def _extract_list(doc):
rtree = select_all(doc, 'tr.forum_header_border[name="hover"]')
results = []
for l in rtree:
el = select_one(l, 'a.epinfo')
title = get_text(el)
img = '/img/icons/film.svg'
el = select_one(l, 'a.magnet')
url = get_attr(el, 'href')
if url is None:
continue
subs = series_season_episode(title)
tds = select_all(l, 'td')
seeds = get_text(select_one(tds[-1], 'font'))
if not seeds:
seeds = '0'
released = get_text(tds[-2])
size = get_text(tds[-3])
if not size:
size = 'NA'
result = {}
result['title'] = title
result['img'] = img
result['url'] = url
result['subs'] = subs
result['seeds'] = seeds
result['released'] = released
result['size'] = size
results.append(result)
return results
def _extract(doc):
rtree = select_all(doc, 'li.list-item')
results = PlayItemList()
for l in rtree:
a = select_one(l, 'a')
url = get_attr(a, 'href')
if url is None or not url.startswith('/iplayer'):
continue
url = "http://www.bbc.co.uk" + url
pdiv = select_one(l, 'div.primary')
idiv = select_one(pdiv, 'div.r-image')
img = get_attr(idiv, 'data-ip-src')
sdiv = select_one(l, 'div.secondary')
title = get_text(select_one(sdiv, 'div.title'))
subtitle = get_text(select_one(sdiv, 'div.subtitle'))
synopsis = get_text(select_one(sdiv, 'p.synopsis'))
item = PlayItem(title, img, url, subtitle, synopsis)
a = select_one(l, 'a.view-more-container')
if a is not None:
link = "http://bbc.co.uk" + a.get('href')
item.add_action(MoreEpisodesAction(link, title))
results.add(item)
return results
def search(q):
q = q.replace(' ', '-')
q = q.replace("'", '')
doc = get_doc(_SEARCH_URL + q)
rtree = select_all(doc, 'div.search-wrapper')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'div.remaining-time')
if el is not None and get_text(el).strip() == 'unavailable':
continue
el = select_one(l, 'h4 a')
url = get_attr(el, 'href')
title = get_text(el)
el = select_one(l, "div.search-result-image a img")
img = get_attr(el, 'src')
el = select_one(l, ".search-episode-count")
matched = int(get_attr(el, 'data-matched_episodes'))
episodes = get_text(el)
episodes = int(episodes[0:episodes.find(' ')])
action = None
if episodes > matched:
action = MoreEpisodesAction(url, title)
eps = select_all(l, ".episode")
for e in eps:
el = select_one(e, ".episode-title a")
url = _PREFIX + get_attr(el, 'href')
subtitle = get_text(el)
el = select_one(e, ".description")
synopsis = get_text_content(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
if action:
item.add_action(action)
break
return results
def _extract(doc):
rtree = select_all(doc, 'li.browse-content-item-videos')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
href = get_attr(el, 'href')
if href is None:
continue
url = _PREFIX + href
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.browse-content-top-line')
subtitle = get_text(el)
el = select_one(l, 'div.browse-content-second-line')
title = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = get_attr(el, 'href')
if not url.startswith('/talks/'):
continue
url = _PREFIX + url
title = get_text(el)
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.search__result__description')
synopsis = get_text(el)
results.add(PlayItem(title, img, url, synopsis=synopsis))
return results
def _extract(doc):
rtree = select_all(doc, 'li.browse-content-item-videos')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
href = get_attr(el, 'href')
if href is None:
continue
url = _PREFIX + href
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.browse-content-top-line')
subtitle = get_text(el)
el = select_one(l, 'div.browse-content-second-line')
title = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = get_attr(el, 'href')
