stevazi/addon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

Migliorato support.match e sostituito ove usato

Browse Source 
- Fix Animeforce
 - Fix AnimeSubITA
This commit is contained in:
Alhaziel
2020-01-15 18:44:03 +01:00
parent 89cbb8ae12
commit fce3bf2590
21 changed files with 271 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files
channels/animeforce.py
+91 -52
View File
@@ -3,14 +3,11 @@
# Canale per AnimeForce # Canale per AnimeForce
# ------------------------------------------------------------ # ------------------------------------------------------------
from servers.decrypters import adfly
from core import support from core import support
host = support.config.get_channel_url() host = support.config.get_channel_url()
IDIOMAS = {'Italiano': 'IT'} list_servers = ['directo', 'vvvvid']
list_language = IDIOMAS.values()
list_servers = ['directo', 'openload', 'vvvvid']
list_quality = ['default'] list_quality = ['default']
@@ -45,47 +42,40 @@ def newest(categoria):
return itemlist return itemlist
@support.scrape
def search(item, texto): def search(item, texto):
# debug = True support.log(texto)
search = texto item.args = 'noorder'
item.url = host + '/?s=' + texto + '&cat=6010'
item.contentType = 'tvshow' item.contentType = 'tvshow'
patron = r'<a href="(?P<url>[^"]+)">\s*<strong[^>]+>(?P<title>[^<]+)<' try:
action = 'episodios' return peliculas(item)
return locals() # Continua la ricerca in caso di errore
except:
import sys
for line in sys.exc_info():
support.logger.error("%s" % line)
return []
@support.scrape @support.scrape
def peliculas(item): def peliculas(item):
anime = True anime = True
action = 'episodios' action = 'episodios'
if not item.args:
if item.args == 'newest': pagination = ''
patron = r'<a href="(?P<url>[^"]+)">\s*<img src="(?P<thumb>[^"]+)" alt="(?P<title>.*?)(?: Sub| sub| SUB|")' patron = r'<a\s*href="(?P<url>[^"]+)"\s*title="(?P<title>[^"]+)">'
action = 'findvideos'
elif item.args == 'last':
patron = r'<a href="(?P<url>[^"]+)">\s*<img src="(?P<thumb>[^"]+)" alt="(?P<title>.*?)(?: Sub| sub| SUB|")'
elif item.args == 'corso': elif item.args == 'corso':
pagination = '' pagination = ''
patron = r'<strong><a href="(?P<url>[^"]+)">(?P<title>.*?) [Ss][Uu][Bb]' patron = r'<strong><a href="(?P<url>[^"]+)">(?P<title>.*?) [Ss][Uu][Bb]'
else: else:
pagination = '' patron = r'<a href="(?P<url>[^"]+)"[^>]+>\s*<img src="(?P<thumb>[^"]+)" alt="(?P<title>.*?)(?: Sub| sub| SUB|")'
patron = r'<a href="(?P<url>[^"]+)">\s*<strong[^>]+>(?P<title>[^<]+)<'
if item.args == 'newest': item.action = 'findvideos'
def itemHook(item): def itemHook(item):
if 'sub-ita' in item.url: if 'sub-ita' in item.url:
if item.args != 'newest': item.title = item.title + support.typo('Sub-ITA','_ [] color kod') if item.args != 'newest': item.title = item.title + support.typo('Sub-ITA','_ [] color kod')
item.contentLanguage = 'Sub-ITA' item.contentLanguage = 'Sub-ITA'
if item.args == 'newest':
url = support.match(item, '<a href="([^"]+)" title="[^"]+" target="[^"]+" class="btn', headers=headers)[0]
item.url = url[0] if url else ''
delete = support.scrapertools.find_single_match(item.fulltitle, r'( Episodi.*)')
episode = support.scrapertools.find_single_match(item.title, r'Episodi(?:o)? (?:\d+÷)?(\d+)')
item.title = support.typo(episode + ' - ','bold') + item.title.replace(delete,'')
item.fulltitle = item.show = item.title.replace(delete,'')
item.episode = episode
return item return item
return locals() return locals()
@@ -94,9 +84,15 @@ def peliculas(item):
@support.scrape @support.scrape
def episodios(item): def episodios(item):
anime = True anime = True
patron = r'<td style[^>]+>\s*.*?(?:<span[^>]+)?<strong>(?P<title>[^<]+)<\/strong>.*?<td style[^>]+>\s*<a href="(?P<url>[^"]+)"[^>]+>' data = support.match(item, headers=headers).data
if '<h6>Streaming</h6>' in data:
patron = r'<td style[^>]+>\s*.*?(?:<span[^>]+)?<strong>(?P<title>[^<]+)<\/strong>.*?<td style[^>]+>\s*<a href="(?P<url>[^"]+)"[^>]+>'
else:
patron = r'<a\s*href="(?P<url>[^"]+)"\s*title="(?P<title>[^"]+)"\s*class="btn btn-dark mb-1">'
def itemHook(item): def itemHook(item):
item.url = item.url.replace(host, '') support.log(item)
if item.url.startswith('//'): item.url= 'https:' + item.url
elif item.url.startswith('/'): item.url= 'https:/' + item.url
return item return item
action = 'findvideos' action = 'findvideos'
return locals() return locals()
@@ -104,38 +100,81 @@ def episodios(item):
def findvideos(item): def findvideos(item):
support.log(item) support.log(item)
# try:
# from urlparse import urljoin
# except:
# from urllib.parse import urljoin
# support.dbg()
itemlist = [] itemlist = []
if item.episode:
from lib import unshortenit
url, c = unshortenit.unshorten(item.url)
url = support.match(item, r'<a href="([^"]+)"[^>]*>', patronBlock=r'Episodio %s(.*?)</tr>' % item.episode ,url=url)[0]
item.url = url[0] if url else ''
if 'vvvvid' in item.url: if 'vvvvid' in item.url:
item.action = 'play' import requests
itemlist.append(item) from lib import vvvvid_decoder
if support.match(item.url, string=True, patron=r'(\d+/\d+)').match:
item.action = 'play'
itemlist.append(item)
else:
# VVVVID vars
vvvvid_host = 'https://www.vvvvid.it/vvvvid/ondemand/'
vvvvid_headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:62.0) Gecko/20100101 Firefox/62.0'}
if 'http' not in item.url: # VVVVID session
if '//' in item.url[:2]: current_session = requests.Session()
item.url = 'http:' + item.url login_page = 'https://www.vvvvid.it/user/login'
elif host not in item.url: conn_id = current_session.get(login_page, headers=vvvvid_headers).json()['data']['conn_id']
item.url = host + item.url payload = {'conn_id': conn_id}
# collect parameters
show_id = support.match(item.url, string=True, patron=r'(\d+)').match
ep_number = support.match(item.title, patron=r'(\d+)').match
json_file = current_session.get(vvvvid_host + show_id + '/seasons/', headers=vvvvid_headers, params=payload).json()
