chainetv/chaineTV.py

242 lines
8.0 KiB
Python
Raw Normal View History

2018-08-17 18:31:23 +00:00
import json
import sys
import os
import unicodedata
import webbrowser
import urllib.request
2018-08-18 17:57:43 +00:00
import re
2018-08-20 21:07:50 +00:00
import io
from PIL import Image,ImageTk
2018-08-20 19:53:16 +00:00
from bs4 import BeautifulSoup
2018-08-20 21:07:50 +00:00
from tkinter import Label,Button,Frame,Tk,Entry,StringVar,LEFT,RIGHT,PhotoImage,Image
class Labbelink (Label):
def __init__(self,parent,text,link):
Label.__init__(self,parent,text=text,fg="blue",cursor="hand2")
self.link=link
self.bind("<Button-1>",self._openlink)
2018-08-18 17:57:43 +00:00
def _openlink(self,evt):
webbrowser.open(self.link)
2018-08-17 18:31:23 +00:00
class Interface:
def __init__(self):
self.datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json"
self.data = load_jsonfile(self.datafilepath)
self.fenetre = Tk()
self.fenetre.title("recherche de chaine")
self.value = StringVar()
self.label = Label(self.fenetre, text="entrer numero de chaine")
self.entree = Entry(self.fenetre, textvariable=self.value, width=30)
self.frame = Frame(self.fenetre)
self.resultframe = Frame(self.fenetre)
2018-08-17 18:31:23 +00:00
self.bouton_update_base = Button(
self.fenetre, text="update la base de chaine", command=self.click_update)
self.bouton = Button(self.frame, text="OK", command=self.click)
self.reset = Button(self.frame, text="reset", command=self.click_reset)
self.label.pack()
self.entree.pack()
self.entree.focus_set()
self.resultframe.pack(expand=1,fill='both')
2018-08-17 18:31:23 +00:00
self.frame.pack()
self.bouton.pack(side=LEFT)
self.reset.pack(side=RIGHT)
self.bouton_update_base.pack()
self.fenetre.bind("<Key-Return>", self.enter)
self.fenetre.bind("<Key-Escape>", self.eventreset)
def enter(self,evt):
self.click()
def eventreset(self,evt):
self.click_reset()
def mainloop(self):
self.fenetre.mainloop()
def click(self):
print(self.value.get())
2018-08-17 18:31:23 +00:00
try:
strlink=geturlprogrammetv(self.data[self.value.get()])
link= Labbelink(self.resultframe,self.data[self.value.get()],strlink)
link.pack()
2018-08-17 18:31:23 +00:00
print(self.data[self.value.get()])
2018-08-20 19:53:16 +00:00
self.resultframe.update()
emision=parse_emmission(strlink)
2018-08-20 21:07:50 +00:00
if emision:
if emision == "can't find show":
Label(self.resultframe,text="impssible de parser cette chaine").pack()
else:
2018-08-20 21:07:50 +00:00
raw_data = urllib.request.urlopen(emision['img']).read()
image = ImageTk.PhotoImage(file=io.BytesIO(raw_data))
photolabel=Label(self.resultframe,image=image)
photolabel.image = image
photolabel.pack()
2018-08-20 19:53:16 +00:00
Labbelink(self.resultframe,("emmision ce soir: "+emision["title"]),emision['href']).pack()
if len(emision['casting']) > 0:
Label(self.resultframe,text="réalisateur: "+emision['casting'][0]).pack()
Label(self.resultframe,text="acteur: "+str(emision['casting'][1:])).pack()
2018-08-20 21:07:50 +00:00
Label(self.resultframe,text="synopsys: " +emision['synopsis'],wraplength=350).pack()
else:
Label(self.resultframe,text="pas de connection internet impossible de determiner l'émission du soir").pack()
2018-08-20 19:53:16 +00:00
2018-08-17 18:31:23 +00:00
except KeyError:
print("numero de chaine inconnue")
unknow=Label(self.resultframe, text="numero de chaine inconnue")
unknow.pack()
#self.label2["text"] += geturlprogrammetv(self.data[self.value.get()])
2018-08-17 18:31:23 +00:00
self.value.set("")
def click_reset(self):
print("reset")
for child in self.resultframe.winfo_children():
child.destroy()
2018-08-17 18:31:23 +00:00
def click_update(self):
parsechaine(self.datafilepath)
