Fix Support Match
This commit is contained in:
Alhaziel
@@ -122,7 +122,7 @@ def last(item):
|
||||
if item.contentType == 'episode':
|
||||
matches = support.match(item, r'<a href="([^">]+)".*?>([^(:(|[)]+)([^<]+)<\/a>', '<article class="sequex-post-content.*?</article>', headers)[0]
|
||||
else:
|
||||
matches = support.match(item, r'<ahref=([^>]+)>([^(:(|[)]+)([^<]+)<\/a>', r'<strong>Ultimi 100 film Aggiornati:<\/a><\/strong>(.*?)<td>', headers)[0]
|
||||
matches = support.match(item, r'<a href=([^>]+)>([^(:(|[)]+)([^<]+)<\/a>', r'<strong>Ultimi 100 film Aggiornati:<\/a><\/strong>(.*?)<td>', headers)[0]
|
||||
|
||||
for url, title, info in matches:
|
||||
add = True
|
||||
|
||||
@@ -103,35 +103,16 @@ def nuoveserie(item):
|
||||
|
||||
patron_block = ''
|
||||
if 'inedite' in item.args:
|
||||
patron_block = r'<div\sclass="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div'
|
||||
patron_block = r'<div class="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div'
|
||||
elif 'da non perdere' in item.args:
|
||||
patron_block = r'<div\sclass="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div'
|
||||
patron_block = r'<div class="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div'
|
||||
elif 'classiche' in item.args:
|
||||
patron_block = r'<div\sclass="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div'
|
||||
patron_block = r'<div class="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div'
|
||||
else:
|
||||
patron_block = r'<div\sclass="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div'
|
||||
patron_block = r'<div class="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div'
|
||||
|
||||
patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>'
|
||||
patron += r'[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p>'
|
||||
|
||||
matches = support.match(item, patron, patron_block, headers)[0]
|
||||
|
||||
for scrapedurl, scrapedthumbnail, scrapedtitle in matches:
|
||||
scrapedtitle = cleantitle(scrapedtitle)
|
||||
|
||||
itemlist.append(
|
||||
Item(channel=item.channel,
|
||||
action="episodios",
|
||||
contentType="episode",
|
||||
title=scrapedtitle,
|
||||
fulltitle=scrapedtitle,
|
||||
url=scrapedurl,
|
||||
show=scrapedtitle,
|
||||
thumbnail=scrapedthumbnail,
|
||||
folder=True))
|
||||
|
||||
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
|
||||
return itemlist
|
||||
patron = r'<a href="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p>'
|
||||
return support.scrape(item, patron, ['url', 'thumb', 'title'], patron_block=patron_block, action='episodios')
|
||||
|
||||
|
||||
# ================================================================================================================
|
||||
@@ -141,47 +122,10 @@ def serietvaggiornate(item):
|
||||
log()
|
||||
itemlist = []
|
||||
|
||||
patron_block = r'<div\sclass="container container-title-serie-lastep container-scheda" meta-slug="lastep">(.*?)</div></div><div'
|
||||
patron = r'<a\srel="nofollow" href="([^"]+)"[^>]+> <img\s*.*?src="([^"]+)"[^>]+>[^>]+>'
|
||||
patron += r'[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>'
|
||||
patron_block = r'<div class="container\s*container-title-serie-lastep\s*container-scheda" meta-slug="lastep">(.*?)<\/div><\/div><div'
|
||||
patron = r'<a rel="nofollow" href="([^"]+)"[^>]+> <img.*?src="([^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^(?:<|\()]+)(?:\(([^\)]+)\))?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>'
|
||||
|
||||
matches = support.match(item, patron, patron_block, headers)[0]