season_id = str(json_file['data'][0]['season_id'])
json_file = current_session.get(vvvvid_host + show_id + '/season/' + season_id +'/', headers=vvvvid_headers, params=payload).json()
# select the correct episode
for episode in json_file['data']:
support.log('Number',int(episode['number']),int(ep_number))
if int(episode['number']) == int(ep_number):
url = vvvvid_decoder.dec_ei(episode['embed_info'] or episode['embed_info'])
if 'youtube' in url: item.url = url
item.url = url.replace('manifest.f4m','master.m3u8').replace('http://','https://').replace('/z/','/i/')
if 'https' not in item.url:
url = support.match(item, url='https://or01.top-ix.org/videomg/_definst_/mp4:' + item.url + '/playlist.m3u')[1]
url = url.split()[-1]
itemlist.append(
support.Item(action= 'play',
url= 'https://or01.top-ix.org/videomg/_definst_/mp4:' + item.url + '/' + url,
server= 'directo'))
elif 'adf.ly' in item.url:
from servers.decrypters import adfly
url = adfly.get_long_url(item.url)
if 'adf.ly' in item.url:
item.url = adfly.get_long_url(item.url)
elif 'bit.ly' in item.url: elif 'bit.ly' in item.url:
item.url = support.httptools.downloadpage(item.url, only_headers=True, follow_redirects=False).headers.get("location") url = support.httptools.downloadpage(item.url, only_headers=True, follow_redirects=False).headers.get("location")
else:
url = host
for u in item.url.split('/'):
# support.log(i)
if u and 'animeforce' not in u and 'http' not in u:
url += '/' + u
if 'php?' in url:
url = support.httptools.downloadpage(url, only_headers=True, follow_redirects=False).headers.get("location")
url = support.match(url, patron=r'class="button"><a href=(?:")?([^" ]+)', headers=headers).match
else:
url = support.match(url, patron=[r'<source src=(?:")?([^" ]+)',r'name="_wp_http_referer" value="([^"]+)"']).match
if url.startswith('//'): url = 'https:' + url
elif url.startswith('/'): url = 'https:/' + url
matches = support.match(item, r'button"><a href="([^"]+)"')[0]
for video in matches:
itemlist.append( itemlist.append(
support.Item(channel=item.channel, support.Item(channel=item.channel,
action="play", action="play",
title='diretto', title='Diretto',
url=video, url=url,
server='directo')) server='directo'))
return support.server(item, itemlist=itemlist) return support.server(item, itemlist=itemlist)
channels/animeleggendari.py
+3 -3
View File
@@ -74,7 +74,7 @@ def peliculas(item):
@support.scrape @support.scrape
def episodios(item): def episodios(item):
data = support.match(item, headers=headers)[1] data = support.match(item, headers=headers).data
if not any(x in data for x in ['Lista Episodi', 'Movie Parte']): if not any(x in data for x in ['Lista Episodi', 'Movie Parte']):
support.log('NOT IN DATA') support.log('NOT IN DATA')
patron = r'(?:iframe src|str)="(?P<url>[^"]+)"' patron = r'(?:iframe src|str)="(?P<url>[^"]+)"'
@@ -107,7 +107,7 @@ def episodios(item):
return locals() return locals()
def check(item): def check(item):
data = support.match(item, headers=headers)[1] data = support.match(item, headers=headers).data
if 'Lista Episodi' not in data: if 'Lista Episodi' not in data:
item.data = data item.data = data
return findvideos(item) return findvideos(item)
@@ -120,7 +120,7 @@ def findvideos(item):
if item.data: if item.data:
data = item.data data = item.data
else: else:
matches = support.match(item, '(?:str="([^"]+)"|iframe src="([^"]+)")')[0] matches = support.match(item, patron=r'(?:str="([^"]+)"|iframe src="([^"]+)")').matches
data = '' data = ''
if matches: if matches:
for match in matches: for match in matches:
channels/animesaturn.py
+6 -7
View File
@@ -10,8 +10,7 @@ __channel__ = "animesaturn"
host = support.config.get_setting("channel_host", __channel__) host = support.config.get_setting("channel_host", __channel__)
headers={'X-Requested-With': 'XMLHttpRequest'} headers={'X-Requested-With': 'XMLHttpRequest'}
IDIOMAS = {'Italiano': 'ITA'}
list_language = IDIOMAS.values()
list_servers = ['openload', 'fembed', 'animeworld'] list_servers = ['openload', 'fembed', 'animeworld']
list_quality = ['default', '480p', '720p', '1080p'] list_quality = ['default', '480p', '720p', '1080p']
@@ -67,7 +66,7 @@ def peliculas(item):
deflang= 'Sub-ITA' deflang= 'Sub-ITA'
if item.args == 'updated': if item.args == 'updated':
post = "page=" + str(item.page if item.page else 1) if item.page > 1 else None post = "page=" + str(item.page if item.page else 1) if item.page > 1 else None
page, data = support.match(item, r'data-page="(\d+)" title="Next">', post=post, headers=headers) page= support.match(item, patron=r'data-page="(\d+)" title="Next">', post=post, headers=headers).match
patron = r'<img alt="[^"]+" src="(?P<thumb>[^"]+)" [^>]+></div></a>\s*<a href="(?P<url>[^"]+)"><div class="testo">(?P<title>[^\(<]+)(?:(?P<lang>\(([^\)]+)\)))?</div></a>\s*<a href="[^"]+"><div class="testo2">[^\d]+(?P<episode>\d+)</div></a>' patron = r'<img alt="[^"]+" src="(?P<thumb>[^"]+)" [^>]+></div></a>\s*<a href="(?P<url>[^"]+)"><div class="testo">(?P<title>[^\(<]+)(?:(?P<lang>\(([^\)]+)\)))?</div></a>\s*<a href="[^"]+"><div class="testo2">[^\d]+(?P<episode>\d+)</div></a>'
if page: nextpage = page if page: nextpage = page
item.contentType='episode' item.contentType='episode'
@@ -85,8 +84,8 @@ def peliculas(item):
def check(item): def check(item):
movie, data = support.match(item, r'Episodi:</b> (\d*) Movie') movie = support.match(item, patron=r'Episodi:</b> (\d*) Movie')
anime_id = support.match(data, r'anime_id=(\d+)')[0][0] anime_id = support.match(movie.data, patron=r'anime_id=(\d+)').match
item.url = host + "/loading_anime?anime_id=" + anime_id item.url = host + "/loading_anime?anime_id=" + anime_id
if movie: if movie:
item.contentType = 'movie' item.contentType = 'movie'
@@ -108,9 +107,9 @@ def episodios(item):
def findvideos(item): def findvideos(item):
support.log() support.log()
itemlist = [] itemlist = []