if not url.startswith('/talks/'):
continue
url = _PREFIX + url
title = get_text(el)
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.search__result__description')
synopsis = get_text(el)
results.add(PlayItem(title, img, url, synopsis=synopsis))
return results
def search(q):
q = q.replace(' ', '-')
q = q.replace("'", '')
doc = get_doc(_SEARCH_URL + q)
rtree = select_all(doc, 'div.search-wrapper')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'h4 a')
url = get_attr(el, 'href')
title = get_text(el)
el = select_one(l, "div.search-result-image a img")
img = get_attr(el, 'src')
el = select_one(l, ".search-episode-count")
matched = int(get_attr(el, 'data-matched_episodes'))
episodes = get_text(el)
episodes = int(episodes[0:episodes.find(' ')])
action = None
if episodes > matched:
action = MoreEpisodesAction(url, title)
eps = select_all(l, ".episode")
for e in eps:
el = select_one(e, ".episode-title a")
url = _PREFIX + get_attr(el, 'href')
subtitle = get_text(el)
el = select_one(e, ".description")
synopsis = get_text_content(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
if action:
item.add_action(action)
break
return results
def _extract(doc):
rtree = select_all(doc, 'li.list-item')
results = PlayItemList()
for l in rtree:
a = select_one(l, 'a')
url = get_attr(a, 'href')
if url is None:
continue
if url.startswith('/iplayer'):
url = "http://www.bbc.co.uk" + url
pdiv = select_one(l, 'div.primary')
idiv = select_one(pdiv, 'div.r-image')
if idiv is None:
idiv = select_one(pdiv, 'div.rs-image')
idiv = select_one(idiv, 'source')
img = get_attr(idiv, 'srcset')
else:
img = get_attr(idiv, 'data-ip-src')
sdiv = select_one(l, 'div.secondary')
title = get_text(select_one(sdiv, 'div.title'))
subtitle = get_text(select_one(sdiv, 'div.subtitle'))
synopsis = get_text(select_one(sdiv, 'p.synopsis'))
item = PlayItem(title, img, url, subtitle, synopsis)
a = select_one(l, 'a.view-more-container')
if a is not None:
link = "http://bbc.co.uk" + a.get('href')
item.add_action(MoreEpisodesAction(link, title))
results.add(item)
return results
def _extract_popular(doc):
rtree = select_all(doc, 'li.most-popular__item')
results = PlayItemList()
for l in rtree:
a = select_one(l, 'a')
url = get_attr(a, 'href')
if url is None:
continue
if url.startswith('/iplayer'):
url = "http://www.bbc.co.uk" + url
idiv = select_one(l, 'div.rs-image')
idiv = select_one(idiv, 'source')
img = get_attr(idiv, 'srcset')
img = img.split()[0]
idiv = select_one(l, 'div.content-item__info__text')
title = get_text(select_one(idiv, 'div.content-item__title'))
pdiv = select_one(idiv, 'div.content-item__info__primary')
subtitle = get_text(select_one(pdiv, 'div.content-item__description'))
pdiv = select_one(idiv, 'div.content-item__info__secondary')
synopsis = get_text(select_one(pdiv, 'div.content-item__description'))
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
return results
def _extract_showlist(doc):
rtree = select_all(doc, 'tr[name="hover"]')
img = None
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a.thread_link')
title = get_text(el)
url = get_attr(el, 'href')
el = select_one(l, 'b')
rating = get_text(el)
subtitle = "Rating: " + rating
item = ShowMoreItem(title, img, url, subtitle)
results.add(item)
return results
def feed(idx):
doc = get_doc(_FEEDLIST[idx]['url'])
rtree = select_all(doc, 'div.post-block')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = get_attr(el, 'href')
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.post-block__content')
subtitle = get_text(el)
el = select_one(l, 'a.post-block__title__link')
title = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
