Python爬取OPGG上英雄联盟英雄胜率及选取率信息的操作

getHTMLText(url)->fillHeroInformation(hlist,html)->printHeroInformation(hlist)

def getHTMLText(url): #返回html文档信息
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text #返回html内容
    except:
        return ""

def fillHeroInformation(hlist,html): #将英雄信息存入hlist列表
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find(name = "tbody",attrs = "tabItem champion-trend-tier-TOP").children: #遍历上单tbody标签的儿子标签
        if isinstance(tr,bs4.element.Tag): #判断tr是否为标签类型，去除空行
            tds = tr('td') #查找tr标签下的td标签
            heroName = tds[3].find(attrs = "champion-index-table__name").string #英雄名
            winRate = tds[4].string #胜率
            pickRate = tds[5].string #选取率
            hlist.append([heroName,winRate,pickRate]) #将英雄信息添加到hlist列表中

 def printHeroInformation(hlist): #输出hlist列表信息
     print("{:^20}\t{:^20}\t{:^20}\t{:^20}".format("英雄名","胜率","选取率","位置"))
     for i in range(len(hlist)):
         i = hlist[i]
         print("{:^20}\t{:^20}\t{:^20}\t{:^20}".format(i[0],i[1],i[2],"上单"))

 def main():
     url = "http://www.op.gg/champion/statistics"
     hlist = []
     html = getHTMLText(url) #获得html文档信息
     fillHeroInformation(hlist,html) #将英雄信息写入hlist列表
     printHeroInformation(hlist) #输出信息

import requests #导入requests库
import bs4 #导入bs4库
from bs4 import BeautifulSoup #导入BeautifulSoup库
def getHTMLText(url): #返回html文档信息
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text #返回html内容
    except:
        return ""
def fillHeroInformation(hlist,html): #将英雄信息存入hlist列表
    soup = BeautifulSoup(html,"html.parser")
    for tr in soup.find(name = "tbody",attrs = "tabItem champion-trend-tier-TOP").children: #遍历上单tbody标签的儿子标签
        if isinstance(tr,bs4.element.Tag): #判断tr是否为标签类型，去除空行
            tds = tr('td') #查找tr标签下的td标签
            heroName = tds[3].find(attrs = "champion-index-table__name").string #英雄名
            winRate = tds[4].string #胜率
            pickRate = tds[5].string #选取率
            hlist.append([heroName,winRate,pickRate]) #将英雄信息添加到hlist列表中
def printHeroInformation(hlist): #输出hlist列表信息
    print("{:^20}\t{:^20}\t{:^20}\t{:^20}".format("英雄名","胜率","选取率","位置"))
    for i in range(len(hlist)):
        i = hlist[i]
        print("{:^20}\t{:^20}\t{:^20}\t{:^20}".format(i[0],i[1],i[2],"上单"))
def main():
    url = "http://www.op.gg/champion/statistics"
    hlist = []
    html = getHTMLText(url) #获得html文档信息
    fillHeroInformation(hlist,html) #将英雄信息写入hlist列表
    printHeroInformation(hlist) #输出信息
main()

fillHeroInformation(hlist,html)

for tr in soup.find(name = "tbody",attrs = "tabItem champion-trend-tier-TOP").children语句