urls = support.match(item, r'<a href="([^"]+)"><div class="downloadestreaming">', headers=headers)[0] urls = support.match(item, patron=r'<a href="([^"]+)"><div class="downloadestreaming">', headers=headers, debug=True).matches
if urls: if urls:
links = support.match(item, r'(?:<source type="[^"]+"\s*src=|file:\s*)"([^"]+)"', url=urls[0], headers=headers)[0] links = support.match(urls[0], patron=r'(?:<source type="[^"]+"\s*src=|file:\s*)"([^"]+)"', headers=headers).matches
for link in links: for link in links:
itemlist.append( itemlist.append(
support.Item(channel=item.channel, support.Item(channel=item.channel,
channels/animesubita.py
+23 -29
View File
@@ -34,7 +34,7 @@ def newest(categoria):
if itemlist[-1].action == "ultimiep": if itemlist[-1].action == "ultimiep":
itemlist.pop() itemlist.pop()
# Continua l'esecuzione in caso di errore # Continua l'esecuzione in caso di errore
except: except:
import sys import sys
for line in sys.exc_info(): for line in sys.exc_info():
@@ -50,7 +50,7 @@ def search(item, texto):
item.args = 'alt' item.args = 'alt'
try: try:
return peliculas(item) return peliculas(item)
# Continua la ricerca in caso di errore # Continua la ricerca in caso di errore
except: except:
import sys import sys
for line in sys.exc_info(): for line in sys.exc_info():
@@ -67,10 +67,9 @@ def genres(item):
@support.scrape @support.scrape
def peliculas(item): def peliculas(item):
anime = True anime = True
if item.args == 'updated': if item.args == 'updated':
#patron = r'<div class="post-thumbnail">\s*<a href="(?P<url>[^"]+)" title="(?P<title>.*?)\s*(?P<episode>Episodio \d+)[^"]+"[^>]*>\s*<img[^src]+src="(?P<thumb>[^"]+)"'
patron = r'<div class="post-thumbnail">\s*<a href="(?P<url>[^"]+)" title="(?P<title>.*?)\s*Episodio (?P<episode>\d+) (?P<lang>[a-zA-Z-\s]+)[^"]*"> <img[^src]+src="(?P<thumb>[^"]+)"' patron = r'<div class="post-thumbnail">\s*<a href="(?P<url>[^"]+)" title="(?P<title>.*?)\s*Episodio (?P<episode>\d+) (?P<lang>[a-zA-Z-\s]+)[^"]*"> <img[^src]+src="(?P<thumb>[^"]+)"'
patronNext = r'<link rel="next" href="([^"]+)"\s*/>' patronNext = r'<link rel="next" href="([^"]+)"\s*/>'
action = 'findvideos' action = 'findvideos'
@@ -98,32 +97,27 @@ def findvideos(item):
itemlist = [] itemlist = []
if item.args == 'updated': if item.args == 'updated':
ep = support.match(item.fulltitle,r'(Episodio\s*\d+)')[0][0] ep = support.match(item.fulltitle, patron=r'(\d+)').match
item.url = support.re.sub(r'episodio-\d+-|oav-\d+-', '',item.url) item.url = support.re.sub(r'episodio-\d+-|oav-\d+-'+ep, '',item.url)
if 'streaming' not in item.url: item.url = item.url.replace('sub-ita','sub-ita-streaming') if 'streaming' not in item.url: item.url = item.url.replace('sub-ita','sub-ita-streaming')
item.url = support.match(item, r'<a href="([^"]+)"[^>]+>', ep + '(.*?)</tr>', )[0][0] item.url = support.match(item, patron= ep + r'[^>]+>[^>]+>[^>]+><a href="([^"]+)"').match
urls = support.match(item.url, r'(episodio\d*.php.*)')[0] # post
for url in urls: url = host + '/' + support.match(item.url, patron=r'(episodio\d*.php.*?)"').match.replace('%3F','?').replace('%3D','=')
url = host + '/' + url headers['Referer'] = url
headers['Referer'] = url cookies = ""
data = support.match(item, headers=headers, url=url)[1] matches = support.re.compile('(.%s.*?)\n' % host.replace("http://", "").replace("www.", ""), support.re.DOTALL).findall(support.config.get_cookie_data())
cookies = "" for cookie in matches:
matches = support.re.compile('(.%s.*?)\n' % host.replace("http://", "").replace("www.", ""), support.re.DOTALL).findall(support.config.get_cookie_data()) cookies += cookie.split('\t')[5] + "=" + cookie.split('\t')[6] + ";"
for cookie in matches: headers['Cookie'] = cookies[:-1]
cookies += cookie.split('\t')[5] + "=" + cookie.split('\t')[6] + ";"
headers['Cookie'] = cookies[:-1] url = support.match(url, patron=r'<source src="([^"]+)"[^>]+>').match
url = support.match(data, r'<source src="([^"]+)"[^>]+>')[0][0] + '|' + support.urllib.urlencode(headers)
itemlist.append(
support.Item(channel=item.channel,
action="play",
title='diretto',
quality='',
url=url,
server='directo',
fulltitle=item.fulltitle,
show=item.show))
return support.server(item,url,itemlist) itemlist.append(
support.Item(channel=item.channel,
action="play",
title='Diretto',
url=url + '|' + support.urllib.urlencode(headers),
server='directo'))
return support.server(item,itemlist=itemlist)
channels/animetubeita.py
+2 -2
View File
@@ -98,11 +98,11 @@ def episodios(item):
def findvideos(item): def findvideos(item):
itemlist=[] itemlist=[]
if item.args == 'last': if item.args == 'last':
match = support.match(item, r'href="(?P<url>[^"]+)"[^>]+><strong>DOWNLOAD &amp; STREAMING</strong>', url=item.url)[0] match = support.match(item, patron=r'href="(?P<url>[^"]+)"[^>]+><strong>DOWNLOAD &amp; STREAMING</strong>').match
if match: if match:
patronBlock = r'<h6>Episodio</h6>(?P<block>.*?)(?:<!--|</table>)' patronBlock = r'<h6>Episodio</h6>(?P<block>.*?)(?:<!--|</table>)'
patron = r'<a href="http://link\.animetubeita\.com/2361078/(?P<url>[^"]+)"' patron = r'<a href="http://link\.animetubeita\.com/2361078/(?P<url>[^"]+)"'
match = support.match(item, patron, patronBlock, headers, match[0])[0] match = support.match(match, patron=patron, patronBlock=patronBlock, headers=headers).match
else: return itemlist else: return itemlist
if match: item.url = match[-1] if match: item.url = match[-1]
channels/animeworld.py
+9 -7
View File
@@ -34,7 +34,7 @@ def mainlist(item):
def genres(item): def genres(item):
support.log() support.log()
itemlist = [] itemlist = []
matches = support.match(item, r'<input.*?name="([^"]+)" value="([^"]+)"\s*>[^>]+>([^<]+)<\/label>' , r'<button class="btn btn-sm btn-default dropdown-toggle" data-toggle="dropdown"> Generi <span.[^>]+>(.*?)</ul>', headers=headers)[0] matches = support.match(item, patron=r'<input.*?name="([^"]+)" value="([^"]+)"\s*>[^>]+>([^<]+)<\/label>' , patronBlock=r'<button class="btn btn-sm btn-default dropdown-toggle" data-toggle="dropdown"> Generi <span.[^>]+>(.*?)</ul>', headers=headers).matches
