def search_results(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
for elem in soup.find_all("div", class_="result-item"):
url = elem.a["href"]
thumb = elem.img["src"]
title = elem.img["alt"]
year = elem.find("span", class_="year").text
language = get_language(elem)
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
language=language,
infoLabels={'year': year})
if "movies" in url:
new_item.action = "findvideos"
new_item.contentTitle = new_item.title
else:
new_item.action = "seasons"
new_item.contentSerieName = new_item.title
new_item.context = filtertools.context(item, list_language,
list_quality)
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find_all("a", class_="arrow_pag")[-1]["href"]
except:
return itemlist
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='search_results'))
return itemlist
def list_all(item):
logger.info()
itemlist = []
data = get_source(item.url)
json_data = jsontools.load(data)
if len(json_data) > 0:
for elem in json_data['pagination']['data']:
year = elem['year']
lang = elem['language']
url = '%ssecure/titles/%s?titleId=%s' % (host, elem['id'],
elem['id'])
if elem['poster']:
thumb = elem['poster']
else:
thumb = ''
new_item = Item(channel=item.channel,
title=elem['name'],
thumbnail=thumb,
url=url,
infoLabels={'year': year})
if 'movie' in item.url:
new_item.contentTitle = elem['name']
new_item.action = 'findvideos'
else:
new_item.contentSerieName = elem['name']
new_item.action = 'seasons'
itemlist.append(new_item)
tmdb.set_infoLabels(itemlist, True)
## Pagination
try:
next_page = '%s%s' % (item.url,
json_data['pagination']['next_page_url'].replace(
'/?', '&'))
itemlist.append(
Item(channel=item.channel,
action='list_all',
url=next_page,
title='Siguiente >>'))
except:
pass
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("ul", class_="list-movie").find_all("li",
class_="item")
for elem in matches:
url = elem.a["href"]
title = elem.h2.text
year = scrapertools.find_single_match(elem.h4.text, "(\d{4})")
thumb = elem.a.img["src"]
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={'year': year})
if "/serie" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
new_item.context = filtertools.context(item, list_language,
list_quality)
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("a", class_="nextpostslink")["href"]
if url_next_page:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='list_all',
section=item.section))
except:
pass
return itemlist
def list_all(item):
logger.info()
itemlist = []
media_type = item.media_type
json_data = load_json(item)
if json_data:
for media in json_data[media_type]:
quality, language, plot, poster = set_extra_values(media)
title = media['title']
title = set_title(title, language, quality)
new_item = Item(channel=item.channel,
title=format_title(title),
quality=quality,
language=language,
plot=plot,
personal_plot=plot,
thumbnail=poster,
path=item.path)
new_item.infoLabels[
'year'] = media['year'] if 'year' in media else ''
new_item.infoLabels[
'tmdb_id'] = media['tmdb_id'] if 'tmdb_id' in media else ''
if 'movies_list' in json_data or 'generic_list' in json_data:
new_item.url = media
new_item.contentTitle = media['title']
new_item.action = 'findvideos'
else:
new_item.url = media['seasons_list']
new_item.contentSerieName = media['title']
new_item.action = 'seasons'
itemlist.append(new_item)
if not 'generic_list' in json_data:
tmdb.set_infoLabels(itemlist, seekTmdb=True)
for item in itemlist:
if item.personal_plot != item.plot and item.personal_plot:
item.plot = '\n\n' + typo(
'',
'submenu') + '\n' + item.personal_plot + '\n' + typo(
'', 'submenu') + '\n\n' + item.plot
return itemlist
def listado(item):
logger.info()
itemlist = []
data = get_source(item.url)
url_pagination = scrapertools.find_single_match(
data, '<li class="active">.*?</li><li><a href="([^"]+)">')
data = scrapertools.find_multiple_matches(
data, '<ul class="ListAnimes[^>]+>(.*?)</ul>')
data = "".join(data)
matches = re.compile(
'<a href="([^"]+)">.+?<img src="([^"]+)".+?<span class=.+?>(.*?)</span>.+?<h3.*?>(.*?)</h3>'
'.*?</p><p>(.*?)</p>', re.DOTALL).findall(data)
for url, thumbnail, _type, title, plot in matches:
url = urlparse.urljoin(HOST, url)
thumbnail = urlparse.urljoin(HOST, thumbnail)
