def _search_person_cb(what):
print "searching for " + what
page = util.request(BASE_URL + "hledat/complete-films/?q=" + urllib.quote(what))
results = []
data = util.substr(page, '<div id="search-creators', '<div class="footer')
for m in re.finditer(
'<h3 class="subject"[^<]+<a href="(?P<url>[^"]+)[^>]+>(?P<name>[^<]+).+?<p>(?P<info>[^<]+)',
data,
re.DOTALL | re.IGNORECASE,
):
results.append((m.group("url"), m.group("name") + " (" + m.group("info") + ")"))
for m in re.finditer(
"<li(?P<item>.+?)</li>", util.substr(data, '<ul class="creators others', "</div"), re.DOTALL | re.IGNORECASE
):
base = re.search('<a href="(?P<url>[^"]+)[^>]+>(?P<name>[^<]+)', m.group("item"))
if base:
name = base.group("name")
for n in re.finditer("<span[^>]*>(?P<data>[^<]+)", m.group("item")):
name = "%s %s" % (name, n.group("data"))
results.append((base.group("url"), name))
for url, name in results:
info = scrapper._empty_info()
info["url"] = url
add_person(name, info)
xbmcplugin.endOfDirectory(int(sys.argv[1]))
def list_show_page(self, url, page, seasons=False, episodes=False):
result = []
if "/p/epizody" in url or "/p/epiz%C3%B3dy" in url or "p/archiv" in url:
if seasons:
season_data = util.substr(page, SERIES_START2, SERIES_END2)
for m in re.finditer(SERIES_ITER_RE2, season_data, re.DOTALL | re.IGNORECASE):
item = self.dir_item()
item['title'] = m.group('title')
item['url'] = url + '#post=%s' % (m.group('id'))
self._filter(result, item)
if episodes:
for m in re.finditer(EPISODE_ITER_RE2, page, re.DOTALL | re.IGNORECASE):
item = self.video_item()
item['title'] = "%s (%s)" % (m.group('title'), m.group('date'))
item['url'] = m.group('url')
self._filter(result, item)
else:
if seasons:
season_data = util.substr(page, SERIES_START, SERIES_END)
for m in re.finditer(SERIES_ITER_RE, season_data, re.DOTALL | re.IGNORECASE):
item = self.dir_item()
item['title'] = m.group('title')
item['url'] = 'http://' + urlparse.urlparse(url).netloc + '/ajax.json?' + m.group('url')
self._filter(result, item)
if episodes:
episodes_data = util.substr(page, EPISODE_START, EPISODE_END)
for m in re.finditer(EPISODE_ITER_RE, page, re.DOTALL | re.IGNORECASE):
item = self.video_item()
item['title'] = "%s. %s (%s)" % (m.group('episode'), m.group('title'), m.group('date'))
item['url'] = m.group('url')
self._filter(result, item)
return result
def _search_movie_cb(what):
print "searching for movie " + what
url = BASE_URL + "hledat/complete-films/?q=" + urllib.quote(what)
page = util.request(url)
results = []
data = util.substr(page, '<div id="search-films', '<div class="footer')
for m in re.finditer(
'<h3 class="subject"[^<]+<a href="(?P<url>[^"]+)[^>]+>(?P<name>[^<]+).+?<p>(?P<info>[^<]+)',
data,
re.DOTALL | re.IGNORECASE,
):
results.append((m.group("url"), "%s (%s)" % (m.group("name"), m.group("info"))))
for m in re.finditer(
"<li(?P<item>.+?)</li>", util.substr(data, '<ul class="films others', "</div"), re.DOTALL | re.IGNORECASE
):
base = re.search('<a href="(?P<url>[^"]+)[^>]+>(?P<name>[^<]+)', m.group("item"))
if base:
name = base.group("name")
for n in re.finditer("<span[^>]*>(?P<data>[^<]+)", m.group("item")):
name = "%s %s" % (name, n.group("data"))
results.append((base.group("url"), name))
if preload():
return preload_items(results)
add_items(results)
xbmcplugin.endOfDirectory(int(sys.argv[1]))
def list_episodes(self, url, page=0):
result = []
if url.find('ajax.json') != -1:
headers = {'X-Requested-With':'XMLHttpRequest',
'Referer':util.substr(url, url, url.split('/')[-1])
}
httpdata = util.request(url, headers)
httpdata = util.json.loads(httpdata)['content']
else:
httpdata = util.request(url)
httpdata = util.substr(httpdata, EPISODE_START, EPISODE_END)
entries = 0
skip_entries = MAX_PAGE_ENTRIES * page
for m in re.finditer(EPISODE_ITER_RE, httpdata, re.DOTALL | re.IGNORECASE):
entries += 1
if entries < skip_entries:
continue
item = self.video_item()
item['title'] = "%s. %s (%s)" % (m.group('episode'), m.group('title'), m.group('date'))
item['url'] = m.group('url')
self._filter(result, item)
if entries >= (skip_entries + MAX_PAGE_ENTRIES):
page += 1
item = self.dir_item()
item['type'] = 'next'
item['url'] = "#episodes##%d#" % (page) + url
result.append(item)
break
return result
def show(self, page):
result = []
data = util.substr(page, '<div id="search', "<hr>")
for m in re.finditer(
'<div.+?class="scene[^>]*>.+?<img src="(?P<img>[^"]+)" alt="(?P<name>[^"]+).+?<div class="sc-name">(?P<author>[^<]+).+?<a href="(?P<url>[^"]+)',
data,
re.IGNORECASE | re.DOTALL,
):
name = "%s (%s)" % (m.group("name"), m.group("author"))
item = self.video_item()
item["title"] = name
item["url"] = m.group("url")
item["img"] = m.group("img")
self._filter(result, item)
data = util.substr(page, 'class="pages">', "</div>")
next = re.search('<a href="(?P<url>[^"]+)"[^<]+<img src="/images/page-right.gif', data)
prev = re.search('<a href="(?P<url>[^"]+)"[^<]+<img src="/images/page-left.gif', data)
if prev:
item = self.dir_item()
item["type"] = "prev"
item["url"] = prev.group("url")
result.append(item)
if next:
item = self.dir_item()
item["type"] = "next"
item["url"] = next.group("url")
result.append(item)
return result
def list(self,url):
result = []
url = self._url(url)
page = util.request(url)
q = url.find('?')