for name, value, title in matches: for name, value, title in matches:
support.menuItem(itemlist, __channel__, support.typo(title, 'bold'), 'peliculas', host + '/filter?' + name + '=' + value + '&sort=' + order(), 'tvshow', args='sub') support.menuItem(itemlist, __channel__, support.typo(title, 'bold'), 'peliculas', host + '/filter?' + name + '=' + value + '&sort=' + order(), 'tvshow', args='sub')
return itemlist return itemlist
@@ -44,7 +44,7 @@ def build_menu(item):
support.log() support.log()
itemlist = [] itemlist = []
support.menuItem(itemlist, __channel__, 'Tutti bold', 'peliculas', item.url , 'tvshow' , args=item.args) support.menuItem(itemlist, __channel__, 'Tutti bold', 'peliculas', item.url , 'tvshow' , args=item.args)
matches = support.match(item,r'<button class="btn btn-sm btn-default dropdown-toggle" data-toggle="dropdown"> (.*?) <span.[^>]+>(.*?)</ul>',r'<form class="filters.*?>(.*?)</form>', headers=headers)[0] matches = support.match(item, patron=r'<button class="btn btn-sm btn-default dropdown-toggle" data-toggle="dropdown"> (.*?) <span.[^>]+>(.*?)</ul>', patronBlock=r'<form class="filters.*?>(.*?)</form>', headers=headers).matches
for title, html in matches: for title, html in matches:
if title not in 'Lingua Ordine': if title not in 'Lingua Ordine':
support.menuItem(itemlist, __channel__, title + ' submenu bold', 'build_sub_menu', html, 'tvshow', args=item.args) support.menuItem(itemlist, __channel__, title + ' submenu bold', 'build_sub_menu', html, 'tvshow', args=item.args)
@@ -127,7 +127,7 @@ def peliculas(item):
def episodios(item): def episodios(item):
anime=True anime=True
pagination = 50 pagination = 50
data = support.match(item, headers=headers)[1] data = support.match(item, headers=headers).data
if 'VVVVID' in data: patronBlock= r'<div class="server\s*active\s*"(?P<block>.*?)</ul>' if 'VVVVID' in data: patronBlock= r'<div class="server\s*active\s*"(?P<block>.*?)</ul>'
else: patronBlock= r'server active(?P<block>.*?)server hidden ' else: patronBlock= r'server active(?P<block>.*?)server hidden '
patron = r'<li><a [^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+" href="(?P<url>[^"]+)"[^>]+>(?P<episode>[^<]+)<' patron = r'<li><a [^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+" href="(?P<url>[^"]+)"[^>]+>(?P<episode>[^<]+)<'
@@ -143,9 +143,11 @@ def findvideos(item):
import time import time
support.log(item) support.log(item)
itemlist = [] itemlist = []
matches, data = support.match(item, r'class="tab.*?data-name="([0-9]+)">', headers=headers) matches = support.match(item, patron=r'class="tab.*?data-name="([0-9]+)">', headers=headers)
data = matches.data
matches = matches.matches
videoData = '' videoData = ''
for serverid in matches: for serverid in matches:
if not item.number: item.number = support.scrapertools.find_single_match(item.title, r'(\d+) -') if not item.number: item.number = support.scrapertools.find_single_match(item.title, r'(\d+) -')
block = support.scrapertools.find_multiple_matches(data, 'data-id="' + serverid + '">(.*?)<div class="server') block = support.scrapertools.find_multiple_matches(data, 'data-id="' + serverid + '">(.*?)<div class="server')
@@ -153,7 +155,7 @@ def findvideos(item):
support.log('ID= ',serverid) support.log('ID= ',serverid)
if id: if id:
if serverid == '26': if serverid == '26':
matches = support.match(item, r'<a href="([^"]+)"', url='%s/ajax/episode/serverPlayer?id=%s' % (host, item.url.split('/')[-1]))[0] matches = support.match('%s/ajax/episode/serverPlayer?id=%s' % (host, item.url.split('/')[-1]), patron=r'<a href="([^"]+)"', ).matches
for url in matches: for url in matches:
videoData += '\n' + url videoData += '\n' + url
else: else:
@@ -162,7 +164,7 @@ def findvideos(item):
json = jsontools.load(dataJson) json = jsontools.load(dataJson)
support.log(json) support.log(json)
if 'keepsetsu' in json['grabber']: if 'keepsetsu' in json['grabber']:
matches = support.match(item, r'<iframe\s*src="([^"]+)"', url=json['grabber'])[0] matches = support.match(json['grabber'], patron=r'<iframe\s*src="([^"]+)"'),matches
for url in matches: for url in matches:
videoData += '\n' + url videoData += '\n' + url
else: else:
channels/casacinema.py
+3 -3
View File
@@ -39,7 +39,7 @@ def genres(item):
def select(item): def select(item):
item.data = support.match(item)[1] item.data = support.match(item).data
if 'continua con il video' in item.data.lower(): if 'continua con il video' in item.data.lower():
support.log('select = ### è un film ###') support.log('select = ### è un film ###')
item.contentType = 'movie' item.contentType = 'movie'
@@ -140,10 +140,10 @@ def episodios(item):
def findvideos(item): def findvideos(item):
if item.contentType != 'movie': if item.contentType != 'movie':
links = support.match(item.url, r'href="([^"]+)"')[0] links = support.match(item.url, patron=r'href="([^"]+)"').matches
else: else:
matchData = item.data if item.data else item matchData = item.data if item.data else item
links = support.match(matchData, r'(?:SRC|href)="([^"]+)"', patronBlock=r'<div class="col-md-10">(.+?)<div class="ads">')[0] links = support.match(matchData, patron=r'(?:SRC|href)="([^"]+)"', patronBlock=r'<div class="col-md-10">(.+?)<div class="ads">').matches
data = '' data = ''
from lib.unshortenit import unshorten_only from lib.unshortenit import unshorten_only
for link in links: for link in links:
channels/cb01anime.py
+6 -6
View File
@@ -59,7 +59,7 @@ def peliculas(item):
blacklist = Blacklist blacklist = Blacklist
item.contentType = 'tvshow' item.contentType = 'tvshow'
if item.args == 'newest': if item.args == 'newest':
data = support.match(item)[1] # data = support.match(item).data
patron = r'<div id="blockvids"><ul><li><a href="(?P<url>[^"]+)"[^>]+><img src="(?P<thumb>[^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(?P<title>[^\[]+)\[(?P<lang>[^\]]+)\]' patron = r'<div id="blockvids"><ul><li><a href="(?P<url>[^"]+)"[^>]+><img src="(?P<thumb>[^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(?P<title>[^\[]+)\[(?P<lang>[^\]]+)\]'