self.data = load_jsonfile(self.datafilepath)
labelupdate = Label(self.resultframe, text="update chaine done"+"\r")
labelupdate.pack()
def _openlink(self,link):
webbrowser.open_new(link)
2018-08-17 18:31:23 +00:00
def load_jsonfile(file):
try:
with open(file, 'r', encoding='utf-8') as f:
return json.load(f)
except FileNotFoundError:
parsechaine(file)
with open(file, 'r', encoding='utf-8') as f:
return json.load(f)
def RepresentsInt(s):
try:
int(s)
return True
except ValueError:
return False
except TypeError:
return False
def parsechaine(file):
2018-08-17 18:31:23 +00:00
URL = 'https://fr.wikipedia.org/wiki/Liste_des_cha%C3%AEnes_de_Canal'
liste_chaine = {}
response = urllib.request.urlopen(URL)
html = response.read()
parse = BeautifulSoup(html,"html.parser")
for item in parse.find_all('table'):
if (item.get("class") == ['wikitable'] or item.get("class") == ['wikitable', 'sortable']):
for tr in item.find_all('tr'):
firstTD = tr.find()
num = firstTD.text
#print(num)
if RepresentsInt(num):
if RepresentsInt(firstTD.find_next().string):
2018-08-18 17:57:43 +00:00
#print(firstTD.find_next().find_next().text)
liste_chaine[int(num)] = firstTD.find_next().find_next().text
2018-08-17 18:31:23 +00:00
else:
#print(firstTD.find_next().string)
liste_chaine[int(num)] = firstTD.find_next().text
print(json.dumps(liste_chaine, indent=4))
with open(file, 'w', encoding='utf-8') as f:
json.dump(liste_chaine, f, indent=4)
def geturlprogrammetv(strsearch):
strsearch=unicodedata.normalize('NFD', strsearch).encode('ascii', 'ignore')
strsearch=strsearch.decode("utf-8")
strsearch=strsearch.replace(" ","+")
return "https://www.programme-tv.net/rechercher?q="+strsearch
def parse_emmission(URL):
try:
response = urllib.request.urlopen(URL)
except urllib.error.URLError:
return False
html = response.read()
parse=BeautifulSoup(html,"html.parser")
link=parse.select_one(".prog_name")
if link == None:
return "can't find show"
href="https://www.programme-tv.net"+link['href']
response = urllib.request.urlopen(href)
html = response.read()
parse=BeautifulSoup(html,"html.parser")
divcasting=parse.select_one(".descriptif")
casting=divcasting.find_all(href=re.compile("biographie"))
i=0
for actor in casting:
casting[i]=actor.text
i+=1
divsynopsis=parse.select_one(".episode-synopsis")
img=divsynopsis.find_next('img')['data-src']
synopsis=divsynopsis.select_one(".d-b").text
2018-08-20 17:06:50 +00:00
return {'title':link['title'],'href':href,'casting':casting,'synopsis':remove_first_space(synopsis),'img':img}
2018-08-17 18:31:23 +00:00
def remove_first_space (string):
space_number=0
for char in string:
2018-08-20 17:06:50 +00:00
if char.isspace():
space_number+=1
else:
break
return string[space_number:]
2018-08-17 18:31:23 +00:00
def cli(num):
datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json"
data = load_jsonfile(datafilepath)
print(num)
try:
2018-08-18 17:57:43 +00:00
print(data[num])
2018-08-17 18:31:23 +00:00
except KeyError:
print("numero de chaine inconnue")
return
emision=parse_emmission(geturlprogrammetv(data[num]))
if emision:
if emision == "can't find show":
print ("impssible de parser cette chaine")
else:
print("emmision ce soir: "+emision["title"])
if len(emision['casting']) > 0:
print("réalisateur: "+emision['casting'][0])
print("acteur: "+str(emision['casting'][1:]))
print("synopsys: " +emision['synopsis'])
print("lien: "+emision['href'])
else:
print("pas de connection internet impossible de determiner l'émission du soir")
print("")
2018-08-17 18:31:23 +00:00
if len(sys.argv) > 1:
for i in sys.argv[1:]:
if i =="update":
parsechaine(os.path.dirname(os.path.realpath(__file__))+"/chaine.json")
else:
cli(i)
else:
2018-08-18 17:57:43 +00:00
Interface().mainloop()