def Fantojian(readfilename, writefilename, append):
strs = Readfromjson(readfilename)
for i in strs:
traditional_sentence = i
simplified_sentence = Traditional2Simplified(traditional_sentence)
try:
simplified_sentence = json.loads(simplified_sentence,
encoding="utf-8")
writejson(simplified_sentence, writefilename, append)
except:
print(simplified_sentence)
if i<len(htmls)-1:
attendteams = []#球队的连接并非都在b标签中
if i==0:
attendteams = getAttendteams6(soup, "第一","第二")
elif i>=12 and i<=20:
attendteams = getAttendteams6(soup, "亞","亞")
else:
try:
attendteams = getAttendteams5(soup,"[A-Z].*組","[A-Z].*組")#仅计算小组赛(A,B,C,组),表格无序号为td
if attendteams==[]:
attendteams = getAttendteams5_b(soup, "[A-Z].*組", "[A-Z].*組")#仅计算小组赛(A,B,C,组),表格有序号为td
if attendteams==[]:
attendteams = getAttendteams5(soup, "組", "組")#无小组赛页面，计算第一、二组，表格无序号为td
if attendteams==[]:
print(i)
attendteams = getAttendteams5_b(soup, "組", "組")#无小组赛页面，计算第一、二组，表格有序号为td
except:
attendteams=getAttendteams5_c(soup, "[A-Z].*組", "[A-Z].*組")#一个表格中嵌套了两个表格
dict["attendteams"]=attendteams
print(i,url,len(attendteams),attendteams)
writejson(dict,"亚冠_output.json","a")
# #若页面为繁体，转化为简体
# Fantojian("亚冠_output.json","亚冠_output(简).json","a")
attendteams = getAttendteams(time, soup)
if time == "2008-09":
attendteams = getAttendteams2(time, soup) #08-09
if time == "2018-19" or time == "2016-17": #16-17的常规赛数据为个人数据
attendteams = getAttendteams3(time, soup) #18-19
if time == "2005-06":
attendteams = getAttendteams4(time, soup) #05-06
game["attendteams"] = attendteams
Inforbox = getInforbox(soup)
game["Inforbox"] = Inforbox
brief = getBrief(soup)
game["brief"] = brief
return game
urls = [] #cba的url信息
for i in range(5, 20):
j = i + 1
if i == 19:
time = ""
else:
time = "20%02d-%02d年" % (i, j)
url = str(time) + "中国男子篮球职业联赛"
url = "https://zh.wikipedia.org/wiki/" + quote(url, safe='')
urls.append(url)
game = parseCba(time, url)
writejson(dict, "cba_output.json", "a")
dict = {"name": "", "link": "", "brief": "", "Inforbox": ""} # "attendteams": "",
soup=htmls[i]
url=geturlfromhtml(soup)
dict["link"]=url
name=soup.select("title")[0].get_text().replace(" - 维基百科，自由的百科全书","")
dict["name"]=name
infobox=getInforbox(soup)
dict["Inforbox"]=infobox
brief=getBrief(soup).strip("\n")
if brief=="":
brief=getBrief2(soup).strip("\n")
dict["brief"]=brief
if i<len(htmls)-1:
attendteams = []
try:#getAttendteams2和2的顺序不能颠倒
attendteams = getAttendteams2(soup,"積分榜")
print(url, attendteams)
except:
attendteams = getAttendteams(soup,"積分榜")
print(url,attendteams)
dict["attendteams"]=attendteams
writejson(dict,"ENgland/英超_output.json")
dict = {"name": "", "link": "", "brief": "", "Inforbox": ""}#"attendteams": "",
soup=htmls[i]
url=geturlfromhtml(soup)
dict["link"]=url
name=soup.select("title")[0].get_text().replace(" - 维基百科，自由的百科全书","")
dict["name"]=name
infobox=getInforbox(soup)
dict["Inforbox"]=infobox
brief=getBrief(soup).strip("\n")
if brief=="":
brief=getBrief2(soup).strip("\n")
dict["brief"]=brief
if i<len(htmls)-1:
attendteams = []
try:#getAttendteams4和3的顺序不能颠倒
attendteams = getAttendteams4(soup,"积分榜","積分榜")
print(url, attendteams)
except:
attendteams = getAttendteams3(soup,"积分榜","積分榜")
print(url,attendteams)
dict["attendteams"]=attendteams
writejson(dict, "CSL/中超_output.json")
from langconv import *
from ReadfromJson import Readfromjson
from WritetoJson import writejson
import json
def Traditional2Simplified(sentence):
'''
将sentence中的繁体字转为简体字
:param sentence: 待转换的句子
:return: 将句子中繁体字转换为简体字之后的句子
'''
sentence = Converter('zh-hans').convert(sentence)
return sentence
if __name__ == "__main__":
strs = Readfromjson("AFC/亚冠_output.json")
for i in strs:
traditional_sentence = i
simplified_sentence = Traditional2Simplified(traditional_sentence)
try:
simplified_sentence = json.loads(simplified_sentence,
encoding="utf-8")
writejson(simplified_sentence, "AFC/亚冠_output(简).json", "a")
except:
print(simplified_sentence)