else: else:
patron = r'<div class="span4">\s*<a href="(?P<url>[^"]+)"><img src="(?P<thumb>[^"]+)"[^>]+><\/a>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+> <h1>(?P<title>[^<\[]+)(?:\[(?P<lang>[^\]]+)\])?</h1></a>.*?-->(?:.*?<br />)?\s*(?P<plot>[^<]+)' patron = r'<div class="span4">\s*<a href="(?P<url>[^"]+)"><img src="(?P<thumb>[^"]+)"[^>]+><\/a>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+> <h1>(?P<title>[^<\[]+)(?:\[(?P<lang>[^\]]+)\])?</h1></a>.*?-->(?:.*?<br />)?\s*(?P<plot>[^<]+)'
@@ -68,7 +68,7 @@ def peliculas(item):
return locals() return locals()
def check(item): def check(item):
item.url = support.match(item,r'(?:<p>|/>)(.*?)(?:<br|</td>|</p>)', r'Streaming:(.*?)</tr>')[0] item.url = support.match(item, patron=r'(?:<p>|/>)(.*?)(?:<br|</td>|</p>)', patronBlock=r'Streaming:(.*?)</tr>').matches
if 'Episodio' in str(item.url): if 'Episodio' in str(item.url):
item.contentType = 'tvshow' item.contentType = 'tvshow'
return episodios(item) return episodios(item)
@@ -87,14 +87,14 @@ def episodios(item):
sp = 0 sp = 0
for match in item.url: for match in item.url:
if 'stagione' in match.lower(): if 'stagione' in match.lower():
find_season = support.match(match, r'Stagione\s*(\d+)')[0] find_season = support.match(match, patron=r'Stagione\s*(\d+)').match
season = int(find_season[0]) if find_season else season + 1 if 'prima' not in match.lower() else season season = int(find_season) if find_season else season + 1 if 'prima' not in match.lower() else season
else: else:
try: title = support.match(match,'<a[^>]+>([^<]+)</a>')[0][0] try: title = support.match(match, patron=r'<a[^>]+>([^<]+)</a>').match
except: title = '' except: title = ''
if title: if title:
if 'episodio' in title.lower(): if 'episodio' in title.lower():
ep = support.match(match, r'Episodio ((?:\d+.\d|\d+|\D+))')[0][0] ep = support.match(match, patron=r'Episodio ((?:\d+.\d|\d+|\D+))').match
check = ep.isdigit() check = ep.isdigit()
if check or '.' in ep: if check or '.' in ep:
if '.' in ep: if '.' in ep:
channels/cinetecadibologna.py
+1 -1
View File
@@ -73,7 +73,7 @@ def findvideos(item):
support.log() support.log()
itemlist = [] itemlist = []
matches = support.match(item, 'filename: "(.*?)"')[0] matches = support.match(item, patron=r'filename: "(.*?)"').matches
for url in matches: for url in matches:
itemlist.append( itemlist.append(
channels/dreamsub.py
+16 -9
View File
@@ -31,10 +31,11 @@ def menu(item):
action = 'peliculas' action = 'peliculas'
patronBlock = r'<div class="filter-header"><b>%s</b>(?P<block>.*?)<div class="filter-box">' % item.args patronBlock = r'<div class="filter-header"><b>%s</b>(?P<block>.*?)<div class="filter-box">' % item.args
patronMenu = r'<a class="[^"]+" data-state="[^"]+" (?P<url>[^>]+)>[^>]+></i>[^>]+></i>[^>]+></i>(?P<title>[^>]+)</a>' patronMenu = r'<a class="[^"]+" data-state="[^"]+" (?P<other>[^>]+)>[^>]+></i>[^>]+></i>[^>]+></i>(?P<title>[^>]+)</a>'
def itemHook(item): def itemHook(item):
for Type, ID in support.match(item.url, r'data-type="([^"]+)" data-id="([^"]+)"')[0]: support.log(item.type)
for Type, ID in support.match(item.other, patron=r'data-type="([^"]+)" data-id="([^"]+)"').matches:
item.url = host + '/search?' + Type + 'Y=' + ID item.url = host + '/search?' + Type + 'Y=' + ID
return item return item
return locals() return locals()
@@ -110,28 +111,34 @@ def findvideos(item):
itemlist = [] itemlist = []
support.log() support.log()
matches, data = support.match(item, r'<a href="([^"]+)"', r'<div style="white-space: (.*?)<div id="main-content"') matches = support.match(item, patron=r'<a href="([^"]+)"', patronBlock=r'<div style="white-space: (.*?)<div id="main-content"')
if not matches: if not matches.matches:
item.data = data item.data = matches.data
item.contentType = 'tvshow' item.contentType = 'tvshow'
return episodios(item) return episodios(item)
matches.sort() # matches.matches.sort()
for url in matches: for url in matches.matches:
lang = url.split('/')[-2] lang = url.split('/')[-2]
if 'ita' in lang.lower():
language = 'ITA'
if 'sub' in lang.lower():
language = 'Sub-' + language
quality = url.split('/')[-1] quality = url.split('/')[-1]
itemlist.append( itemlist.append(
support.Item(channel=item.channel, support.Item(channel=item.channel,
action="play", action="play",
contentType=item.contentType, contentType=item.contentType,
title=lang, title=language,
url=url, url=url,
contentLanguage = lang, contentLanguage = language,
quality = quality, quality = quality,
order = quality.replace('p','').zfill(4),
server='directo', server='directo',
)) ))
itemlist.sort(key=lambda x: (x.title, x.order), reverse=False)
return support.server(item, itemlist=itemlist) return support.server(item, itemlist=itemlist)
channels/fastsubita.py
+4 -2
View File
@@ -145,7 +145,9 @@ def findvideos(item):
itemlist = [] itemlist = []
patronBlock = '<div class="entry-content">(?P<block>.*)<footer class="entry-footer">' patronBlock = '<div class="entry-content">(?P<block>.*)<footer class="entry-footer">'
patron = r'<a href="([^"]+)">' patron = r'<a href="([^"]+)">'
matches, data = support.match(item, patron, patronBlock, headers) html = support.match(item, patron=patron, patronBlock=patronBlock, headers=headers)
matches = html.matches
data= html.data
if item.args != 'episodios': if item.args != 'episodios':
item.infoLabels['mediatype'] = 'episode' item.infoLabels['mediatype'] = 'episode'
@@ -156,7 +158,7 @@ def findvideos(item):
itemlist += support.server(item, data) itemlist += support.server(item, data)
data = httptools.downloadpage(item.url).data data = support.match(item.url).data
patron = r'>Posted in <a href="https?://fastsubita.com/serietv/([^/]+)/(?:[^"]+)?"' patron = r'>Posted in <a href="https?://fastsubita.com/serietv/([^/]+)/(?:[^"]+)?"'