|
||||
|
||||
for scrapedurl, scrapedthumbnail, scrapedep, scrapedtitle in matches:
|
||||
episode = re.compile(r'^(\d+)x(\d+)', re.DOTALL).findall(scrapedep) # Prendo stagione ed episodioso
|
||||
scrapedtitle = cleantitle(scrapedtitle)
|
||||
|
||||
contentlanguage = ""
|
||||
if 'sub-ita' in scrapedep.strip().lower():
|
||||
contentlanguage = 'Sub-ITA'
|
||||
|
||||
extra = r'<span\s.*?meta-stag="%s" meta-ep="%s" meta-embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"[^>]*>' % (
|
||||
episode[0][0], episode[0][1].lstrip("0"))
|
||||
|
||||
infoLabels = {}
|
||||
infoLabels['episode'] = episode[0][1].zfill(2)
|
||||
infoLabels['season'] = episode[0][0]
|
||||
|
||||
title = str(
|
||||
"%s - %sx%s %s" % (scrapedtitle, infoLabels['season'], infoLabels['episode'], contentlanguage)).strip()
|
||||
|
||||
itemlist.append(
|
||||
Item(channel=item.channel,
|
||||
action="findepvideos",
|
||||
contentType="episode",
|
||||
title=title,
|
||||
show=scrapedtitle,
|
||||
fulltitle=scrapedtitle,
|
||||
url=scrapedurl,
|
||||
extra=extra,
|
||||
thumbnail=scrapedthumbnail,
|
||||
contentLanguage=contentlanguage,
|
||||
infoLabels=infoLabels,
|
||||
folder=True))
|
||||
|
||||
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
|
||||
|
||||
return itemlist
|
||||
return support.scrape(item, patron, ['url', 'thumb', 'episode', 'lang', 'title'], patron_block=patron_block, action='findvideos')
|
||||
|
||||
|
||||
# ================================================================================================================
|
||||
@@ -202,29 +146,7 @@ def lista_serie(item):
|
||||
patron_block = r'<div\sclass="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\sclass="container-fluid whitebg" style="">'
|
||||
patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>'
|
||||
|
||||
matches, data = support.match(item, patron, patron_block, headers)
|
||||
|
||||
for scrapedurl, scrapedimg, scrapedtitle in matches:
|
||||
scrapedtitle = cleantitle(scrapedtitle)
|
||||
|
||||
if scrapedtitle not in ['DMCA', 'Contatti', 'Lista di tutte le serie tv']:
|
||||
itemlist.append(
|
||||
Item(channel=item.channel,
|
||||
action="episodios",
|
||||
contentType="episode",
|
||||
title=scrapedtitle,
|
||||
fulltitle=scrapedtitle,
|
||||
url=scrapedurl,
|
||||
thumbnail=scrapedimg,
|
||||
extra=item.extra,
|
||||
show=scrapedtitle,
|
||||
folder=True))
|
||||
|
||||
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
|
||||
|
||||
support.nextPage(itemlist, item, data, r"<link\s.*?rel='next'\shref='([^']*)'")
|
||||
|
||||
return itemlist
|
||||
return support.scrape(item, patron, ['url', 'thumb', 'title'], patron_block=patron_block, patronNext=r"<link\s.*?rel='next'\shref='([^']*)'", action='episodios')
|
||||
|
||||
|
||||
# ================================================================================================================
|
||||
@@ -235,7 +157,7 @@ def episodios(item):
|
||||
itemlist = []
|
||||
|
||||
patron = r'<div\sclass="[^"]+">\s([^<]+)<\/div>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+><p[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>'
|
||||
patron += r'[^<]+[^"]+".*?serie="([^"]+)".*?stag="([0-9]*)".*?ep="([0-9]*)"\s'
|
||||
patron += r'[^"]+".*?serie="([^"]+)".*?stag="([0-9]*)".*?ep="([0-9]*)"\s'
|
||||
patron += r'.*?embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>\s?'
|
||||
patron += r'(?:<img\sclass="[^"]+" meta-src="([^"]+)"[^>]+>|<img\sclass="[^"]+" src="" data-original="([^"]+)"[^>]+>)?'