new_item = Item(channel=item.channel,
action="episodios",
title=title,
url=url,
thumbnail=thumbnail,
plot=plot)
if _type == "Anime":
new_item.contentSerieName = title
new_item.context = renumbertools.context(item)
else:
new_item.contentType = "movie"
new_item.contentTitle = title
itemlist.append(new_item)
if url_pagination:
url = urlparse.urljoin(HOST, url_pagination)
title = ">> Pagina Siguiente"
itemlist.append(
Item(channel=item.channel, action="listado", title=title, url=url))
tmdb.set_infoLabels(itemlist, seekTmdb=True)
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("ul",
class_="MovieList NoLmtxt Rows AX A06 B04 C03 E20")
if not matches:
return itemlist
for elem in matches.find_all("article"):
url = elem.a["href"]
title = elem.a.h3.text
thumb = elem.img
if thumb.has_attr("data-lazy-src"):
thumb = thumb["data-lazy-src"]
else:
thumb = thumb["src"]
try:
year = elem.find("span", class_="Year").text
except:
year = '-'
new_item = Item(channel=item.channel,
url=url,
title=title,
thumbnail=thumb,
infoLabels={'year': year})
if elem.figcaption or elem.find("span", class_="TpTv BgA"):
new_item.action = "seasons"
new_item.contentSerieName = title
else:
new_item.action = "findvideos"
new_item.contentTitle = title
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
next_page = soup.find("a", class_="next page-numbers")["href"]
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=next_page,
action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find_all("div", class_="main-peliculas")[-1].find_all(
"div", class_="movie-box-1")
for elem in matches:
thumb = elem.a.figure.img["src"]
title = elem.a.p.text
url = elem.a["href"]
year = elem.a.span.text
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={"year": year})
if "serie/" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
#try:
url_next_page = soup.find("ul",
class_="pagination").find_all("li")[-1].a["href"]
#except:
# return itemlist
if url_next_page:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("div", class_="Posters")
for elem in matches.find_all("a"):
url = elem["href"]
thumb = elem.img["src"]
title = scrapertools.find_single_match(elem.p.text, r"(.*?) \(")
year = scrapertools.find_single_match(elem.p.text, r"(\d{4})")
if item.type and item.type.lower() not in url:
continue
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={"year": year})
if "/pelicula/" in url:
new_item.contentTitle = title
new_item.action = "findvideos"
else:
new_item.contentSerieName = title
new_item.action = "seasons"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
# Paginación
try:
next_page = soup.find("a", class_="page-link", rel="next")["href"]
if next_page:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=next_page,
action='list_all'))
except:
pass
return itemlist
def listado(item):
logger.info()
data = httptools.downloadpage(item.url).data
data = re.sub(r"\n|\r|\t|\s{2}|-\s", "", data)
url_pagination = scrapertools.find_single_match(
data, '<li class="current">.*?</li>[\s]<li><a href="([^"]+)">')
data = scrapertools.find_single_match(
data, '</div><div class="full">(.*?)<div class="pagination')
matches = re.compile(
'<img.+?src="([^"]+)".+?<a href="([^"]+)">(.*?)</a>.+?'
'<div class="full item_info genres_info">(.*?)</div>.+?class="full">(.*?)</p>',
re.DOTALL).findall(data)
itemlist = []
for thumbnail, url, title, genres, plot in matches:
title = clean_title(title)
url = urlparse.urljoin(HOST, url)
thumbnail = urlparse.urljoin(HOST, thumbnail)
new_item = Item(
channel=item.channel,
action="episodios",
title=title,
url=url,
thumbnail=thumbnail,
contentTitle=title,
plot=plot,
)
if "Pelicula Anime" in genres:
new_item.contentType = "movie"
new_item.contentTitle = title
else:
new_item.contentSerieName = title
new_item.context = renumbertools.context(item)
itemlist.append(new_item)
if url_pagination:
url = urlparse.urljoin(HOST, url_pagination)
title = ">> Pagina Siguiente"
itemlist.append(
Item(channel=item.channel, action="listado", title=title, url=url))
tmdb.set_infoLabels(itemlist, seekTmdb=True)
return itemlist
def list_all(item):
logger.info()
itemlist = []
data = get_source(item.url)
patron = '<article class="Item"><a href="([^>]+)"><div class="Poster"><img src="([^"]+)".*?'
