vincent/chainetv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ajout titre synopsys et casting a la cli

Browse Source
This commit is contained in:
vincent 2018-08-18 19:03:27 +02:00
parent 055e4f17c1
commit e89626e630
2 changed files with 51 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
chaineTV.py
View File

@ -5,6 +5,8 @@ import os
import unicodedata import unicodedata
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import webbrowser import webbrowser
import urllib.request
class Labbelink (Label): class Labbelink (Label):
@ -18,7 +20,6 @@ class Labbelink (Label):
class Interface: class Interface:
def __init__(self): def __init__(self):
self.datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json" self.datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json"
self.data = load_jsonfile(self.datafilepath) self.data = load_jsonfile(self.datafilepath)
@ -110,7 +111,7 @@ def RepresentsInt(s):
return False return False
def parsechaine(file): def parsechaine(file):
import urllib.request
URL = 'https://fr.wikipedia.org/wiki/Liste_des_cha%C3%AEnes_de_Canal' URL = 'https://fr.wikipedia.org/wiki/Liste_des_cha%C3%AEnes_de_Canal'
liste_chaine = {} liste_chaine = {}
response = urllib.request.urlopen(URL) response = urllib.request.urlopen(URL)
@ -142,6 +143,29 @@ def geturlprogrammetv(strsearch):
return "https://www.programme-tv.net/rechercher?q="+strsearch 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")
response = urllib.request.urlopen(("https://www.programme-tv.net"+link['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
return {'title':link['title'],'href':("https://www.programme-tv.net"+link['href']),'casting':casting,'synopsis':synopsis,'img':img}
def cli(num): def cli(num):
datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json" datafilepath=os.path.dirname(os.path.realpath(__file__))+"/chaine.json"
@ -152,8 +176,17 @@ def cli(num):
except KeyError: except KeyError:
print("numero de chaine inconnue") print("numero de chaine inconnue")
return return
print (geturlprogrammetv(data[num])) emision=parse_emmission(geturlprogrammetv(data[num]))
if emision:
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")
if len(sys.argv) > 1: if len(sys.argv) > 1:
for i in sys.argv[1:]: for i in sys.argv[1:]:

16
parserHTML.py
View File

@ -4,6 +4,7 @@
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import urllib.request import urllib.request
import json import json
import re
def RepresentsInt(s): def RepresentsInt(s):
try: try:
@ -47,7 +48,20 @@ def parse_emmission(URL):
html = response.read() html = response.read()
parse=BeautifulSoup(html,"html.parser") parse=BeautifulSoup(html,"html.parser")
link=parse.select_one(".prog_name") link=parse.select_one(".prog_name")
return {'title':link['title'],'href':("https://www.programme-tv.net"+link['href'])} response = urllib.request.urlopen(("https://www.programme-tv.net"+link['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
return {'title':link['title'],'href':("https://www.programme-tv.net"+link['href']),'casting':casting,'synopsis':synopsis,'img':img}
print(parse_emmission("https://www.programme-tv.net/rechercher?q=France+3")) print(parse_emmission("https://www.programme-tv.net/rechercher?q=France+3"))