if q > 0:
url = url[:q]
data = util.substr(page,'<div id=\"videolist','<div class=\"paging-adfox\">')
pattern='<div class=\"img-wrapper\"><a href=\"(?P<url>[^\"]+)\" title=\"(?P<name>[^\"]+)(.+?)<img(.+?)src=\"(?P<img>[^\"]+)(.+?)<p class=\"dsc\">(?P<plot>[^<]+)'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
item = self.video_item()
item['title'] = m.group('name')
item['url'] = m.group('url')
item['img'] = m.group('img')
item['plot'] = m.group('plot')
self._filter(result,item)
data = util.substr(page,'<div class=\"jumpto\"','</div>')
data = util.substr(page,'<p class=\"paging','</p>')
next = re.search('<a href=\"(?P<url>[^\"]+)\"><img(.+?)next\.png',data,re.IGNORECASE | re.DOTALL)
if next:
item = self.dir_item()
item['type'] = 'next'
item['url'] = url+next.group('url')
result.append(item)
return result
def list_archive_page(self, show_page, showon=False, showoff=False):
showonlist = []
if showon:
page = util.substr(show_page, VYSIELANE_START, NEVYSIELANE_START)
for m in re.finditer(VYSIELANE_ITER_RE, page, re.DOTALL | re.IGNORECASE):
item = self.dir_item()
item['title'] = m.group('title')
item['plot'] = m.group('desc')
item['url'] = m.group('url') + "#season_episode"
if m.group('itime') is not None:
item['type'] = "showon7d"
else:
item['type'] = "showon"
showonlist.append(item)
showonlist.sort(key=lambda x: x['title'].lower())
showofflist = []
if showoff:
page = util.substr(show_page, NEVYSIELANE_START, NEVYSIELANE_END)
for m in re.finditer(NEVYSIELANE_ITER_RE, page, re.DOTALL | re.IGNORECASE):
item = self.dir_item()
item['title'] = m.group('title')
item['url'] = m.group('url') + "#season_episode"
item['type'] = "showoff"
showofflist.append(item)
showofflist.sort(key=lambda x: x['title'].lower())
result = showonlist + showofflist
return result
def list_by_letter(self, url):
result = []
page = self.get_data_cached(url)
data = util.substr(page, '<ul class=\"content', '</ul>')
subs = self.get_subs()
for m in re.finditer('<a class=\"title\" href=\"(?P<url>[^\"]+)[^>]+>(?P<name>[^<]+)', data,
re.IGNORECASE | re.DOTALL):
item = {'url': m.group('url'), 'title': m.group('name')}
if item['url'] in subs:
item['menu'] = {"[B][COLOR red]Remove from subscription[/COLOR][/B]": {
'url': m.group('url'), 'action': 'remove-subscription', 'name': m.group('name')}
}
else:
item['menu'] = {"[B][COLOR red]Add to library[/COLOR][/B]": {
'url': m.group('url'), 'action': 'add-to-library', 'name': m.group('name')}}
self._filter(result, item)
paging = util.substr(page, '<div class=\"pagination\"', '</div')
next = re.search('<li class=\"next[^<]+<a href=\"\?page=(?P<page>\d+)', paging,
re.IGNORECASE | re.DOTALL)
if next:
next_page = int(next.group('page'))
current = re.search('\?page=(?P<page>\d)', url)
current_page = 0
if self.is_most_popular(url) and next_page > 10:
return result
if current:
current_page = int(current.group('page'))
if current_page < next_page:
url = re.sub('\?.+?$', '', url) + '?page=' + str(next_page)
result += self.list_by_letter(url)
return result
def list_content(self, page, url=None):
result = []
if not url: url = self.base_url
data = util.substr(page, '<div class=\"contentArea', '<div class=\"pagination\">')
pattern = '<h\d class=\"postTitle\"><a href=\"(?P<url>[^\"]+)(.+?)<span>(?P<title>[^<]+)</span></a></h\d>(.+?)<span class=\"postDate\">(?P<date>[^\<]+)</span>(.+?)<div class=\"postContent">[^<]+<a[^>]+[^<]+<img src=\"(?P<img>[^\"]+)(.+?)<div class=\"obs\">(?P<plot>.+?)</div>'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
plot = re.sub('<br[^>]*>', '', m.group('plot'))
item = self.video_item()
item['title'] = m.group('title')
item['img'] = m.group('img')
item['plot'] = plot
item['url'] = m.group('url')
self._filter(result, item)
data = util.substr(page, '<div class=\"pagination\">', '</div>')
m = re.search('<li class=\"info\"><span>([^<]+)', data)
n = re.search('<li class=\"prev\"[^<]+<a href=\"(?P<url>[^\"]+)[^<]+<span>(?P<name>[^<]+)', data)
k = re.search('<li class=\"next\"[^<]+<a href=\"(?P<url>[^\"]+)[^<]+<span>(?P<name>[^<]+)', data)
# replace last / + everyting till the end
#myurl = re.sub('\/[\w\-]+$', '/', url)
if not m == None:
if not n == None:
item = self.dir_item()
item['type'] = 'prev'
#item['title'] = '%s - %s' % (m.group(1), n.group('name'))
item['url'] = n.group('url')
result.append(item)
if not k == None:
item = self.dir_item()
item['type'] = 'next'
#item['title'] = '%s - %s' % (m.group(1), k.group('name'))
item['url'] = k.group('url')
result.append(item)
return result
def list_content(self, page, url=None):
result = []
if not url: url = self.base_url
data = util.substr(page, '<div class=\"items no-wrapper no-padder', '<div class=\"my-pagination>')
pattern = '<article class=\"video\".+?<a href=\"(?P<url>[^\"]+)\" *title=\"(?P<title>[^\"]+)\"(.+?)<img src=\"(?P<img>[^\"]+)\".+?<p>(?P<plot>[^<]+?)<\/p>.+?<li class=\"i-published\".+?title=\"(?P<date>[^\"]+)\"'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
item = self.video_item()
item['title'] = m.group('title')
item['img'] = m.group('img').strip()
item['plot'] = self.decode_plot(m.group('plot'))
item['url'] = self.base_url[:-1] + m.group('url')
item['menu'] = {'$30060':{'list':'#related#' + item['url'], 'action-type':'list'}}
print item
self._filter(result, item)
data = util.substr(page, '<ul class=\"my-pagination', '</div>')
n = re.search('<li class=\"paginate_button previous *\"[^<]+<a href=\"(?P<url>[^\"]+)\">(?P<name>[^<]+)<', data)
k = re.search('<li class=\"paginate_button next *\"[^<]+<a href=\"(?P<url>[^\"]+)\">(?P<name>[^<]+)<', data)
if not n == None:
item = self.dir_item()
item['type'] = 'prev'
# item['title'] = '%s - %s' % (m.group(1), n.group('name'))
item['url'] = n.group('url')
result.append(item)
if not k == None:
item = self.dir_item()
item['type'] = 'next'
# item['title'] = '%s - %s' % (m.group(1), k.group('name'))
item['url'] = k.group('url')
result.append(item)
return result
def list_videos(self, url):
result = []
page = util.request(url)
data = util.substr(page, '<div class="articles">','<div class="paginator">')
listing_iter_re = r"""
<article\ class=\"row\">.+?