patron += '<h2>([^>]+)</h2>.*?</article>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedthumbnail, scrapedtitle in matches:
title = scrapedtitle
scrapedtitle = re.sub(' \((.*?)\)$', '', scrapedtitle)
thumbnail = scrapedthumbnail.strip()
url = scrapedurl
filter_thumb = thumbnail.replace("https://image.tmdb.org/t/p/w154", "")
filter_list = {"poster_path": filter_thumb}
filter_list = filter_list.items()
thumbnail = re.sub('p/w\d+', 'p/original', thumbnail)
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumbnail,
infoLabels={'filtro': filter_list})
if item.type == 'peliculas' or 'peliculas' in url:
new_item.action = 'findvideos'
new_item.contentTitle = scrapedtitle
else:
new_item.action = 'seasons'
new_item.contentSerieName = scrapedtitle
itemlist.append(new_item)
tmdb.set_infoLabels(itemlist, seekTmdb=True)
# Paginación
url_next_page = scrapertools.find_single_match(
data, '<link rel="next" href="([^"]+)"')
if url_next_page:
itemlist.append(
item.clone(title="Siguiente >>",
url=url_next_page,
action='list_all'))
return itemlist
def alpha_list(item):
logger.info()
itemlist = list()
data = create_soup(item.url)
soup = data.find("tbody")
if not soup:
return itemlist
for elem in soup.find_all("tr"):
info = elem.find("td", class_="MvTbTtl")
thumb = elem.find("td", class_="MvTbImg").a.img["src"]
url = info.a["href"]
title = info.a.text.strip()
year = ''
quality = ''
if '/pelicula/' in url:
quality = elem.find("span", class_="Qlty").text
try:
year = elem.find("td", text=re.compile(r"\d{4}")).text
except:
pass
new_item = Item(channel=item.channel, title=title, url=url, thumbnail=thumb, infoLabels={"year": year})
if '/pelicula/' in url:
new_item.contentTitle = title
new_item.action = "findvideos"
new_item.quality = quality
else:
new_item.contentSerieName = title
new_item.action = "seasons"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
next_page = data.find("a", class_="next page-numbers")["href"]
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=next_page, action='list_all'))
except:
pass
return itemlist
def list_all(item):
logger.info()
json_data = {"results": []}
itemlist = list()
for x in range(3):
try:
matches = httptools.downloadpage('%s%s' % (item.url, item.page)).json
except:
break
if matches and "results" in matches:
json_data["results"] += matches["results"]
item.page += 1
for data in json_data["results"]:
if "content" in data:
elem = BeautifulSoup(data["content"], "html5lib", from_encoding="utf-8")
url = host + elem.a["href"]
year = scrapertools.find_single_match(data["date"], r"(\d{4})")
else:
url = "%s/serie/%s" % (host, data["slug"])
year = ''
title = data["titulo"]
thumb = data["poster"]
content_id = data["ID"]
new_item = Item(channel=item.channel, title=title, url=url, thumbnail=thumb, content_id=content_id,
infoLabels={'year': year}, info=data)
if "/serie" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=item.url, action='list_all',
page=item.page + 1))
except:
pass
return itemlist
def search_results(item):
logger.info()
itemlist = []
data = get_source(item.url)
patron = '<article>.*?<a href="([^"]+)"><img src="([^"]+)" alt="([^"]+)" />'
patron += '<span class="([^"]+)".*?IMDb (.*?)</.*?year">([^<]+)<.*?<p>(.*?)</p>'
matches = re.compile(patron, re.DOTALL).findall(data)
for url, scrapedthumb, scrapedtitle, typo, rating, year, plot in matches:
title = re.sub(r'\s*\((\d{4})\)$', '', scrapedtitle)
contentTitle = title
if not config.get_setting('unify'):
rcolor = color_rating(rating)
title += ' [COLOR grey](%s)[/COLOR] [COLOR %s](%s)[/COLOR]' % (
year, rcolor, rating)
thumbnail = re.sub("(w\d+/)", "original/", scrapedthumb)
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumbnail,
plot=plot,
language='VO',
infoLabels={'year': year})
if typo == 'movies':
new_item.contentTitle = contentTitle
new_item.action = 'findvideos'
else:
new_item.contentSerieName = contentTitle
new_item.action = 'seasons'
if not config.get_setting('unify'):