def feed(idx):
doc = get_doc(_FEEDLIST[idx]['url'])
rtree = select_all(doc, 'div.thumbs li')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = get_attr(el, 'href')
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'h4.talk-link__speaker')
subtitle = get_text(el)
el = select_one(l, 'a span')
title = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
def feed(idx):
url = _FEEDLIST[idx]['url']
doc = get_doc(url)
rtree = select_all(doc, "a.complex-link")
results = PlayItemList()
for l in rtree:
url = get_attr(l, 'href')
el = select_one(l, '.tout__title')
if el is None:
continue
title = get_text(el)
el = select_one(l, 'img.fluid-media__media')
img = get_attr(el, 'src')
el = select_one(l, 'p.tout__meta')
subtitle = get_text_content(el)
if subtitle == 'No episodes available':
continue
item = PlayItem(title, img, url, subtitle)
if subtitle != '1 episode':
item.add_action(MoreEpisodesAction(url, title))
results.add(item)
if idx == 0:
global _SHOWLIST
_SHOWLIST = results
return results
def search(q):
session = new_session()
doc = get_doc(_SEARCH_URL + q, session=session)
title = get_text(select_one(doc, 'head > title'))
if title.startswith('Cookies - '):
doc = get_doc(_SEARCH_URL + q, session=session)
return _extract_sort(doc)
def feed(idx):
url = _FEEDLIST[idx]['url']
doc = get_doc(url)
rtree = select_all(doc, "a.complex-link")
results = PlayItemList()
for l in rtree:
url = get_attr(l, 'href')
el = select_one(l, '.tout__title')
if el is None:
continue
title = get_text(el)
el = select_one(l, 'img.fluid-media__media')
img = get_attr(el, 'src')
el = select_one(l, 'p.tout__meta')
subtitle = get_text_content(el)
if subtitle == 'No episodes available':
continue
item = PlayItem(title, img, url, subtitle)
if subtitle != '1 episode':
item.add_action(MoreEpisodesAction(url, title))
results.add(item)
if idx == 0:
global _SHOWLIST
_SHOWLIST = results
return results
def feed(idx):
url = _FEEDLIST[idx]['url']
doc = get_doc(url)
rtree = select_all(doc, 'li.programme')
results = PlayItemList()
for l in rtree:
el = select_one(l, '.programme-title a')
url = _PREFIX + get_attr(el, 'href')
title = get_text(el)
el = select_one(l, 'img')
img = get_attr(el, 'src')
subtitle = get_text(select_one(l, '.episode-info span.episode-free'))
item = PlayItem(title, img, url, subtitle)
if (subtitle is not None) and (not subtitle.startswith('1 ')):
item.add_action(MoreEpisodesAction(url, title))
results.add(item)
return results
def search(q):
doc = get_doc(_SEARCH_URL, params={'q': q})
rtree = select_all(doc, 'article.search__result')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = get_attr(el, 'href')
if not url.startswith('/talks/'):
continue
url = _PREFIX + url
title = get_text(el)
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'div.search__result__description')
synopsis = get_text(el)
results.add(PlayItem(title, img, url, synopsis=synopsis))
return results
def showmore(link):
doc = get_doc(link)
rtree = select_all(doc, "a.complex-link")
results = PlayItemList()
for l in rtree:
url = get_attr(l, 'href')
el = select_one(l, 'img.fluid-media__media')
img = get_attr(el, 'src')
el = select_one(l, 'h3')
title = get_text(el)
el = select_one(l, 'time')
subtitle = get_text(el)
el = select_one(l, 'p.tout__summary')
synopsis = get_text(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
return results
def showmore(link):
doc = get_doc(link)
rtree = select_all(doc, "a.complex-link")
results = PlayItemList()
for l in rtree:
url = get_attr(l, 'href')
el = select_one(l, 'img.fluid-media__media')
img = get_attr(el, 'src')
el = select_one(l, 'h3')
title = get_text(el)
el = select_one(l, 'time')