<a\ href=\"(?P<url>[^\"]+)\"><i\ class=\"ta3-icon-video\"[^>]+>[^>]+>(?P<title>[^<]+)</a>.+?
</article> """
for m in re.finditer(listing_iter_re, data, re.DOTALL | re.VERBOSE):
item = self.video_item()
item['title'] = m.group('title').strip()
#item['title'] = "%s (%s)" % (m.group('title').strip(), m.group('date').strip())
item['url'] = m.group('url')
self._filter(result, item)
pager_data = util.substr(page,'<div class="paginator">', '</div>')
next_page_match = re.search(r'<li class="next"><a href="(?P<url>[^"]+)', pager_data)
if next_page_match:
item = self.dir_item()
item['type'] = 'next'
next_url = next_page_match.group('url').replace('&','&')
# ta3.com gives invalid page urls for publicistika
if "publicistika.html" in url:
purl = urlparse.urlparse(url)
pnext_url = urlparse.urlparse(next_url)
next_url = "http://" + purl.netloc + purl.path + "?" + pnext_url.query
item['url'] = next_url
self._filter(result, item)
return result
def list_content(self, page):
result = []
data = util.substr(page, LISTING_START, LISTING_END)
for m in re.finditer(LISTING_ITER_RE, data, re.DOTALL | re.VERBOSE):
item = self.video_item()
item['title'] = "%s - (%s)" % (m.group('title').strip(), m.group('date').strip())
item['img'] = m.group('img')
item['url'] = m.group('url')
if 'section_title' in m.groupdict() and 'section_url' in m.groupdict():
item['menu'] = {"Sekcia - "+m.group('section_title'):{'list':m.group('section_url'), 'action-type':'list'}}
self._filter(result, item)
pager_data = util.substr(page, PAGER_START, PAGER_END)
for m in re.finditer("<a.+?</a>", pager_data, re.DOTALL):
p = re.search(PAGE_PREV_RE, m.group(), re.DOTALL)
n = re.search(PAGE_NEXT_RE, m.group(), re.DOTALL)
if p:
item = self.dir_item()
item['type'] = 'prev'
item['url'] = p.group('url')
result.append(item)
if n:
item = self.dir_item()
item['type'] = 'next'
item['url'] = n.group('url')
result.append(item)
return result
def list(self,url):
result = []
url = self._url(url)
print url
page = util.request(url)
data = util.substr(page,'<div id=\"archive','end #archive')
pattern = '<div class=\"cover\"><a href=\"(?P<url>[^\"]+)(.+?)title=\"(?P<name>[^\"]+)(.+?)<img src=\"(?P<logo>[^\"]+)(.+?)<p class=\"postmetadata\">(?P<fired>[^<]+)(.+?)<p>(?P<plot>[^<]+)'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
name = ('%s - %s' % (m.group('name'),m.group('fired').replace('/',''))).strip()
item = self.video_item()
item['title'] = name
item['img'] = m.group('logo')
item['plot'] = m.group('plot')
item['url'] = m.group('url')
self._filter(result,item)
data = util.substr(page,'<div class=\"navigation\">','</div>')
type = 'next'
for m in re.finditer('<a href=\"(.+?)(?P<page>/page/[\d]+)',data,re.IGNORECASE | re.DOTALL):
item = self.dir_item()
item['type'] = type
if type == 'next':
type = 'prev'
item['url'] = m.group('page')
result.append(item)
return result
def list(self, url):
if url.find("#fm#") == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(
url, headers={"X-Requested-With": "XMLHttpRequest", "Referer": url, "Cookie": "uloz-to-id=1561277170;"}
)
script = util.substr(page, "var kn", "</script>")
keymap = None
key = None
k = re.search('{([^\;]+)"', script, re.IGNORECASE | re.DOTALL)
if k:
keymap = json.loads("{" + k.group(1) + '"}')
j = re.search('kapp\(kn\["([^"]+)"', script, re.IGNORECASE | re.DOTALL)
if j:
key = j.group(1)
if not (j and k):
self.error("error parsing page - unable to locate keys")
return []
burl = b64decode("I2h0dHA6Ly9kZWNyLWNlY2gucmhjbG91ZC5jb20vZGVjcnlwdC8/a2V5PSVzJnZhbHVlPSVz")
murl = b64decode("aHR0cDovL2RlY3ItY2VjaC5yaGNsb3VkLmNvbS9kZWNyeXB0Lw==")
data = util.substr(page, '<ul class="chessFiles', "</ul>")
result = []
req = {"seed": keymap[key], "values": keymap}
decr = json.loads(util.post_json(murl, req))
for li in re.finditer('<li data-icon="(?P<key>[^"]+)', data, re.IGNORECASE | re.DOTALL):
body = urllib.unquote(b64decode(decr[li.group("key")]))
m = re.search(
'<li>.+?<div data-icon="(?P<key>[^"]+)[^<]+<img(.+?)src="(?P<logo>[^"]+)(.+?)<div class="fileInfo(?P<info>.+?)</h4>',
body,
re.IGNORECASE | re.DOTALL,
)
if not m:
continue
value = keymap[m.group("key")]
info = m.group("info")
iurl = burl % (keymap[key], value)
item = self.video_item()
item["title"] = ".. title not found.."
