def peliculas(item):
support.log()
if item.extra == 'search':
itemlist = support.scrape(item, r'<a href="([^"]+)">\s*<div[^=]+=[^=]+=[^=]+=[^=]+=[^=]+="(.*?)"[^>]+>[^<]+<[^>]+>\s*<h[^=]+="titleFilm">(.*?)<', ['url', 'thumb', 'title'], headers, patronNext='<a class="next page-numbers" href="([^"]+)">')
else:
itemlist = support.scrape(item, r'<img width[^s]+src="([^"]+)[^>]+>[^>]+>[^>]+>[^>]+><a href="([^"]+)">([^<]+)<\/a>[^>]+>[^>]+>[^>]+>(?:[^>]+>|)[^I]+IMDB\:\s*([^<]+)<', ['thumb', 'url', 'title', 'rating'], headers, patronNext='<a class="next page-numbers" href="([^"]+)">')
for item in itemlist:
item.title = re.sub(r'.\(.*?\)', '', item.title)
return itemlist
def video(item):
logger.info('[filmsenzalimiti.py] video')
itemlist = []
patron = '<div class="col-mt-5 postsh">.*?<a href="([^"]+)" title="([^"]+)">.*?<span class="rating-number">(.*?)<.*?<img src="([^"]+)"'
patronNext = '<a href="([^"]+)"><i class="glyphicon glyphicon-chevron-right"'
support.scrape(item,
itemlist,
patron, ['url', 'title', 'rating', 'thumb'],
patronNext=patronNext)
return itemlist
def peliculas_list(item):
support.log()
block = r'<tbody>(.*)<\/tbody>'
patron = r'<td class="mlnh-thumb"><a href="([^"]+)" title="([^"]+)".*?> <img.*?src="([^"]+)".*?<td class="mlnh-3">([0-9]+)<\/td><td class="mlnh-4">(.*?)<\/td>'
return support.scrape(item,
patron, ['url', 'title', 'year', 'quality'],
patron_block=block)
def generos(item):
patron = '<a href="([^"#]+)">([a-zA-Z]+)'
return support.scrape(
item,
patron, ['url', 'title'],
patron_block='<a href="#">Genere</a><ul class="sub-menu">.*?</ul>',
action='peliculas')
def peliculas(item):
support.log()
if item.contentType == 'movie' or '/serietv/' not in item.url:
patron = r'<div class="?card-image"?>.*?<img src="?([^" ]+)"? alt.*?<a href="?([^" >]+)(?:\/|")>([^<[(]+)(?:\[([A-Za-z0-9/-]+)])? (?:\(([0-9]{4})\))?.*?<strong>([^<>&]+).*?DURATA ([0-9]+).*?<br(?: /)?>([^<>]+)'
listGroups = [
'thumb', 'url', 'title', 'quality', 'year', 'genre', 'duration',
'plot'
]
action = 'findvideos'
else:
patron = r'div class="card-image">.*?<img src="([^ ]+)" alt.*?<a href="([^ >]+)">([^<[(]+)<\/a>.*?<strong><span style="[^"]+">([^<>0-9(]+)\(([0-9]{4}).*?<\/(p|div)>([^<>]+)'
listGroups = ['thumb', 'url', 'title', 'genre', 'year', 'plot']
action = 'episodios'
return support.scrape(
item,
patron_block=[
r'<div class="?sequex-page-left"?>(.*?)<aside class="?sequex-page-right"?>',
'<div class="?card-image"?>.*?(?=<div class="?card-image"?>|<div class="?rating"?>)'
],
patron=patron,
listGroups=listGroups,
patronNext=
'<a class="?page-link"? href="?([^>]+)"?><i class="fa fa-angle-right">',
blacklist=blacklist,
action=action)
def genres(item):
return support.scrape(
item,
patron_block=r'<div id="bordobar" class="dropdown-menu(.*?)</li>',
patron=r'<a class="dropdown-item" href="([^"]+)" title="([A-z]+)"',
listGroups=['url', 'title'],
action='video')
def last_ep(item):
log('ANIME PER TUTTI')
return support.scrape(
item,
'<a href="([^"]+)">([^<]+)<', ['url', 'title'],
patron_block='<ul class="mh-tab-content-posts">(.*?)<\/ul>',
action='findvideos')
def genres(item):
itemlist = support.scrape(
item,
'<a href="([^"]+)">([^<]+)<', ['url', 'title'],
action='peliculas',
patron_block=r'Generi.*?<ul.*?>(.*?)<\/ul>',
blacklist=['Contattaci', 'Privacy Policy', 'DMCA'])
return support.thumb(itemlist)
def year(item):
findhost()
patron = r'<a href="([^"#]+)">(\d+)'
return support.scrape(
item,
patron, ['url', 'title'],
patron_block='<a href="#">Anno</a><ul class="sub-menu">.*?</ul>',
action='peliculas',
url_host=host)
def peliculas(item):
return support.scrape(
item,
r'<h2>(.*?)</h2>\s*<img src="([^"]+)" alt="[^"]*" />\s*<A HREF="([^"]+)">',
['title', 'thumb', 'url'],
headers,
patronNext=
r"<span class='current'>\d+</span><a rel='nofollow' class='page larger' href='([^']+)'>\d+</a>",