series = scrapertools.find_single_match(data, patron) series = scrapertools.find_single_match(data, patron)
titles = support.typo(series.upper().replace('-', ' '), 'bold color kod') titles = support.typo(series.upper().replace('-', ' '), 'bold color kod')
channels/piratestreaming.py
+1 -1
View File
@@ -99,7 +99,7 @@ def findvideos(item):
if item.contentType == 'episode': if item.contentType == 'episode':
data = item.url data = item.url
else: else:
data = support.match(item)[1] data = support.match(item).data
if 'link-episode' in data: if 'link-episode' in data:
item.data = data item.data = data
return episodios(item) return episodios(item)
channels/seriehd.py
+3 -3
View File
@@ -34,11 +34,11 @@ def peliculas(item):
@support.scrape @support.scrape
def episodios(item): def episodios(item):
data ='' data =''
url = support.match(item, patronBlock=r'<iframe width=".+?" height=".+?" src="([^"]+)" allowfullscreen frameborder="0">')[1] url = support.match(item, patron=r'<iframe width=".+?" height=".+?" src="([^"]+)" allowfullscreen frameborder="0">').match
seasons = support.match(item, r'<a href="([^"]+)">(\d+)<', r'<h3>STAGIONE</h3><ul>(.*?)</ul>', headers, url)[0] seasons = support.match(url, patron=r'<a href="([^"]+)">(\d+)<', patronBlock=r'<h3>STAGIONE</h3><ul>(.*?)</ul>', headers=headers).matches
for season_url, season in seasons: for season_url, season in seasons:
season_url = support.urlparse.urljoin(url, season_url) season_url = support.urlparse.urljoin(url, season_url)
episodes = support.match(item, r'<a href="([^"]+)">(\d+)<', '<h3>EPISODIO</h3><ul>(.*?)</ul>', headers, season_url)[0] episodes = support.match(season_url, patron=r'<a href="([^"]+)">(\d+)<', patronBlock=r'<h3>EPISODIO</h3><ul>(.*?)</ul>', headers=headers).matches
for episode_url, episode in episodes: for episode_url, episode in episodes:
episode_url = support.urlparse.urljoin(url, episode_url) episode_url = support.urlparse.urljoin(url, episode_url)
title = season + "x" + episode.zfill(2) + ' - ' + item.fulltitle title = season + "x" + episode.zfill(2) + ' - ' + item.fulltitle
channels/serietvsubita.py
+9 -5
View File
@@ -108,7 +108,7 @@ def lista_serie(item):
else: else:
# Extrae las entradas # Extrae las entradas
patron = r'<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>' patron = r'<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>'
matches = support.match(item, patron, headers=headers)[0] matches = support.match(item, patron=patron, headers=headers).matches
for i, (scrapedurl, scrapedtitle) in enumerate(matches): for i, (scrapedurl, scrapedtitle) in enumerate(matches):
scrapedplot = "" scrapedplot = ""
scrapedthumbnail = "" scrapedthumbnail = ""
@@ -148,7 +148,9 @@ def episodios(item, itemlist=[]):
patron += r'<p><a href="([^"]+)">' patron += r'<p><a href="([^"]+)">'
matches, data = support.match(item, patron, headers=headers) html = support.match(item, patron=patron, headers=headers)
matches = html.matches
data = html.data
for scrapedurl, scrapedtitle, scrapedthumbnail in matches: for scrapedurl, scrapedtitle, scrapedthumbnail in matches:
scrapedplot = "" scrapedplot = ""
@@ -224,7 +226,9 @@ def peliculas_tv(item):
patron = '<div class="post-meta">\s*<a href="([^"]+)"\s*title="([^"]+)"\s*class=".*?"></a>' patron = '<div class="post-meta">\s*<a href="([^"]+)"\s*title="([^"]+)"\s*class=".*?"></a>'
matches, data = support.match(item, patron, headers=headers) html = support.match(item, patron=patron, headers=headers)
matches = html.matches
data = html.data
for scrapedurl, scrapedtitle in matches: for scrapedurl, scrapedtitle in matches:
if scrapedtitle in ["FACEBOOK", "RAPIDGATOR", "WELCOME!"]: if scrapedtitle in ["FACEBOOK", "RAPIDGATOR", "WELCOME!"]:
@@ -298,7 +302,7 @@ def search(item, texto):
itemlist = [] itemlist = []
patron = '<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>' patron = '<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>'
matches = support.match(item, patron, headers=headers)[0] matches = support.match(item, patron=patron, headers=headers).matches
for i, (scrapedurl, scrapedtitle) in enumerate(matches): for i, (scrapedurl, scrapedtitle) in enumerate(matches):
if texto.upper() in scrapedtitle.upper(): if texto.upper() in scrapedtitle.upper():
scrapedthumbnail = "" scrapedthumbnail = ""
@@ -333,7 +337,7 @@ def list_az(item):
alphabet = dict() alphabet = dict()
patron = '<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>' patron = '<li class="cat-item cat-item-\d+"><a href="([^"]+)"\s?>([^<]+)</a>'
matches = support.match(item, patron, headers=headers)[0] matches = support.match(item, patron=patron, headers=headers).matches
for i, (scrapedurl, scrapedtitle) in enumerate(matches): for i, (scrapedurl, scrapedtitle) in enumerate(matches):
letter = scrapedtitle[0].upper() letter = scrapedtitle[0].upper()
if letter not in alphabet: if letter not in alphabet:
channels/serietvu.py
+1 -1
View File
@@ -50,7 +50,7 @@ def peliculas(item):
@support.scrape @support.scrape
def episodios(item): def episodios(item):
seasons, data = support.match(item, r'<option value="(\d+)"[^>]*>\D+(\d+)') seasons = support.match(item, patron=r'<option value="(\d+)"[^>]*>\D+(\d+)').matches
patronBlock = r'</select><div style="clear:both"></div></h2>(?P<block>.*?)<div id="trailer" class="tab">' patronBlock = r'</select><div style="clear:both"></div></h2>(?P<block>.*?)<div id="trailer" class="tab">'
patron = r'(?:<div class="list (?:active)?" data-id="(?P<season>\d+)">[^>]+>)?\s*<a data-id="(?P<episode>\d+)(?:[ ](?P<lang>[SuUbBiItTaA\-]+))?"(?P<url>[^>]+)>[^>]+>[^>]+>(?P<title>.+?)(?:\sSub-ITA)?<' patron = r'(?:<div class="list (?:active)?" data-id="(?P<season>\d+)">[^>]+>)?\s*<a data-id="(?P<episode>\d+)(?:[ ](?P<lang>[SuUbBiItTaA\-]+))?"(?P<url>[^>]+)>[^>]+>[^>]+>(?P<title>.+?)(?:\sSub-ITA)?<'
def itemHook(item): def itemHook(item):
channels/streamtime.py
+3 -3
View File
@@ -149,15 +149,15 @@ def findvideos(item):
id = item.args['id'] id = item.args['id']
season = str(item.args['season']) season = str(item.args['season'])
episode = str(item.args['episode']) episode = str(item.args['episode'])