new_item.title += '[COLOR blue] (Serie)[/COLOR]'
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
return itemlist
def peliculas(item):
logger.info()
itemlist = []
# action = ''
# contentType = ''
data = httptools.downloadpage(item.url).data
data = re.sub(r"\n|\r|\t|\s{2}| |<br>", "", data)
patron = '<img class="posterentrada" src="/([^"]+)".*?' # img
patron += '<a href="([^"]+)">.*?' # url
patron += '<p class="description_poster">.*?\(([^<]+)\)</p>.*?' # year
patron += '<div class="Description"> <div>([^<]+)</div>.*?' # plot
patron += '<strong>([^<]+)</strong></h4>' # title
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedthumbnail, scrapedurl, year, plot, scrapedtitle in matches:
new_item = Item(channel=item.channel, thumbnail=host + scrapedthumbnail,
infoLabels={"year": year}, url=scrapedurl, title=scrapedtitle,
plot=plot)
if 'serie' in scrapedurl:
new_item.action = 'temporadas'
new_item.contentType = 'tvshow'
new_item.contentSerieName = scrapedtitle
new_item.title += ' [COLOR blue](Serie)[/COLOR]'
else:
new_item.action = 'findvideos'
contentType = 'movie'
new_item.contentTitle = scrapedtitle
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, __modo_grafico__)
pagination = scrapertools.find_single_match(
data, '<li><a href="([^"]+)" rel="next">')
if pagination:
itemlist.append(Item(channel=__channel__, action="peliculas", title="» Siguiente »",
url=pagination, folder=True, text_blod=True, thumbnail=get_thumb("next.png")))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("div", class_="dt-css-grid").find_all("article")
for elem in matches:
url = elem.h3.a["href"]
title = elem.h3.a.text
thumb = elem.img["src"]
year = "-"
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={"year": year})
if "serie-" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("div", class_="pagination").find(
"span", class_="current").next_sibling["href"]
except:
return itemlist
if url_next_page and len(matches) > 16:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url).find("div", class_="peliculas")
matches = soup.find_all("div", class_="item")
for elem in matches:
url = elem.a["href"]
title = elem.find("div", class_="fixyear").h2.text
title = re.sub(r"\(\d{4}(?:-Actualidad|-\d{4})?\)", "", title)
year = elem.find("span", class_="year").text
thumb = elem.img["src"]
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={"year": year})
if not "series/" in url:
new_item.contentTitle = title
new_item.action = "findvideos"
else:
new_item.contentSerieName = title
new_item.action = "seasons"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("div", class_="nav-previous").a["href"]
except:
return itemlist
if url_next_page:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = []
media_type = item.media_type
json_data = load_json(item)
for media in json_data[media_type]:
quality, language, plot, poster = set_extra_values(media)
title = media['title']
title = set_title(title, language, quality)
new_item = Item(channel=item.channel,
title=title,
quality=quality,
language=language,
plot=plot,
thumbnail=poster)
new_item.infoLabels['year'] = media['year'] if 'year' in media else ''
new_item.infoLabels[
'tmdb_id'] = media['tmdb_id'] if 'tmdb_id' in media else ''
if 'movies_list' in json_data:
new_item.url = media
new_item.contentTitle = media['title']
new_item.action = 'findvideos'
if 'year' in media:
new_item.infoLabels['year'] = media['year']
if 'tmdb_id' in media:
new_item.infoLabels['tmdb_id'] = media['tmdb_id']
else:
new_item.url = media['seasons_list']
new_item.contentSerieName = media['title']
new_item.action = 'seasons'
if 'year' in media:
new_item.infoLabels['year'] = media['year']
if 'tmdb_id' in media:
new_item.infoLabels['tmdb_id'] = media['tmdb_id']
itemlist.append(new_item)
tmdb.set_infoLabels(itemlist, seekTmdb=True)
return itemlist
def list_all(item):
logger.info()
itemlist = []
data = get_source(item.url)
patron = '<article class=Item><a href=([^>]+)><div class=Poster>'