action='episodios')
def AZlist(item):
support.log()
return support.scrape(
item,
r'<a title="([^"]+)" href="([^"]+)"', ['title', 'url'],
headers,
patron_block=r'<div class="movies-letter">(.*?)<\/div>',
action='peliculas_list',
url_host=host)
def episodios(item):
item.contentType = 'episode'
return support.scrape(
item,
patron_block=[
r'<article class="sequex-post-content">(.*?)<\/article>',
r'<div class="sp-head[a-z ]*?" title="Espandi">[^<>]*?</div>(.*?)<div class="spdiv">\[riduci\]</div>'
],
patron='<p>([0-9]+(?:×|×)[0-9]+)(.*?)(?:<\/p>|<br)',
listGroups=['title', 'url'])
def peliculas(item):
item.contentType = 'episode'
return support.scrape(
item,
r'<h2>(.*?)</h2>\s*<img src="([^"]+)" alt="[^"]*" />\s*<A HREF="([^"]+)">.*?<span class="year">([0-9]{4}).*?<span class="calidad">([A-Z]+)',
['title', 'thumb', 'url', 'year', 'quality'],
headers,
patronNext=
r"<span class='current'>\d+</span><a rel='nofollow' class='page larger' href='([^']+)'>\d+</a>",
action='episodios')
def newest(categoria):
findhost()
itemlist = []
item = Item()
item.url = host + '/lista-film-ultimi-100-film-aggiunti/'
return support.scrape(
item,
r'<a href=([^>]+)>([^<([]+)(?:\[([A-Z]+)\])?\s\(([0-9]{4})\)<\/a>',
['url', 'title', 'quality', 'year'],
patron_block=r'Ultimi 100 film aggiunti:.*?<\/td>')
def genre(item):
itemlist = support.scrape(item,
'<a href="([^"]+)">([^<]+)</a>',
['url', 'title'],
headers, [
'Serie TV', 'Serie TV Americane',
'Serie TV Italiane', 'altadefinizione'
],
action='peliculas')
return thumb(itemlist)
def menu(item):
support.log()
itemlist = support.scrape(item,
'<li><a href="(.*?)">(.*?)</a></li>',
['url', 'title'],
headers,
patron_block='<ul class="listSubCat" id="' +
str(item.args) + '">(.*?)</ul>',
action='peliculas')
return support.thumb(itemlist)
def categories(item):
support.log(item)
itemlist = support.scrape(
item,
'<li><a href="([^"]+)">(.*?)</a></li>', ['url', 'title'],
headers,
'Altadefinizione01',
patron_block='<ul class="kategori_list">(.*?)</ul>',
action='peliculas',
url_host=host)
return support.thumb(itemlist)
def menu(item):
patron_block = r'<ul class="sub-menu">.*?</ul>'
patron = r'menu-category-list"><a href="([^"]+)">([^<]+)<'
list_groups = ["url", "title"]
return support.scrape(item,
patron,
list_groups,
blacklist="Anime",
action="peliculas_menu",
patron_block=patron_block)
def episodios(item):
patron = r'<td class="MvTbTtl"><a href="([^"]+)">(.*?)<\/a>.*?>\d{4}<'
list_groups = ["url", "title", "year"]
itemlist = support.scrape(item, patron, list_groups)
for itm in itemlist:
fixedtitle = scrapertools.get_season_and_episode(itm.url)
itm.title = fixedtitle + " - " + itm.title
itm.fulltitle = fixedtitle + " - " + itm.fulltitle
return itemlist
def search_peliculas(item):
logger.info(item.channel + 'search_peliculas')
logger.info('TYPE= ' + item.contentType)
if item.contentType == 'movie':
action = 'findvideos'
else:
action = 'episodios'
return support.scrape(
item,
r'<a href="([^"]+)"><span[^>]+><[^>]+><\/a>[^h]+h2>(.*?)<',
["url", "title"],
patronNext="<a rel='nofollow' class=previouspostslink href='([^']+)'",
headers=headers,
action=action)
def peliculas(item):
support.log()
list_groups = ["url", "thumb", "title", "year", "rating", "duration"]
patron = r'<article.*?"TPost C".*?href="([^"]+)".*?img.*?src="([^"]+)".*?<h3.*?>([^<]+).*?Year">'
if item.args == "latests":
patron += r'([^<]+)'
else:
patron += r'(\d{4}).*?AAIco-star.*?>([^<]+).*?AAIco-access_time">([^<]+).*?Qlty'
patron_next = r'page-numbers current.*?href="([^"]+)"'
if item.contentType == "movie":
patron += r'\">([^<]+)'
list_groups.append("quality")
action = "findvideos" if item.contentType == "movie" else "episodios"
return support.scrape(item,
patron,
list_groups,
patronNext=patron_next,
action=action)