res = support.match(item, 'src="([^"]+)"[^>]*></video>', url=url, headers=[['Referer', domain]]) res = support.match(url, patron='src="([^"]+)"[^>]*></video>', headers=[['Referer', domain]]).match
itemlist = [] itemlist = []
if res[0]: if res:
itemlist.append( itemlist.append(
Item(channel=item.channel, Item(channel=item.channel,
action="play", action="play",
title='contentful', title='contentful',
url=res[0][0], url=res,
server='directo', server='directo',
fulltitle=item.fulltitle, fulltitle=item.fulltitle,
thumbnail=item.thumbnail, thumbnail=item.thumbnail,
channels/tantifilm.py
+4 -4
View File
@@ -124,7 +124,7 @@ def anime(item):
log() log()
itemlist = [] itemlist = []
seasons = support.match(item, r'<div class="sp-body[^"]+">(.*?)<\/div>')[0] seasons = support.match(item, patron=r'<div class="sp-body[^"]+">(.*?)<\/div>').matches
for season in seasons: for season in seasons:
episodes = scrapertools.find_multiple_matches(season, r'<a.*?href="([^"]+)"[^>]+>([^<]+)<\/a>(.*?)<(:?br|\/p)') episodes = scrapertools.find_multiple_matches(season, r'<a.*?href="([^"]+)"[^>]+>([^<]+)<\/a>(.*?)<(:?br|\/p)')
for url, title, urls, none in episodes: for url, title, urls, none in episodes:
@@ -208,7 +208,7 @@ def newest(categoria):
item = Item() item = Item()
item.url = host +'/aggiornamenti/' item.url = host +'/aggiornamenti/'
matches = support.match(item, r'mediaWrapAlt recomended_videos"[^>]+>\s*<a href="([^"]+)" title="([^"]+)" rel="bookmark">\s*<img[^s]+src="([^"]+)"[^>]+>')[0] matches = support.match(item, patron=r'mediaWrapAlt recomended_videos"[^>]+>\s*<a href="([^"]+)" title="([^"]+)" rel="bookmark">\s*<img[^s]+src="([^"]+)"[^>]+>').matches
for url, title, thumb in matches: for url, title, thumb in matches:
title = scrapertools.decodeHtmlentities(title).replace("Permalink to ", "").replace("streaming", "") title = scrapertools.decodeHtmlentities(title).replace("Permalink to ", "").replace("streaming", "")
@@ -236,11 +236,11 @@ def findvideos(item):
## data = item.url ## data = item.url
## else: ## else:
## data = httptools.downloadpage(item.url, headers=headers).data ## data = httptools.downloadpage(item.url, headers=headers).data
data = httptools.downloadpage(item.url, headers=headers).data data = support.match(item.url, headers=headers).data
data = re.sub('\n|\t', ' ', data) data = re.sub('\n|\t', ' ', data)
data = re.sub(r'>\s+<', '> <', data) data = re.sub(r'>\s+<', '> <', data)
check = scrapertools.find_single_match(data, r'<div class="category-film">\s+<h3>\s+(.*?)\s+</h3>\s+</div>') check = support.match(data, patron=r'<div class="category-film">\s+<h3>\s+(.*?)\s+</h3>\s+</div>').match
if 'sub' in check.lower(): if 'sub' in check.lower():
item.contentLanguage = 'Sub-ITA' item.contentLanguage = 'Sub-ITA'
support.log("CHECK : ", check) support.log("CHECK : ", check)
channels/toonitalia.py
+1 -1
View File
@@ -104,7 +104,7 @@ def peliculas(item):
@support.scrape @support.scrape
def episodios(item): def episodios(item):
anime = True anime = True
data = support.match(item, headers=headers)[1] data = support.match(item, headers=headers).data
if 'https://vcrypt.net' in data: if 'https://vcrypt.net' in data:
patron = r'(?:<br /> |<p>)(?P<title>[^<]+)<a href="(?P<url>[^"]+)"' patron = r'(?:<br /> |<p>)(?P<title>[^<]+)<a href="(?P<url>[^"]+)"'
else: else:
channels/vvvvid.py
+3 -3
View File
@@ -131,7 +131,7 @@ def peliculas(item):
elif '=' in item.args: elif '=' in item.args:
json_file = current_session.get(item.url + 'channels', headers=headers, params=payload).json() json_file = current_session.get(item.url + 'channels', headers=headers, params=payload).json()
Filter = support.match(item.args,r'\?([^=]+)=')[0][0] Filter = support.match(item.args, patron=r'\?([^=]+)=').match
keys = [i[Filter] for i in json_file['data'] if Filter in i][0] keys = [i[Filter] for i in json_file['data'] if Filter in i][0]
for key in keys: for key in keys:
if key not in ['1','2']: if key not in ['1','2']:
@@ -162,7 +162,7 @@ def episodios(item):
for episode in episodes: for episode in episodes:
for key in episode: for key in episode:
if 'stagione' in key['title'].encode('utf8').lower(): if 'stagione' in key['title'].encode('utf8').lower():
match = support.match(key['title'].encode('utf8'), r'[Ss]tagione\s*(\d+) - [Ee]pisodio\s*(\d+)')[0][0] match = support.match(key['title'].encode('utf8'), patron=r'[Ss]tagione\s*(\d+) - [Ee]pisodio\s*(\d+)').match
title = match[0]+'x'+match[1] + ' - ' + item.fulltitle title = match[0]+'x'+match[1] + ' - ' + item.fulltitle
make_item = True make_item = True
elif int(key['season_id']) == int(season_id): elif int(key['season_id']) == int(season_id):
@@ -206,7 +206,7 @@ def findvideos(item):
if 'youtube' in url: item.url = url if 'youtube' in url: item.url = url
item.url = url.replace('manifest.f4m','master.m3u8').replace('http://','https://').replace('/z/','/i/') item.url = url.replace('manifest.f4m','master.m3u8').replace('http://','https://').replace('/z/','/i/')
if 'https' not in item.url: if 'https' not in item.url:
url = support.match(item, url='https://or01.top-ix.org/videomg/_definst_/mp4:' + item.url + '/playlist.m3u')[1] url = support.match('https://or01.top-ix.org/videomg/_definst_/mp4:' + item.url + '/playlist.m3u')
url = url.split()[-1] url = url.split()[-1]
itemlist.append( itemlist.append(
Item(action= 'play', Item(action= 'play',
core/support.py
+79 -18
View File
@@ -180,7 +180,7 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
if debug: if debug:
regexDbg(item, patron, headers, block) regexDbg(item, patron, headers, block)
known_keys = ['url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality', 'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang'] known_keys = ['url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality', 'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang', 'other']
# Legenda known_keys per i groups nei patron # Legenda known_keys per i groups nei patron
# known_keys = ['url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality', # known_keys = ['url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality',
# 'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang'] # 'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang']
@@ -301,7 +301,8 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