subtitle = get_text(el)
el = select_one(l, 'p.tout__summary')
synopsis = get_text(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
return results
def feed(idx):
url = _FEEDLIST[idx]['url']
doc = get_doc(url)
rtree = select_all(doc, 'li.programme')
results = PlayItemList()
for l in rtree:
el = select_one(l, '.programme-title a')
url = _PREFIX + get_attr(el, 'href')
title = get_text(el)
el = select_one(l, 'img')
img = get_attr(el, 'src')
subtitle = get_text(select_one(l, '.episode-info span.episode-free'))
item = PlayItem(title, img, url, subtitle)
if (subtitle is not None) and (not subtitle.startswith('1 ')):
item.add_action(MoreEpisodesAction(url, title))
results.add(item)
return results
def _extract_list(doc):
rtree = select_all(doc, 'tr')
results = []
for l in rtree:
el = select_one(l, 'a.torrents_table__torrent_title > b')
# tr is not a result
if el is None:
continue
title = get_text(el)
el = select_one(l, 'a[title="Torrent magnet link"]')
# DMCA takedown
if el is None:
continue
url = get_attr(el, 'href')
img = '/img/icons/film.svg'
el = select_one(
l, 'span.torrents_table__upload_info > a.text--muted > strong')
cat = get_text(el)
if not (cat in _CAT_WHITELIST):
continue
if cat.endswith('Music'):
img = '/img/icons/music.svg'
subs = None
if cat == 'Movies':
subs = movie_title_year(title)
elif cat == 'TV':
subs = series_season_episode(title)
el = select_one(l, 'td[data-title="Size"]')
size = get_text_content(el)
el = select_one(l, 'td[data-title="Seed"]')
seeds = get_text(el)
el = select_one(l, 'td[data-title="Leech"]')
peers = get_text(el)
result = {}
result['title'] = title
result['url'] = url
result['img'] = img
result['subs'] = subs
result['size'] = size
result['seeds'] = seeds
result['peers'] = peers
results.append(result)
return results
def _extract(doc):
results = PlayItemList()
rtree = select_all(doc, 'div.col')
for r in rtree:
el = select_one(r, "h4")
title = get_text(el)
if not title:
continue
el = select_one(r, "img")
img = get_attr(el, "src")
el = select_one(r, "a.js-click-video")
url = get_attr(el, "href")
results.add(PlayItem(title, img, url))
return results
def _extract(doc):
rtree = select_all(doc, '#browse_content li a')
results = PlayItemList()
for l in rtree:
url = _PREFIX + l.get('href')
title = get_attr(l, 'title')
if title is None:
break
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'time')
subtitle = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
def _extract(doc):
rtree = select_all(doc, '#browse_content li a')
results = PlayItemList()
for l in rtree:
url = _PREFIX + l.get('href')
title = get_attr(l, 'title')
if title is None:
break
el = select_one(l, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'time')
subtitle = get_text(el)
results.add(PlayItem(title, img, url, subtitle))
return results
def _extract(doc):
results = PlayItemList()
rtree = select_all(doc, 'tr')
first = True
for l in rtree:
if first:
first = False
continue
el = select_one(l, "a[title='More from this category']")
maincat = get_text(el)
img = '/img/icons/film.svg'
if maincat is not None:
if maincat == 'Video':
img = '/img/icons/film.svg'
elif maincat == 'Audio':
img = '/img/icons/music.svg'
else:
continue
el = select_one(l, 'a.detLink')
title = get_text(el)
el = select_one(l, "a[title='Download this torrent using magnet']")
url = get_attr(el, 'href')
el = select_one(l, 'font.detDesc')
desc = get_text(el)
start = desc.find(', Size ')
if start == -1:
continue
start = start + 7
end = desc.find(',', start)
if end == -1:
continue
size = desc[start:end].replace("iB", "B")
el = select_one(l, "td:nth-child(3)")
seeds = get_text(el)
el = select_one(l, "td:nth-child(4)")