title = re.search('<div class="fileName.+?<a[^>]+>(?P<title>[^<]+)', info, re.IGNORECASE | re.DOTALL)
if title:
item["title"] = title.group("title")
size = re.search('<span class="fileSize[^>]+>(?P<size>[^<]+)', info, re.IGNORECASE | re.DOTALL)
if size:
item["size"] = size.group("size").strip()
time = re.search('<span class="fileTime[^>]+>(?P<time>[^<]+)', info, re.IGNORECASE | re.DOTALL)
if time:
item["length"] = time.group("time")
item["url"] = iurl
item["img"] = m.group("logo")
self._filter(result, item)
# page navigation
data = util.substr(page, '<div class="paginator', "</div")
mnext = re.search('<a href="(?P<url>[^"]+)" class="next', data)
if mnext:
item = self.dir_item()
item["type"] = "next"
item["url"] = mnext.group("url")
result.append(item)
return result
def filmoteka(p):
if p["filmoteka"] == "":
data = login()
if data:
userid = get_userid(data)
if userid:
page = util.request(furl(userid + "filmoteka"))
data = util.substr(page, '<select name="filter', "</select>")
for m in re.finditer(
'<option value="(?P<value>[^"]+)[^>]+>(?P<name>[^<]+)', data, re.DOTALL | re.IGNORECASE
):
p["filmoteka"] = userid + "filmoteka/filtr-" + m.group("value")
xbmcutil.add_dir(m.group("name"), p)
xbmcplugin.endOfDirectory(int(sys.argv[1]))
else:
page = login(p["filmoteka"])
data = util.substr(page, '<table class="ui-table-list', "</table")
results = []
for m in re.finditer(
'<tr[^<]+<td>(?P<added>[^<]+)</td[^<]+<td[^<]+<a href="(?P<url>[^"]+)[^>]+>(?P<name>[^<]+)',
data,
re.DOTALL | re.IGNORECASE,
):
results.append((m.group("url"), m.group("name")))
if preload():
return preload_items(results)
add_items(results)
xbmcplugin.endOfDirectory(int(sys.argv[1]))
def list_movie_recently_added(self, url):
result = []
page = self.get_data_cached(url)
data = util.substr(page, '<div class=\"content\"', '</ul>')
for m in re.finditer(
'<a class=\"content-block\" href=\"(?P<url>[^\"]+)\" title=\"(?P<name>[^\"]+)',
data, re.IGNORECASE | re.DOTALL):
item = self.video_item()
item['url'] = m.group('url')
item['title'] = m.group('name')
item['menu'] = {"[B][COLOR red]Add to library[/COLOR][/B]": {
'url': m.group('url'), 'action': 'add-to-library', 'name': m.group('name')}}
self._filter(result, item)
paging = util.substr(page, '<div class=\"pagination\"', '</div')
next = re.search('<li class=\"next[^<]+<a href=\"\?page=(?P<page>\d+)', paging,
re.IGNORECASE | re.DOTALL)
if next:
next_page = int(next.group('page'))
current = re.search('\?page=(?P<page>\d)', url)
current_page = 0
if next_page > 5:
return result
if current:
current_page = int(current.group('page'))
if current_page < next_page:
url = re.sub('\?.+?$', '', url) + '?page=' + str(next_page)
result += self.list_movie_recently_added(url)
return result
def film(self,page):
result=[]
data = util.substr(page,self.od,self.do)
pattern='background: url\((?P<img>.+?)\)[\s|\S]*?<h2><a href=\"(?P<url>.+?)\".[^>]+>(?P<name>.+?)</a></h2>'
for m in re.finditer(pattern,data,re.IGNORECASE | re.DOTALL ):
item = self.video_item()
item['url'] = m.group('url')
item['title'] = m.group('name')
item['img'] = m.group('img')
result.append(item)
data = util.substr(page,'<div class=\'wp-pagenavi\'>','<div id=\"sidebar\">')
pattern='<span class=\'pages\'>(?P<pg>.+?)</span>'
m = re.search(pattern, data, re.IGNORECASE | re.DOTALL)
last_page=''
if not m == None:
last_page=m.group('pg').split(' ')
next_page=int(last_page[1])+1
last_page=last_page[-1]
pattern = 'href=\"(?P<url>.+?)\".?><div class=\"next"></div>'
m = re.search(pattern, data, re.IGNORECASE | re.DOTALL)
next_url=''
if not m == None:
next_url=m.group('url')
try:
item = self.dir_item()
item['title'] = 'Přejít na stranu '+ str(next_page)+' z '+ str(last_page)
item['url'] = '#film#'+next_url
result.append(item)
except:
pass
return result
def resolve(self,item,captcha_cb=None,select_cb=None):
item = item.copy()
url = self._url(item['url']).replace('×', '%c3%97')
data = util.substr(util.request(url), '<div id=\"content\"', '#content')
visionone_resolved, onevision_resolved, scz_resolved = [],[],[]
onevision = re.search('(?P<url>http://onevision\.ucoz\.ua/[^<]+)', data, re.IGNORECASE)
if onevision:
onevision_data = util.substr(util.request(onevision.group('url')),'<td class=\"eText\"','<td class=\"rightColumn\"')
onevision_resolved=resolver.findstreams(onevision_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
visionone = re.search('(?P<url>http://visionone\.ucoz\.ru/[^<]+)', data, re.IGNORECASE)
if visionone:
visionone_data = util.substr(util.request(visionone.group('url')),'<td class=\"eText\"','<td class=\"rightColumn\"')
visionone_resolved = resolver.findstreams(visionone_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
scz = re.search('(?P<url>http://scz\.uvadi\.cz/\?p=[\d]+)', data, re.IGNORECASE)
if scz:
scz_data = util.substr(util.request(scz.group('url')),'<div id=\"content\"', '#content')
scz_resolved = resolver.findstreams(scz_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
serialy_resolved = resolver.findstreams(data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>',