patron += '<img src=(.+?)(?:>|alt).*?<h2>([^>]+)</h2>.*?</article>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedthumbnail, scrapedtitle in matches:
title = scrapedtitle
thumbnail = scrapedthumbnail.strip()
url = scrapedurl
filter_thumb = thumbnail.replace("https://image.tmdb.org/t/p/w154", "")
filter_list = {"poster_path": filter_thumb}
filter_list = filter_list.items()
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumbnail,
plot=thumbnail,
infoLabels={'filtro': filter_list})
if item.type == 'peliculas':
new_item.action = 'findvideos'
new_item.contentTitle = scrapedtitle
else:
new_item.action = 'seasons'
new_item.contentSerieName = scrapedtitle
itemlist.append(new_item)
tmdb.set_infoLabels(itemlist, seekTmdb=True)
# Paginación
url_next_page = scrapertools.find_single_match(
data, "<link rel=next href=(.*?) />")
if url_next_page:
itemlist.append(
item.clone(title="Siguiente >>",
url=url_next_page,
action='list_all'))
return itemlist
def lista(item):
logger.info()
itemlist = []
data = httptools.downloadpage(item.url).data
data = re.sub(r"\n|\r|\t|\s{2}| ", "", data)
patron = '<article .*?">'
patron += '<a href="([^"]+)"><.*?><figure.*?>' #scrapedurl
patron += '<img.*?src="([^"]+)".*?>.*?' #scrapedthumbnail
patron += '<h3 class=".*?">([^"]+)<\/h3>' #scrapedtitle
patron += '<span.*?>([^"]+)<\/span>.+?' #scrapedyear
patron += '<a.+?>([^"]+)<\/a>' #scrapedtype
matches = scrapertools.find_multiple_matches(data, patron)
for scrapedurl, scrapedthumbnail, scrapedtitle, scrapedyear, scrapedtype in matches:
title = "%s - %s" % (scrapedtitle, scrapedyear)
new_item = Item(channel=item.channel,
title=title,
url=scrapedurl,
thumbnail=scrapedthumbnail,
type=scrapedtype,
infoLabels={'year': scrapedyear})
if scrapedtype == 'Serie':
new_item.contentSerieName = scrapedtitle
new_item.action = 'episodios'
else:
new_item.contentTitle = scrapedtitle
new_item.action = 'findvideos'
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
#pagination
pag = item.pag + 1
url_next_page = item.url + "/page/" + str(pag) + "/"
if len(itemlist) > 19:
itemlist.append(
item.clone(title="Siguiente >>",
url=url_next_page,
action='lista',
pag=pag))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("div", class_="content")
for elem in matches.find_all("article", id=re.compile(r"^post-\d+")):
title = elem.img["alt"]
title = re.sub("VOSE", "", title)
url = elem.a["href"]
thumb = elem.img["data-src"]
try:
year = elem.find("span",
text=re.compile(r"\d{4}")).text.split(",")[-1]
except:
pass
new_item = Item(channel=item.channel,
url=url,
title=title,
thumbnail=thumb,
infoLabels={"year": year.strip()})
if "serie" in url:
new_item.action = "seasons"
new_item.contentSerieName = title
else:
new_item.action = "findvideos"
new_item.contentTitle = title
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
next_page = soup.find_all("a", class_="arrow_pag")[-1]["href"]
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=next_page,
action="list_all"))
except:
pass
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("ul", id="list-view").find_all("article")
for elem in matches:
url = elem.find("a", class_="lnk-blk")["href"]
title = elem.h2.text
try:
year = elem.find("span", class_="year").a.text
except:
year = "-"
if elem.img.has_attr("data-lazy-src"):
thumb = elem.img["data-lazy-src"]
elif elem.img.has_attr("src"):
thumb = elem.img["src"]
else:
thumb = ""
new_item = Item(channel=item.channel, title=title, url=url, thumbnail=thumb, infoLabels={"year": year})
if "serie/" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("a", class_="nextpostslink")["href"]
except:
return itemlist
if url_next_page and len(matches) > 16:
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=url_next_page, action='list_all'))
return itemlist
def search_results(item):
logger.info()
itemlist = []
data = get_source(item.url)
patron = '<article>.*?<a href="([^"]+)">.*?<img src="([^"]+)" alt="([^"]+)".*?<span class="(tvshows|movies)".*?'
