python爬虫爬取王者荣耀官网全部英雄技能信息(源码分享)

这篇文章为源码分享，爬虫的分析过程请阅读文章

• 《用python爬取王者荣耀官网的英雄皮肤海报(含源码)》

源码

import requests
import json
from bs4 import BeautifulSoup

headers = {
     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
                         'Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5958.400 SLBrowser/10.0.3533.400'}


def GetSoup(url):
    resp = requests.get(url, headers=headers)
    resp.encoding = 'gbk'
    soup = BeautifulSoup(resp.text, 'lxml')
    return soup


#获取json数据，并解析成存有英雄id与名字的列表[[id,name],[id1,name1].......]
def jsonToHeroInfoList(jsonURL):
    resp  =requests.get(jsonURL)
    jsonData = json.loads(resp.text)
    heroInfoList = []
    for data in jsonData:
        hero_info =[]
        hero_info.append(data['ename'])
        hero_info.append(data['cname'])
        heroInfoList.append(hero_info)
    return heroInfoList


Json_url = "https://pvp.qq.com/web201605/js/herolist.json"
heroInfoList = jsonToHeroInfoList(Json_url)
f = open('C:/Users/TTODS/Desktop/王者荣耀/王者荣耀英雄技能介绍.txt', 'a')
for heroInfo in heroInfoList:
    # Get Id
    _id = heroInfo[0]
    name = heroInfo[1]
    f.write("\n\n"+name+'\n')
    # 找技能
    url = 'https://pvp.qq.com/web201605/herodetail/%s.shtml' % _id
    soup = GetSoup(url)
    skillList = soup.find_all('div', class_="show-list")
    for skill in skillList:
       skill_name = skill.find('b').text
       skill_cd = skill.find('span').text
       skill_cost = skill.find_all('span')[1].text
       skill_desc = skill.find('p', class_="skill-desc").text
       if skill_name != "":
           f.write(skill_name+'\n')
           f.write(skill_cost+'\n')
           f.write(skill_cd+'\n')
           f.write(skill_desc+'\n')
           print(skill_name+'\n')
           print(skill_cost)
           print(skill_cd)
           print(skill_desc)
f.close()

爬取结果