'<p><code><strong>(?P<url>http.+?)</strong></code></p>',
'<p><code><strong><big>(?P<url>.+?)</big></strong></code></p>'])
resolved = []
resolved+= serialy_resolved or []
resolved+= visionone_resolved or []
resolved+= onevision_resolved or []
resolved+= scz_resolved or []
resolved = len(resolved) > 0 and resolved or None
result = []
for i in resolved:
item = self.video_item()
item['title'] = i['name']
item['url'] = i['url']
item['quality'] = i['quality']
item['surl'] = i['surl']
item['headers'] = i['headers']
result.append(item)
if len(result) == 1:
return result[0]
elif len(result) > 1 and select_cb:
return select_cb(result)
def list(self,url):
if url.find('#fm#') == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(url,headers={'X-Requested-With':'XMLHttpRequest','Referer':url,'Cookie':'uloz-to-id=1561277170;'})
script = util.substr(page,'var kn','</script>')
keymap = None
key = None
k = re.search('{([^\;]+)"',script,re.IGNORECASE | re.DOTALL)
if k:
keymap = json.loads("{"+k.group(1)+"\"}")
j = re.search('kapp\(kn\[\"([^\"]+)"',script,re.IGNORECASE | re.DOTALL)
if j:
key = j.group(1)
if not (j and k):
self.error('error parsing page - unable to locate keys')
return []
burl = b64decode('I2h0dHA6Ly9jcnlwdG8uamV6em92by5uZXQvZGVjcnlwdC8/a2V5PSVzJnZhbHVlPSVzCg==')
murl = b64decode('aHR0cDovL2NyeXB0by5qZXp6b3ZvLm5ldC9kZWNyeXB0Lwo=')
murl = 'http://crypto.jezzovo.net/decrypt/'
data = util.substr(page,'<ul class=\"chessFiles','</ul>')
result = []
req = {'seed':keymap[key],'values':keymap}
decr = json.loads(util.post_json(murl,req))
for li in re.finditer('<li data-icon=\"(?P<key>[^\"]+)',data, re.IGNORECASE | re.DOTALL):
body = urllib.unquote(b64decode(decr[li.group('key')]))
m = re.search('<li>.+?<div data-icon=\"(?P<key>[^\"]+)[^<]+<img(.+?)src=\"(?P<logo>[^\"]+)(.+?)<div class=\"fileInfo(?P<info>.+?)</h4>',body, re.IGNORECASE | re.DOTALL)
if not m:
continue
value = keymap[m.group('key')]
info = m.group('info')
iurl = burl % (keymap[key],value)
item = self.video_item()
item['title'] = '.. title not found..'
title = re.search('<div class=\"fileName.+?<a[^>]+>(?P<title>[^<]+)',info, re.IGNORECASE|re.DOTALL)
if title:
item['title'] = title.group('title')
size = re.search('<span class=\"fileSize[^>]+>(?P<size>[^<]+)',info, re.IGNORECASE|re.DOTALL)
if size:
item['size'] = size.group('size').strip()
time = re.search('<span class=\"fileTime[^>]+>(?P<time>[^<]+)',info, re.IGNORECASE|re.DOTALL)
if time:
item['length'] = time.group('time')
item['url'] = iurl
item['img'] = m.group('logo')
self._filter(result,item)
# page navigation
data = util.substr(page,'<div class=\"paginator','</div')
mnext = re.search('<a href=\"(?P<url>[^\"]+)\" class="next',data)
if mnext:
item = self.dir_item()
item['type'] = 'next'
item['url'] = mnext.group('url')
result.append(item)
return result
def resolve(self,item,captcha_cb=None,select_cb=None):
item = item.copy()
url = self._url(item['url']).replace('×', '%c3%97')
data = util.substr(util.request(url), '<div id=\"content\"', '#content')
for script in re.finditer('<script.+?src=\"([^\"]+)',data,re.IGNORECASE|re.DOTALL):
try:
data += util.request(script.group(1)).replace('\\\"','\"')
except:
pass
util.init_urllib() # need to reinitialize urrlib, because anyfiles could have left some cookies
visionone_resolved, onevision_resolved, scz_resolved = [],[],[]
onevision = re.search('(?P<url>http://onevision\.ucoz\.ua/[^<]+)', data, re.IGNORECASE)
if onevision:
onevision_data = util.substr(util.request(onevision.group('url')),'<td class=\"eText\"','<td class=\"rightColumn\"')
onevision_resolved=self.findstreams(onevision_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
visionone = re.search('(?P<url>http://visionone\.ucoz\.ru/[^<]+)', data, re.IGNORECASE)
if visionone:
visionone_data = util.substr(util.request(visionone.group('url')),'<td class=\"eText\"','<td class=\"rightColumn\"')
visionone_resolved = self.findstreams(visionone_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
scz = re.search('(?P<url>http://scz\.uvadi\.cz/\?p=[\d]+)', data, re.IGNORECASE)
if scz:
scz_data = util.substr(util.request(scz.group('url')),'<div id=\"content\"', '#content')
scz_resolved = self.findstreams(scz_data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>'])
serialy_resolved = self.findstreams(data, ['<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\'](?P<url>.+?)[\'\"]',
'<object.*?data=(?P<url>.+?)</object>',
'<p><code><strong>(?P<url>http.+?)</strong></code></p>',
'<p><code><strong><big>(?P<url>.+?)</big></strong></code></p>'])
resolved = []
resolved+= serialy_resolved or []
resolved+= visionone_resolved or []
resolved+= onevision_resolved or []
resolved+= scz_resolved or []
resolved = len(resolved) > 0 and resolved or None
if len(resolved) == 1:
return resolved[0]
elif len(resolved) > 1 and select_cb:
return select_cb(resolved)
def list(self,url):
if url.find('#fm#') == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(url,headers={'X-Requested-With':'XMLHttpRequest','Referer':url,'Cookie':'uloz-to-id=1561277170;'}).decode('string-escape')