patron += '"meta".*?"year">([^<]+)<(.*?)<p>([^<]+)</p>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedthumb, scrapedtitle, type, year, lang_data, scrapedplot in matches:
title = scrapedtitle
url = scrapedurl
thumbnail = scrapedthumb.replace('-150x150', '')
plot = scrapedplot
language = get_language(lang_data)
type = re.sub('shows|s', '', type)
if language:
action = 'findvideos'
else:
action = 'seasons'
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumbnail,
plot=plot,
action=action,
type=type,
language=language,
infoLabels={'year': year})
if new_item.action == 'findvideos':
new_item.contentTitle = new_item.title
else:
new_item.contentSerieName = new_item.title
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
return itemlist
def search_results(item):
logger.info()
itemlist = list()
url = "%swp-content/plugins/ajax-search-pro/ajax_search.php" % host
post = {
"action":
"ajaxsearchpro_search",
"aspp":
item.text,
"asid":
"1",
"asp_inst_id":
"1_1",
"options":
"current_page_id=9&qtranslate_lang=0&filters_changed=0&filters_initial=1&asp_gen%5B%5D=title&asp_gen%5B%5D=content&asp_gen%5B%5D=excerpt&customset%5B%5D=post"
}
matches = create_soup(url, post=post).find_all("div", class_="asp_content")
for elem in matches:
url = elem.a["href"]
thumb = elem.find("div", class_="asp_image asp_lazy")["data-src"]
title = elem.h3.text.strip()
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={'year': '-'})
if "serie-" in url:
new_item.action = "seasons"
new_item.contentSerieName = new_item.title
new_item.context = filtertools.context(item, list_language,
list_quality)
else:
new_item.action = "findvideos"
new_item.contentTitle = new_item.title
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find_all("div", class_="col-lg-2 col-md-4 col-6")
for elem in matches:
url = elem.a["href"]
lang, title = clear_title(elem.find("p").text)
thumb = elem.img["src"]
year = elem.find("button", class_="btntwo").text
c_type = elem.find("button", class_="btnone").text.lower()
new_item = Item(channel=item.channel,
title=title,
url=url,
action="episodios",
language=lang,
thumbnail=thumb,
infoLabels={"year": year})
if c_type not in ["live action", "pelicula"]:
new_item.contentSerieName = title
else:
new_item.contentTitle = title
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("a", rel="next")["href"]
if url_next_page and len(itemlist) > 8:
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=url_next_page,
action='list_all'))
except:
pass
return itemlist
def list_all(item):
logger.info()
itemlist = []
full_data = get_source(item.url)
data = scrapertools.find_single_match(full_data, '<div class="Posters">(.*?)</(?:ul|a></div>)')
patron = 'href="([^"]+)".*?src="([^"]+)".*?<p>([^<]+)</p>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedthumbnail, scrapedtitle in matches:
year = scrapertools.find_single_match(scrapedtitle, '(\d{4})')
title = scrapertools.find_single_match(scrapedtitle, '([^\(]+)\(?').strip()
thumbnail = scrapedthumbnail
filter_thumb = thumbnail.replace("https://image.tmdb.org/t/p/w300", "")
filter_list = {"poster_path": filter_thumb}
filter_list = filter_list.items()
url = scrapedurl
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumbnail,
infoLabels={'filtro':filter_list, 'year':year})
if item.type == 'peliculas' or 'serie' not in url:
new_item.action = 'findvideos'
new_item.contentTitle = title
else:
new_item.action = 'seasons'
new_item.contentSerieName = title
itemlist.append(new_item)
tmdb.set_infoLabels(itemlist, seekTmdb=True)
# Paginación
next_page_pattern = '<a class="page-link" href="([^"]+)" data-ci-pagination-page="\d+" rel="next">></a>'
url_next_page = scrapertools.find_single_match(full_data, next_page_pattern)
if url_next_page:
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=url_next_page, action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
if item.search or item.genre:
matches = soup.find("div", id="movies-a").find_all("article")