|
||||
|
||||
@@ -255,7 +177,7 @@ def episodios(item):
|
||||
itemlist.append(
|
||||
Item(channel=item.channel,
|
||||
action="findvideos",
|
||||
title=title,
|
||||
title=support.typo(title, 'bold'),
|
||||
fulltitle=scrapedtitle,
|
||||
url=scrapedurl + "\r\n" + scrapedurl2 + "\r\n" + scrapedurl3,
|
||||
contentType="episode",
|
||||
@@ -290,5 +212,11 @@ def findepvideos(item):
|
||||
# ----------------------------------------------------------------------------------------------------------------
|
||||
def findvideos(item):
|
||||
log()
|
||||
logger.debug(item.url)
|
||||
return support.server(item, data=item.url)
|
||||
if item.contentType == 'tvshow':
|
||||
data = httptools.downloadpage(item.url, headers=headers).data
|
||||
matches = scrapertools.find_multiple_matches(data, item.extra)
|
||||
data = "\r\n".join(matches[0])
|
||||
else:
|
||||
log(item.url)
|
||||
data = item.url
|
||||
return support.server(item, data)
|
||||
|
||||
@@ -130,7 +130,7 @@ def peliculas(item):
|
||||
action = 'findvideos' if item.extra == 'movie' else 'episodios'
|
||||
if item.args == 'movie':
|
||||
patron= r'<div class="mediaWrap mediaWrapAlt">[^<]+<a href="([^"]+)" title="Permalink to\s([^"]+) \(([^<]+)\).*?"[^>]+>[^<]+<img[^s]+src="([^"]+)"[^>]+>[^<]+<\/a>.*?<p>\s*([a-zA-Z-0-9]+)\s*<\/p>'
|
||||
itemlist = support.scrape(item, patron, ['url', 'title', 'year', 'thumb', 'quality'], headers, action=action, patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">')
|
||||
itemlist = support.scrape(item, patron, ['url', 'title', 'year', 'thumb', 'quality'], headers, action=action, patron_block='<div id="main_col">(.*?)main_col', patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">')
|
||||
else:
|
||||
patron = r'<div class="media3">[^>]+><a href="([^"]+)"><img[^s]+src="([^"]+)"[^>]+><\/a><[^>]+><a[^<]+><p>([^<]+) \(([^\)]+)[^<]+<\/p>.*?<p>\s*([a-zA-Z-0-9]+)\s*<\/p>'
|
||||
itemlist = support.scrape(item, patron, ['url', 'thumb', 'title', 'year', 'quality'], headers, action=action, patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">')
|
||||
@@ -210,7 +210,7 @@ def anime(item):
|
||||
|
||||
def findvideos(item):
|
||||
log()
|
||||
itemlist = []
|
||||
# itemlist = []
|
||||
|
||||
if item.args == 'anime':
|
||||
data = item.url
|
||||
@@ -233,6 +233,5 @@ def findvideos(item):
|
||||
page = httptools.downloadpage(url, headers=headers).data
|
||||
data += '\t' + scrapertoolsV2.find_single_match(page,'<meta name="og:url" content="([^=]+)">')
|
||||
|
||||
itemlist= support.server(item, data, headers, True, True)
|
||||
support.videolibrary(itemlist, item, 'color kod bold')
|
||||
return itemlist
|
||||
return support.server(item, data, headers=headers)
|
||||
# return itemlist
|
||||
|
||||
+1
-1
@@ -113,4 +113,4 @@ def play(item):
|
||||
|
||||
data = support.swzz_get_url(item)
|
||||
|
||||
return support.server(item, data, headers)
|
||||
return support.server(item, data, headers=headers)
|
||||
|
||||
+3
-2
@@ -167,7 +167,7 @@ def scrape(item, patron = '', listGroups = [], headers="", blacklist="", data=""
|
||||
scraped['episode'] = re.sub(r'\s-\s|-|x|–', 'x' , scraped['episode'])
|
||||
longtitle = typo(scraped['episode'] + ' - ', 'bold') + longtitle
|
||||
if scraped['title2']:
|
||||
title2 = scrapertoolsV2.decodeHtmlentities(scraped["title2"]).strip()
|
||||
title2 = scrapertoolsV2.decodeHtmlentities(scraped["title2"]).replace('"', "'").strip()
|
||||
longtitle = longtitle + typo(title2, 'bold _ -- _')
|
||||
if scraped["lang"]:
|
||||
if 'sub' in scraped["lang"].lower():
|
||||
@@ -467,7 +467,8 @@ def match(item, patron='', patron_block='', headers='', url=''):
|
||||
matches = []
|
||||
url = url if url else item.url
|
||||
data = httptools.downloadpage(url, headers=headers, ignore_response_code=True).data.replace("'", '"')
|
||||
data = re.sub(r'\n|\t|\s\s', ' ', data)
|
||||
data = re.sub(r'\n|\t', ' ', data)
|
||||
data = re.sub(r'>\s\s*<', '><', data)
|
||||
log('DATA= ', data)
|
||||
|
||||
if patron_block:
|
||||
|
||||
Reference in New Issue
Block a user