script = util.substr(page,'var kn','</script>')
keymap = None
key = None
k = re.search(r'({.+?})',script)
if k:
keymap = util.json.loads(k.group(1))
j = re.search(r'ad.push\(\[kn, kn\["([^"]+)', script)
if j:
key = j.group(1)
if not (j and k):
self.error('error parsing page - unable to locate keys')
return []
burl = b64decode('I2h0dHA6Ly9kZWNyLWNlY2gucmhjbG91ZC5jb20vZGVjcnlwdC8/a2V5PSVzJnZhbHVlPSVz')
murl = b64decode('aHR0cDovL2RlY3ItY2VjaC5yaGNsb3VkLmNvbS9kZWNyeXB0Lw==')
result = []
req = {'seed':keymap[key],'values':keymap}
decr = json.loads(util.post_json(murl,req))
for li in re.finditer('<div data-icon=\"(?P<key>[^\"]+)',page, re.IGNORECASE | re.DOTALL):
body = urllib.unquote(b64decode(decr[li.group('key')]))
div_name = util.substr(body, '<div class="name"', '</div>')
title_url_match = re.search(r'<a href="(?P<url>[^"]+)" title="(?P<title>[^"]+)', div_name)
if not title_url_match:
continue
item = self.video_item()
item['title'] = title_url_match.group('title')
item['url'] = title_url_match.group('url')
div_media = util.substr(body, 'div class="media"', '<div class="tools">')
img_match = re.search(r'img src="([^"]+)', div_media)
if img_match:
item['img'] = "http:" + img_match.group(1)
time_match = re.search(r'<span>Čas</span>(.+)', div_media)
if time_match:
item['length'] = time_match.group(1).strip()
size_match = re.search(r'<span>Velikost</span>([^<]+)', div_media)
if size_match:
item['size'] = size_match.group(1).strip()
self._filter(result,item)
# page navigation
data = util.substr(page,'<div class=\"paginator','</div')
mnext = re.search('<a href=\"(?P<url>[^\"]+)\" class="next',data)
if mnext:
item = self.dir_item()
item['type'] = 'next'
item['url'] = util.decode_html(mnext.group('url'))
result.append(item)
return result
def list_subcategories(self, page, category_name):
result = []
data = util.substr(page, CATEGORIES_START, CATEGORIES_END)
data = util.substr(data, category_name, CATEGORIES_END)
for m in re.finditer(CATEGORIES_ITER_RE, data, re.IGNORECASE | re.DOTALL):
if not m.group('type').strip().startswith('child'):
break
item = self.dir_item()
item['title'] = m.group('title')
item['url'] = m.group('url')
self._filter(result, item)
return result
def list(self,url):
if url.find('#fm#') == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(url,headers={'X-Requested-With':'XMLHttpRequest','Referer':url,'Cookie':'uloz-to-id=1561277170;'})
script = util.substr(page,'var kn','</script>')
keymap = None
key = None
k = re.search('{([^\;]+)"',script,re.IGNORECASE | re.DOTALL)
if k:
keymap = json.loads("{"+k.group(1)+"\"}")
j = re.search('kapp\(kn\[\"([^\"]+)"',script,re.IGNORECASE | re.DOTALL)
if j:
key = j.group(1)
if not (j and k):
self.error('error parsing page - unable to locate keys')
return []
burl = b64decode('I2h0dHA6Ly9jcnlwdG8tenNlcnYucmhjbG91ZC5jb20vYXBpL3YyL2RlY3J5cHQvP2tleT0lcyZ2YWx1ZT0lcwo=')
data = util.substr(page,'<ul class=\"chessFiles','</ul>')
result = []
for m in re.finditer('<li>.+?<div data-icon=\"(?P<key>[^\"]+)[^<]+<img(.+?)src=\"(?P<logo>[^\"]+)(.+?)alt=\"(?P<name>[^\"]+)(.+?)<div class=\"fileInfo(?P<info>.+?)</div>',data, re.IGNORECASE | re.DOTALL):
info = m.group('info')
value = keymap[m.group('key')]
iurl = burl % (keymap[key],value)
item = self.video_item()
item['title'] = m.group('name')
size = re.search('<span class=\"fileSize[^>]+>(?P<size>[^<]+)',info, re.IGNORECASE|re.DOTALL)
if size:
item['size'] = size.group('size').strip()
time = re.search('<span class=\"fileTime[^>]+>(?P<time>[^<]+)',info, re.IGNORECASE|re.DOTALL)
if time:
item['length'] = time.group('time')
item['url'] = iurl
item['img'] = m.group('logo')
self._filter(result,item)
# page navigation
data = util.substr(page,'<div class=\"paginator','</div')
mprev = re.search('<a href=\"(?P<url>[^\"]+)\" class=\"prev',data)
if mprev:
item = self.dir_item()
item['type'] = 'prev'
item['url'] = mprev.group('url')
result.append(item)
mnext = re.search('<a href=\"(?P<url>[^\"]+)\" class="next',data)
if mnext:
item = self.dir_item()
item['type'] = 'next'
item['url'] = mnext.group('url')
result.append(item)
return result
def categories(self):
result = []
item = self.dir_item()
item['type'] = 'new'
item['url'] = 'category/new-episode'
result.append(item)
data = util.substr(util.request(self.base_url),'<div id=\"primary\"','<div id=\"secondary')
pattern='<a href=\"(?P<url>[^\"]+)[^>]+>(?P<name>[^<]+)</a>'
for m in re.finditer(pattern, util.substr(data,'Seriály</a>','</ul>'), re.IGNORECASE | re.DOTALL):
item = self.dir_item()
item['title'] = m.group('name')
item['url'] = m.group('url')
result.append(item)
return result
def login(self):
if self.username and self.password and len(self.username) > 0 and len(self.password) > 0:
self.info("Login user=%s, pass=*****" % self.username)
self.rh.throw = False
page = util.request(self.base_url + "login?key=logreg")
if page.find('href="/?do=web-logout') > 0:
self.info("Already logged in")
return True
data = util.substr(page, '<li class="menu-username', "</li")
m = re.search('key=(?P<key>[^"]+)"', data, re.IGNORECASE | re.DOTALL)