peers = get_text(el)
subtitle = chanutils.torrent.subtitle(size, seeds, peers)
subcat = "Movies"
el = select_one(l, ":nth-child(3)")
if el.text is not None:
subcat = get_text(el)
subs = None
if subcat.endswith("Movies"):
subs = movie_title_year(title)
elif subcat.endswith("shows"):
subs = series_season_episode(title)
if not url:
continue
results.add(TorrentPlayItem(title, img, url, subtitle, subs=subs))
return results
def showmore(link):
doc = get_doc(link)
rtree = select_all(doc, 'div.views-row')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = _PREFIX + get_attr(el, 'href')
el = select_one(el, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'span.date-display-single')
subtitle = get_text(el)
el = select_one(l, 'div.field-season-number')
title1 = get_text_content(el)
el = select_one(l, 'div.field-episode-number')
title = title1 + " " + get_text_content(el)
el = select_one(l, 'div.field-name-field-short-synopsis')
synopsis = get_text_content(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
return results
def showmore(link):
doc = get_doc(link)
rtree = select_all(doc, 'div.views-row')
results = PlayItemList()
for l in rtree:
el = select_one(l, 'a')
url = _PREFIX + get_attr(el, 'href')
el = select_one(el, 'img')
img = get_attr(el, 'src')
el = select_one(l, 'span.date-display-single')
subtitle = get_text(el)
el = select_one(l, 'div.field-season-number')
title1 = get_text_content(el)
el = select_one(l, 'div.field-episode-number')
title = title1 + " " + get_text_content(el)
el = select_one(l, 'div.field-name-field-short-synopsis')
synopsis = get_text_content(el)
item = PlayItem(title, img, url, subtitle, synopsis)
results.add(item)
return results
def feed(idx):
url = _FEEDLIST[idx]['url']
doc = get_doc(url)
livetree = select_all(doc, "div.genie-container")
results = PlayItemList()
for l in livetree:
img = get_attr(l, "data-video-posterframe")
title = get_attr(l, "data-video-channel-id")
item = PlayItem(title.upper(), img, url, 'Watch LIVE TV')
results.add(item)
rtree = select_all(doc, "a.complex-link")
for l in rtree:
url = get_attr(l, 'href')
el = select_one(l, '.tout__title')
if el is None:
el = select_one(l, '.slice__title')
if el is None:
continue
title = get_text(el)
el = select_one(l, 'img.fluid-media__media')
img = get_attr(el, 'src')
el = select_one(l, 'p.tout__summary')
if el is None:
el = select_one(l, 'p.tout__meta')
if el is None:
el = select_one(l, 'p.slice__meta')
subtitle = get_text_content(el)
if subtitle == 'No episodes available':
continue
item = PlayItem(title, img, url, subtitle)
if subtitle != '1 episode':
item.add_action(MoreEpisodesAction(url, title))
results.add(item)
return results
def _extract(doc):
rtree = select_all(doc, 'div.thumb-block')
results = PlayItemList()
for l in rtree:
ti = select_one(l, 'div.thumb-inside')
ael = select_one(ti, 'a')
url = _ROOT_URL + get_attr(ael, 'href')
imgel = select_one(ael, 'img')
img = get_attr(imgel, 'data-src')
img = img.replace('THUMBNUM', '2')
tu = select_one(l, 'div.thumb-under')
el = select_one(tu, 'a')
title = get_text(el)
el = select_one(tu, 'p.metadata')
lxml.etree.strip_tags(el, '*')
strings = el.text.replace('\n', ' ').split(' ')
strings = [x for x in strings if x.strip()]
if len(strings) == 2:
size = strings[0]
rating = "NA"
duration = strings[1]
elif len(strings) == 3:
size = strings[0]
rating = strings[1]
duration = strings[2]
elif len(strings) == 4:
size = strings[0]
rating = strings[1]
duration = strings[2] + " " + strings[3]
subtitle = _subtitle({
'Duration': duration,
'Size': size,
'Rating': rating
})
results.add(PlayItem(title, img, url, subtitle))
return results
