tNY2NORVJ3MGdZIiwibWFjIjoiOTM4YWZmNTAyZDBhY2RkMmQzOWQyMDAzZDAyNzhjMDk5ZWZhZWJjMjAzMDI3MzI3MDI2ZGZjYjQ3MDJhYTZlMCJ9; win4000_session=eyJpdiI6IklKSlVWMlFHTkkzaExpdEVGYlNweUE9PSIsInZhbHVlIjoibVpxYjhHWGhocVBYZFwvQW8rZzFzdG1Td3BuRzVLbzRjTHdQd2J4aTJHWXJcL1hpTk5YNU9GUnNTSHpVU2p3Y3UxcDE3UE1UV3BzT2hJektjM2R6K1l0NGR4RmFiY1NhZlIzR0VzakhEQzdmT3Z4UjR2ZDdjZ2RJYlhcL2xzY1J4TnMiLCJtYWMiOiI2NGUyMWEwOWIxOWM1NWJkNmI1OTJlYTJjYmRjMjI1MDdkNWRmOTc5NWMyN2NlNmM0MzRkZThmMjYxOTQ2MjI0In0%3D',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
}
base_url ='http://www.win4000.com/mobile_2340_0_0_1.html'
response = requests.get(url=base_url, headers=headers)
data = response.text
#print(data)
html_data = parsel.Selector(data)
data_list = html_data.xpath('//div[@class="Left_bar"]//ul[@class="clearfix"]/li/a/@href').extract()
#print(data_list)
for alist in data_list:
       #print(alist)
        response_2 = requests.get(url=alist, headers=headers).text
        html_2 = parsel.Selector(response_2)
        img_url = html_2.xpath('//div[@class="pic-meinv"]/a/img/@src').extract_first()
        #print(img_url)
        img_data = requests.get(url=img_url, headers=headers).content
        file_name = img_url.split('/')[-1]
        with open('img\\' + file_name, 'wb') as f:
                print(file_name)
                f.write(img_data)

import requests
import os
url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
}
def save( hero_name, name, img_url):
    filename = f'{hero_name}\\'
    if not os.path.exists(filename):
        os.mkdir(filename)
    img_content = requests.get(url=img_url).content
    with open(filename + name + '.jpg', mode='wb') as f:
        f.write(img_content)
response = requests.get(url=url, headers=headers)
heroes = response.json()['hero']
for hero in heroes:
    hero_id = hero['heroId']
    hero_url = f'https://game.gtimg.cn/images/lol/act/img/js/hero/{hero_id}.js'
    response_1 = requests.get(url=hero_url, headers=headers)
    skins = response_1.json()['skins']
    for index in skins:
        title = index['heroTitle']
        hero_name = index['heroName']+title
        img_name = index['name']
        img_url = index['mainImg']
        if img_url:
            save(hero_name, img_name,img_url)
        else:
            img_url = index['chromaImg']
    print(title)