token = re.search('<input type="hidden" name="_token_".+?value="([^"]+)"', page, re.IGNORECASE | re.DOTALL)
if m and token:
login_url = self.base_url + "login?key=" + m.group("key") + "&do=loginForm-submit"
data = util.post(
login_url,
{
"username": self.username,
"password": self.password,
"remember": "on",
"login": "******",
"_token_": token.group(1),
},
)
if data.find('href="/?do=web-logout') > 0:
self.info("Login successfull")
return True
self.info("Login failed")
return False
def list_tv_show(self, url):
result = []
page = util.request(url)
data = util.substr(page, '<div class=\"content\">', '<script')
for s in re.finditer('<strong.+?</ul>', data, re.IGNORECASE | re.DOTALL):
serie = s.group(0)
serie_name = re.search('<strong>([^<]+)', serie).group(1)
for e in re.finditer('<li.+?</li>', serie, re.IGNORECASE | re.DOTALL):
episode = e.group(0)
item = self.video_item()
ep_name = re.search('<a href=\"#[^<]+<span>(?P<id>[^<]+)</span>(?P<name>[^<]+)',
episode)
if ep_name:
item['title'] = '%s %s %s' % (
serie_name, ep_name.group('id'), ep_name.group('name'))
item['epname'] = ep_name.group('name')
item['ep'] = ep_name
i = re.search('<div class=\"inner-item[^<]+<img src=\"(?P<img>[^\"]+).+?<a href=\"'
'(?P<url>[^\"]+)', episode, re.IGNORECASE | re.DOTALL)
if i:
item['img'] = self._url(i.group('img'))
item['url'] = i.group('url')
if i and ep_name:
self._filter(result, item)
if self.reverse_eps:
result.reverse()
return result
def list_episodes(self, page):
result = []
episodes = []
page = util.substr(page, START_LISTING, END_LISTING)
current_date = to_unicode(re.search(LISTING_DATE_RE, page, re.IGNORECASE | re.DOTALL).group('date'))
self.info("<list_episodes> current_date: %s" % current_date)
prev_url = re.search(LISTING_PAGER_RE, page, re.IGNORECASE | re.DOTALL).group('prevurl')
prev_url = re.sub('&', '&', prev_url)
#self.info("<list_episodes> prev_url: %s" % prev_url)
for m in re.finditer(LISTING_ITER_RE, page, re.IGNORECASE | re.DOTALL):
episodes.append([self._fix_url(re.sub('&', '&', m.group('url'))), m])
self.info("<list_episodes> found %d episodes" % len(episodes))
res = self._request_parallel(episodes)
for p, m in res:
m = m[0]
dnum = to_unicode(m.group('daynum'))
item = self.list_episode(p)
item['title'] = "%s (%s. %s)" % (item['title'], dnum, current_date)
item['date'] = dnum
item['url'] = re.sub('&', '&', m.group('url'))
self._filter(result, item)
result.sort(key=lambda x:int(x['date']), reverse=True)
item = self.dir_item()
item['type'] = 'prev'
item['url'] = prev_url
self._filter(result, item)
return result
def resolve(self, item, captcha_cb=None, select_cb=None):
result = []
item = item.copy()
url = self._url(item['url'])
data = util.substr(util.request(url), '<embed id', '>')
yurl_m = re.search('file=.*?(http[^&]+)&',data,re.DOTALL)
yurl = yurl_m and re.sub('youtu.be/','www.youtube.com/watch?v=',yurl_m.group(1)) or ''
resolved = resolver.findstreams(yurl, ['(?P<url>[^&]+)'])
subs = re.search('captions\.file=([^&]+)', data, re.DOTALL)
if resolved and subs:
for i in resolved:
i['subs'] = self._url(subs.group(1))
if not resolved:
raise ResolveException('Video nenalezeno')
for i in resolved:
item = self.video_item()
item['title'] = i['title']
item['url'] = i['url']
item['quality'] = i['quality']
item['surl'] = i['surl']
item['subs'] = i['subs']
item['headers'] = i['headers']
try:
item['fmt'] = i['fmt']
except KeyError:
pass
print item
result.append(item)
if len(result) == 0:
return result[0]
return select_cb(result)
def list(self,url):
result = []
page = util.request(self._url(url))
data = util.substr(page,'<div class=\"search','<footer')
for m in re.finditer('<div class=\"search-result-box(.+?)</a>',data,re.IGNORECASE | re.DOTALL ):
it = m.group(1)
link = re.search('<a href=([^ ]+)',it,re.IGNORECASE | re.DOTALL)
name = re.search('title=\"([^\"]+)',it,re.IGNORECASE | re.DOTALL)
img = re.search('<img src=\"([^\"]+)',it,re.IGNORECASE | re.DOTALL)
size = re.search('<div class=\"fs\">([^<]+)',it,re.IGNORECASE | re.DOTALL)
time = re.search('<div class=\"vd\">([^<]+)',it,re.IGNORECASE | re.DOTALL)
if name and link:
item = self.video_item()
item['title'] = name.group(1)
if size:
item['size'] = size.group(1).strip()
if time:
item['length'] = time.group(1).strip()
item['url'] = self._url(link.group(1))
item['img'] = self._url(img.group(1))
self._filter(result,item)
next = re.search('<a href=\"(?P<url>[^\"]+)[^>]+>dal',data,re.IGNORECASE | re.DOTALL)
if next:
item = self.dir_item()
item['type'] = 'next'
item['url'] = next.group('url')
result.append(item)
return result
def resolve(self,item,captcha_cb=None,select_cb=None):
item = item.copy()
url = self._url(item['url'])
data = util.request(self._url(item['url']))
data = util.substr(data,'<div class=\"video','</div')
sosac = re.search('\"(http\://[\w]+\.sosac\.ph[^\"]+)',data,re.DOTALL)
if sosac:
data = util.request(sosac.group(1))
resolved = resolver.findstreams(data,[
'<embed( )*flashvars=\"file=(?P<url>[^\"]+)',
'<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\' ](?P<url>.+?)[\'\" ]',
])
result = []
if not resolved:
