爬虫爬取王者荣耀 英雄故事 和技能

爬取王者荣耀英雄故事和技能

源码奉上

import requests
import re
import os
from lxml import etree
if __name__ == '__main__':
    #创建一个文件夹wz
    #打算爬取皮肤图片，铭文，出装等 先创建一个文件夹使用
    if not os.path.exists('./wz'):
        os.mkdir('./wz')
    #爬取的网站
    url = 'https://pvp.qq.com/web201605/herolist.shtml'
    #伪装
    headers = {'User-Agent': 'Mozilla/5.0 (Windows'
                             ' NT 10.0; WOW64)'
                             'AppleWebK'
                             'it/537.36 (KHTML, like Gecko)'
                             ' Chrome/85.0.4183.102 Sa'
                             'fari/537.36'}
    #爬取源码数据
    page= requests.get(url=url,headers=headers)
    #防止乱码
    page.encoding='gbk'
    page_text=page.text
    # print(page_text)
    #进行数据解析
    tree= etree.HTML(page_text)
    #定位到所需数据
    list_w=tree.xpath('//ul[@class="herolist clearfix"]/li')
    for li in list_w:
        #爬取英雄名字
        cover_name=li.xpath('./a/text()')[0]
        #爬取单个英雄对应的网址
        w='https://pvp.qq.com/web201605/'+li.xpath('./a/@href')[0]
        # print(cover_name)
        # print(w)

        page_w=requests.get(url=w,headers=headers)
        page_w.encoding='gbk'
        # 爬取英雄页面源码数据
        page_w_text=page_w.text
        #print(page_w_text)

        #数据解析（英雄故事）
        tree_story =etree.HTML(page_w_text)
        list_story=tree_story.xpath('//div[@class="pop-bd"]')

        for li_story in list_story:
            #拿到英雄故事TXT文本
            story=li_story.xpath('./p/text()')
            print(cover_name,':',story)

        tree_skill = etree.HTML(page_w_text)
        list_skill=tree_skill.xpath('//div[@class="skill-show"]/div')
        for li_skill in list_skill:
            #拿到英雄技能和技能描述
            skill=li_skill.xpath('./p[@class="skill-name"]/b/text()')+li_skill.xpath('./p[@class="skill-desc"]/text()')
            # skill_desc=li_skill.xpath('./p[@class="skill-desc"]/text()')
            print(skill)