python爬取王者荣耀皮肤集

from selenium import webdriver

driver = webdriver.Chrome('D:\数据分析\chromedriver_win32\chromedriver.exe') #下载好对应chromedriver.exe
driver.get('https://pvp.qq.com/web201605/herolist.shtml') #王者荣耀英雄资料页面

点击具体英雄头像就可以进入具体英雄页面，所以我们可以右键检查，得到英雄名和英雄链接的定位。

hrefs = driver.find_elements_by_css_selector(
    'body > div.wrapper > div > div > div.herolist-box > div.herolist-content > ul > li > a')
imgs = driver.find_elements_by_css_selector(
    'body > div.wrapper > div > div > div.herolist-box > div.herolist-content > ul > li > a > img')

hero_detail = [] #英雄名和英雄链接添加到列表
for i in range(len(imgs)):
    item = {}
    item['hero'] = imgs[i].get_attribute("alt")
    item['detial'] = hrefs[i].get_attribute("href")
    hero_detail.append(item)

driver.quit() #关闭chrome

打印列表hero_detail

print(hero_detail)

import lxml.html
import json
import os

skin_list = []  #列表

for i in hero_detail:

    driver = webdriver.Chrome('D:\数据分析\chromedriver_win32\chromedriver.exe')
    driver.maximize_window()
    driver.get(i['detial'])  #英雄链接
    html_datas = driver.page_source  #页面源代码
    driver.quit()

    #利用lxml解析库的etree.parse方法加载本地html文件的路径
    metree = lxml.html.etree
    parser = metree.HTML(html_datas)

    li_list = parser.xpath("/html/body/div[3]/div[1]/div/div/div[2]/ul//li") #定位皮肤的li标签


    for li_element in li_list:
        item = {}
        item["hero_name"] = i['hero']
        skin_name = li_element.xpath("./p/text()")[0]  #皮肤名称
        item["hero_skin_name"] = skin_name
        skin_url = "https:" + li_element.xpath("./i/img/@data-imgname")[0] #皮肤链接
        item["hero_skin_url"] = skin_url
        skin_list.append(item) #皮肤名称对应皮肤链接

打印skin_list皮肤列表

hero_image_dir_name = "./hero/pictures"
if not os.path.exists(hero_image_dir_name):
    os.makedirs(hero_image_dir_name)
# 遍历
for hero_element in skin_list:
    hero_pic_dir = hero_element["hero_name"]
    # 判断
    if not os.path.exists(hero_image_dir_name + "/" + hero_pic_dir):
        os.makedirs(hero_image_dir_name + "/" + hero_pic_dir)
        print("英雄(%s)所存放目录已创建成功!" % hero_pic_dir)
    # 提示
print("所有英雄存放目录已创建成功!")

下载图片放置到对应的目录

import requests
hero_file_dir = "./hero/pictures"
for hero_element in skin_list:
    #文件夹名称
    dir_name = hero_element["hero_name"]
    # 图片皮肤地址
    image_url = hero_element["hero_skin_url"]
    #图片皮肤名称
    hero_skin_name= hero_element["hero_skin_name"]
    # 请求数据
    headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"};
    response = requests.get(image_url, headers=headers, verify=False)

    hero_dir_skin = './hero/pictures/' + dir_name

    if not os.path.exists(hero_dir_skin):
        os.makedirs(hero_dir_skin)
        # 下载并保存
    with open(hero_dir_skin + "/" + hero_skin_name + ".jpg", "wb") as fs:
        fs.write(response.content)

对应目录查看图片