else:
matches = soup.find("section", class_="episodes").find_all("article")
for elem in matches:
url = elem.a["href"]
thumb = "https:" + elem.find("img")["src"]
title = elem.h2.text
mode = elem.find("span", class_="watch").text
new_item = Item(channel=item.channel, title=title, url=url, thumbnail=thumb, infoLabels={"year": "-"})
if "caricatura" in mode.lower():
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find("a", text="NEXT")["href"]
except:
return itemlist
if url_next_page:
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=url_next_page, action='list_all'))
return itemlist
def list_all(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("div", class_="content").find_all("article", id=re.compile(r"^post-\d+"))
for elem in matches:
info_1 = elem.find("div", class_="poster")
info_2 = elem.find("div", class_="data")
thumb = info_1.img["src"]
title = info_1.img["alt"]
url = info_1.a["href"]
try:
year = info_2.find("span", text=re.compile(r"\d{4}")).text.split(",")[-1].strip()
except:
year = "-"
new_item = Item(channel=item.channel, title=title, url=url, thumbnail=thumb, infoLabels={"year": year})
if "tvshows" in url:
new_item.contentSerieName = title
new_item.action = "seasons"
else:
new_item.contentTitle = title
new_item.action = "findvideos"
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
try:
url_next_page = soup.find_all("a", class_="arrow_pag")[-1]["href"]
except:
return itemlist
itemlist.append(Item(channel=item.channel, title="Siguiente >>", url=url_next_page, action='list_all'))
return itemlist
def alpha_list(item):
logger.info()
itemlist = list()
soup = create_soup(item.url)
matches = soup.find("tbody")
for elem in matches.find_all("tr"):
info = elem.find("td", class_="MvTbTtl")
thumb = elem.img["data-lazy-src"]
url = info.a["href"]
title = info.a.text.strip()
try:
year = elem.find("td", text=re.compile(r"\d{4}")).text
except:
year = '-'
new_item = Item(channel=item.channel,
title=title,
url=url,
thumbnail=thumb,
infoLabels={"year": year})
if elem.find("span", class_="TpTv BgA"):
new_item.action = "seasons"
new_item.contentSerieName = title
else:
new_item.action = "findvideos"
new_item.contentTitle = title
logger.debug(new_item)
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, True)
next_page = soup.find("a", class_="next page-numbers")["href"]
itemlist.append(
Item(channel=item.channel,
title="Siguiente >>",
url=next_page,
action='alpha_list'))
return itemlist
def lista(item):
logger.info()
itemlist = []
data = httptools.downloadpage(item.url).data
data = re.sub(r"\n|\r|\t|\s{2}| ", "", data)
patron = '(?is)class="TPost C">.*?href="([^"]+)".*?' #scrapedurl
patron += 'lazy-src="([^"]+)".*?>.*?' #scrapedthumbnail
patron += 'title">([^<]+)<.*?' #scrapedtitle
patron += 'year">([^<]+)<.*?' #scrapedyear
patron += 'href.*?>([^"]+)<\/a>' #scrapedtype
matches = scrapertools.find_multiple_matches(data, patron)
for scrapedurl, scrapedthumbnail, scrapedtitle, scrapedyear, scrapedtype in matches:
if not scrapedthumbnail.startswith("http"):
scrapedthumbnail = "https:" + scrapedthumbnail
title = "%s - %s" % (scrapedtitle, scrapedyear)
new_item = Item(channel=item.channel,
title=title,
url=scrapedurl,
thumbnail=scrapedthumbnail,
type=scrapedtype,
infoLabels={'year': scrapedyear})
if scrapedtype == 'Serie':
new_item.contentSerieName = scrapedtitle
new_item.action = 'episodios'
else:
new_item.contentTitle = scrapedtitle
new_item.action = 'findvideos'
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
#pagination
url_next_page = scrapertools.find_single_match(
data, 'rel="next" href="([^"]+)"')
if len(itemlist) > 0 and url_next_page:
itemlist.append(
item.clone(title="Siguiente >>", url=url_next_page,
action='lista'))
return itemlist
def list_all(item):
logger.info()
itemlist = []
data = get_source(item.url)
patron = '<div class="col-lg-2 col-md-3 col-6 mb-3"><a href="([^"]+)".*?<img src="([^"]+)".*?'