contentTitle= scraped['title'] if item.contentType or CT == 'movie' else '', contentTitle= scraped['title'] if item.contentType or CT == 'movie' else '',
contentLanguage = lang1, contentLanguage = lang1,
contentEpisodeNumber=episode if episode else '', contentEpisodeNumber=episode if episode else '',
news= item.news if item.news else '' news= item.news if item.news else '',
other = scraped['other'] if scraped['other'] else ''
) )
for lg in list(set(listGroups).difference(known_keys)): for lg in list(set(listGroups).difference(known_keys)):
@@ -445,7 +446,7 @@ def scrape(func):
if anime: if anime:
if function == 'episodios' or item.action == 'episodios': autorenumber.renumber(itemlist, item, 'bold') if function == 'episodios' or item.action == 'episodios': autorenumber.renumber(itemlist, item, 'bold')
else: autorenumber.renumber(itemlist) else: autorenumber.renumber(itemlist)
if anime and autorenumber.check(item) == False and not scrapertools.find_single_match(itemlist[0].title, r'(\d+.\d+)'): if anime and autorenumber.check(item) == False and len(itemlist)>0 and not scrapertools.find_single_match(itemlist[0].title, r'(\d+.\d+)'):
pass pass
else: else:
if addVideolibrary and (item.infoLabels["title"] or item.fulltitle): if addVideolibrary and (item.infoLabels["title"] or item.fulltitle):
@@ -772,31 +773,91 @@ def typo(string, typography=''):
return string return string
def match(item, patron='', patronBlock='', headers='', url='', post=''): def match(item_url_string, **args):
'''
match is a function that combines httptools and scraper tools:
'''
log(item_url_string)
matches = [] matches = []
if type(item) == str: url = None
data = item # arguments allowed for scrape
patron = args.get('patron', None)
patronBlock = args.get('patronBlock', None)
patronBlocks = args.get('patronBlock', None)
debug = args.get('debug', False)
debugBlock = args.get('debugBlock', False)
string = args.get('string', False)
# remove scrape arguments
args = dict([(key, val) for key, val in args.items() if key not in ['patron', 'patronBlock', 'patronBlocks', 'debug', 'debugBlock', 'string']])
# dbg()
# check type of item_url_string
if type(item_url_string) == str:
if item_url_string.startswith('http') and not string: url = item_url_string
else : data = item_url_string
else: else:
url = url if url else item.url # if item_url_string is an item use item.url as url
if post: url = item_url_string.url
data = httptools.downloadpage(url, headers=headers, ignore_response_code=True, post=post).data.replace("'", '"')
else: # if there is a url, download the page
data = httptools.downloadpage(url, headers=headers, ignore_response_code=True).data.replace("'", '"') if url:
if args.get('ignore_response_code', None) is None:
args['ignore_response_code'] = True
data = httptools.downloadpage(url, **args).data.replace("'", '"')
# format page data
data = re.sub(r'\n|\t', ' ', data) data = re.sub(r'\n|\t', ' ', data)
data = re.sub(r'>\s\s*<', '><', data) data = re.sub(r'>\s\s*<', '><', data)
log('DATA= ', data)
# collect blocks of a page
if patronBlock: if patronBlock:
block = scrapertools.find_single_match(data, patronBlock) blocks = [scrapertools.find_single_match(data, patronBlock)]
log('BLOCK= ',block) elif patronBlocks:
blocks = scrapertools.find_multiple_matches(data, patronBlock)
else: else:
block = data blocks = [data]
# match
if patron: if patron:
matches = scrapertools.find_multiple_matches(block, patron) if type(patron) == str: patron = [patron]
log('MATCHES= ',matches) for b in blocks:
for p in patron:
matches += scrapertools.find_multiple_matches(b, p)
return matches, block # debug mode
if config.dev_mode():
if debugBlock:
match_dbg(data, patronBlock)
if debug:
for block in blocks:
for p in patron:
match_dbg(block, p)
# create a item
item = Item(data=data,
blocks=blocks,
block=blocks[0] if len(blocks) > 0 else '',
matches=matches,
match=matches[0] if len(matches) > 0 else '')
return item
def match_dbg(data, patron):
import json, urllib2, webbrowser
url = 'https://regex101.com'
headers = {'content-type': 'application/json'}
data = {
'regex': patron,
'flags': 'gm',
'testString': data,
'delimiter': '"""',
'flavor': 'python'
}
r = urllib2.Request(url + '/api/regex', json.dumps(data, encoding='latin1'), headers=headers)
r = urllib2.urlopen(r).read()
permaLink = json.loads(r)['permalinkFragment']
webbrowser.open(url + "/r/" + permaLink)
def download(itemlist, item, typography='', function_level=1, function=''): def download(itemlist, item, typography='', function_level=1, function=''):
specials/community.py
+3 -5
View File
@@ -547,11 +547,9 @@ def episodios(item):
if pagination and i >= pag * pagination: break # pagination if pagination and i >= pag * pagination: break # pagination
match = [] match = []
if episode.has_key('number'): if episode.has_key('number'):
match = support.match(episode['number'], r'(?P<season>\d+)x(?P<episode>\d+)')[0] match = support.match(episode['number'], patron=r'(?P<season>\d+)x(?P<episode>\d+)').match
if match:
match = match[0]
if not match and episode.has_key('title'): if not match and episode.has_key('title'):
match = support.match(episode['title'], r'(?P<season>\d+)x(?P<episode>\d+)')[0] match = support.match(episode['title'], patron=r'(?P<season>\d+)x(?P<episode>\d+)').match
if match: match = match[0] if match: match = match[0]
if match: if match:
episode_number = match[1] episode_number = match[1]
@@ -561,7 +559,7 @@ def episodios(item):
season_number = episode['season'] if episode.has_key('season') else season if season else 1 season_number = episode['season'] if episode.has_key('season') else season if season else 1
episode_number = episode['number'] if episode.has_key('number') else '' episode_number = episode['number'] if episode.has_key('number') else ''
if not episode_number.isdigit(): if not episode_number.isdigit():
episode_number = support.match(episode['title'], r'(?P<episode>\d+)')[0][0] episode_number = support.match(episode['title'], patron=r'(?P<episode>\d+)').match
ep = int(episode_number) if episode_number else ep ep = int(episode_number) if episode_number else ep
if not episode_number: if not episode_number:
episode_number = str(ep).zfill(2) episode_number = str(ep).zfill(2)