patron += 'font-weight-500">([^<]+)<'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedthumbnail, scrapedtitle in matches:
url = urlparse.urljoin(host, scrapedurl)
scrapedtitle = scrapedtitle
thumbnail = scrapedthumbnail
new_item = Item(channel=item.channel,
title=scrapedtitle,
url=url,
thumbnail=thumbnail)
new_item.contentSerieName = scrapedtitle
new_item.action = 'seasons'
new_item.context = filtertools.context(item, list_language,
list_quality)
itemlist.append(new_item)
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Paginacion
if itemlist != []:
page_base = host + 'catalogue'
next_page = scrapertools.find_single_match(
data, '<a href="([^ ]+)" aria-label="Netx">')
if next_page != '':
itemlist.append(
Item(channel=item.channel,
action="list_all",
title='Siguiente >>>',
url=page_base + next_page,
thumbnail=get_thumb("more.png"),
type=item.type))
return itemlist
def listado(item):
logger.info()
itemlist = []
data = httptools.downloadpage(item.url).data
data = re.sub(r"\n|\r|\t|\s{2}| ","",data)
patron = '<div class="MiniFicha">.*?'
patron += '<img src="([^"]+).*?'
patron += '<div class="MiniF_TitleSpecial">[^>]+>([^<]+).*?'
patron += '<b>Categoria:\s*</b>([^&]+)»\s*([^<]+).*?'
patron += '<div class="OpcionesDescargasMini">(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
for thumbnail, title, cat_padres, cat_hijos, opciones in matches:
#logger.debug(thumbnail + "\n" + title + "\n" + cat_padres + "\n" + cat_hijos + "\n" + opciones)
# Obtenemos el año del titulo y eliminamos lo q sobre
patron = '\d{4}$'
year = scrapertools.find_single_match(title,patron)
if year:
title = re.sub(patron, "", title)
patron = '\s?-?\s?(line)?\s?-\s?$'
title = re.sub(patron, "", title,flags=re.IGNORECASE)
# Obtenemos la imagen b por q es mayor
thumbnail = HOST + thumbnail[:-5] + 'b' + thumbnail[-4:]
# Buscamos opcion de ver online
patron = '<a href="http://estrenosly.org/ver-online-([^"]+)'
url_ver = scrapertools.find_single_match(opciones, patron)
if url_ver:
new_item = Item(channel=item.channel, action="findvideos", title=title,
thumbnail=thumbnail, url=url_ver,
infoLabels={"year":year}, text_color = color1)
cat_padres = cat_padres.strip()
if cat_padres in ["peliculas-dvdrip", "HDRIP", "cartelera"]:
#if item.extra == 'movie':
new_item.contentTitle = title
new_item.extra = "movie"
# Filtramos nombres validos para la calidad
patron = ("rip|dvd|screener|hd|ts|Telesync")
if re.search(patron,cat_hijos,flags=re.IGNORECASE):
new_item.contentQuality = cat_hijos
new_item.title = "%s [%s]" % (title, cat_hijos)
elif cat_padres == "peliculas-dvdrip":
new_item.contentQuality = "DVDRIP"
new_item.title = "%s [DVDRIP]" % title
elif cat_padres == "HDRIP":
new_item.contentQuality = "HDRIP"
new_item.title = "%s [HDRIP]" % title
elif cat_padres == "series":
new_item.contentSerieName = cat_hijos
patron = re.compile('(\d+)x(\d+)')
matches = patron.findall(title)
if len(matches) == 1:
new_item.contentSeason = matches[0][0]
new_item.contentEpisodeNumber = matches[0][1].zfill(2)
new_item.extra = "episodie"
else:
# matches == [('1', '01'), ('1', '02'), ('1', '03')]
new_item.extra = "multi-episodie"
else: #Otras categorias q de momento no nos interesan
continue
''' Opcionalmente podriamos obtener los enlaces torrent y descargas directas
patron = '<a href="http://estrenosli.org/descarga-directa-([^"]+)'
new_item.url_descarga = scrapertools.find_single_match(opciones,patron)
patron = '<a href="http://estrenosli.org/descargar-torrent-([^"]+).*?'
new_item.url_torrent = scrapertools.find_single_match(opciones,patron)'''
itemlist.append(new_item)
if itemlist:
# Obtenemos los datos basicos de todas las peliculas mediante multihilos
tmdb.set_infoLabels(itemlist)
# Si es necesario añadir paginacion
patron = '<div class="sPages">.*?'
patron += '<a href="([^"]+)">Siguiente'
url_next_page = scrapertools.find_single_match(data,patron)
if url_next_page:
itemlist.append(Item(channel=item.channel, action="listado", title=">> Página siguiente",
thumbnail=thumbnail_host, url=HOST + url_next_page, folder=True,
text_color = color3, text_blod=True))
return itemlist