self.error('Nothing resolved')
for i in resolved:
item = self.video_item()
item['title'] = i['name']
item['url'] = i['url']
item['quality'] = i['quality']
item['surl'] = i['surl']
item['subs'] = i['subs']
result.append(item)
if len(result)==1:
return result[0]
elif len(result) > 1 and select_cb:
return select_cb(result)
def resolve(self, item, captcha_cb=None, select_cb=None):
item = item.copy()
url = self._url(item['url'])
data = util.request(self._url(item['url']))
data = util.substr(data, '<div class=\"video', '</div')
sosac = re.search('\"(http\://[\w]+\.sosac\.[^\"]+)', data, re.DOTALL)
if sosac:
sosac = HTMLParser.HTMLParser().unescape(sosac.group(1))
self.info("Reading sosac URL " + sosac)
data = util.request(sosac, headers=HDRS)
result = self.findstreams(data, [
'<embed( )*flashvars=\"file=(?P<url>[^\"]+)',
'<embed( )src=\"(?P<url>[^\"]+)',
'<object(.+?)data=\"(?P<url>[^\"]+)',
'<iframe(.+?)src=[\"\' ](?P<url>.+?)[\'\" ]',
'<object.*?data=(?P<url>.+?)</object>'
])
if len(result) == 1:
return result[0]
elif len(result) > 1 and select_cb:
return select_cb(result)
def _categories(self, page, url):
data = util.substr(page, '<ul id=\"menu_kategorie', '</ul')
prefix = ''
mask = '[B]%s[/B]'
if url.find('serialy') >= 0:
prefix = '#show#'
mask = '%s'
result = []
for m in re.finditer(
'<a href=\"(?P<url>[^\"]+)[^<]+<span[^>]*>(?P<name>[^<]+)',
data, re.IGNORECASE | re.DOTALL):
item = self.dir_item()
item['title'] = mask % m.group('name')
item['url'] = prefix + m.group('url')
result.append(item)
# sort this
result = sorted(result, key=lambda i: i['title'])
if prefix == '':
# when listing movie categories, we also list movies on 'main' page
return result + self.list_page(page, '<!-- Movies', '</section')
return result
def __init__(self, master, row, group):
self.row = row
self.group = group
self._value = tk.IntVar(value=1 if group.valid else 0)
self.visible = True
bgcolor = BGCOLORS[row % 2] if group.valid else 'red'
ft = font.Font(size=11)
sticky = tk.N + tk.E + tk.S + tk.W
logger.debug("%s,%s,%s,%s,%s,%s", group.bdz, group.zxl, group.fzxl,
group.tq, group.name, substr(group.name, 18))
self.ckb = tk.Checkbutton(
master,
variable=self._value,
bg=bgcolor,
pady=3,
state=tk.NORMAL if group.valid else tk.DISABLED)
self.lb_bdz = tk.Label(master,
text=substr(group.bdz, 11),
width=13,
bg=bgcolor,
font=ft)
self.lb_zxl = tk.Label(master,
text=substr(group.zxl, 11),
width=13,
bg=bgcolor,
font=ft)
self.lb_fzxl = tk.Label(master,
text=substr(group.fzxl, 11),
width=13,
bg=bgcolor,
font=ft)
self.lb_tq = tk.Label(master,
text=substr(group.tq, 11),
width=13,
bg=bgcolor,
font=ft)
self.lb_name = tk.Label(master,
text=substr(group.name, 22),
width=25,
bg=bgcolor,
font=ft)
self.columns = [
self.ckb, self.lb_bdz, self.lb_zxl, self.lb_fzxl, self.lb_tq,
self.lb_name
]
for i, c in enumerate(self.columns):
c.grid(row=row, column=i, sticky=sticky)
def list_az(self, page):
result = []
images = []
page = util.substr(page, START_AZ, END_AZ)
for m in re.finditer(AZ_ITER_RE, page, re.IGNORECASE | re.DOTALL):
img = {
'remote': self._fix_url(m.group('img')),
'local': self._get_image_path(self._fix_url(m.group('img')))
}
item = self.dir_item()
semicolon = m.group('title').find(':')
if semicolon != -1:
item['title'] = m.group('title')[:semicolon].strip()
else:
item['title'] = m.group('title')
item['img'] = img['local']
item['url'] = m.group('url')
self._filter(result, item)
images.append(img)
self._get_images(images)
return result
def categories(self):
result = []
item = self.dir_item()
item['type'] = 'new'
item['url'] = "?orderby=post_date"
result.append(item)
item = self.dir_item()
item['title'] = 'Top of the month'
item['url'] = "zebricky/mesic/vse"
result.append(item)
data = util.request(self.base_url)
data = util.substr(data, '<ul class=\"nav categories m-b\">', '</div>')
pattern = '<a href=\"(?P<url>[^\"]+)(.+?)>(?P<name>[^<]+)'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
if m.group('url') == '/':
continue
item = self.dir_item()
item['title'] = m.group('name')
item['url'] = m.group('url')
result.append(item)
return result
def getSavedPlaylists(pathCookies):
session = initSession(pathCookies)
loginInfo = google.getLoginInfo(session)
result = []
content = session.get( youtubeUrl + 'channel/' + loginInfo['channel'] + '/playlists' + '?' + urllib.urlencode({'sort': 'dd', 'view_as': 'subscriber', 'view': '52', 'shelf_id': '0'})).text
dummy, i = util.substr ('[{"gridRenderer":{"items"',':',content)
data = json.loads(util.parseBrackets(content, i, ['[',']']))
for item in data:
try:
count = item['gridPlaylistRenderer']['videoCountShortText']['simpleText']
except:
count = ''
result.append({
'id': item['gridPlaylistRenderer']['playlistId'],
'name': item['gridPlaylistRenderer']['title']['runs'][0]['text'],
'thumb': item['gridPlaylistRenderer']['thumbnail']['thumbnails'][0]['url'],
'count': count,
'privacy': 'Public',
'user': '******'
})
return (result)
def url(url):
m = _regex(url)
if not m == None:
data = util.substr(util.request(url), 'class=\"proform\"', '</form>')
#print data
form_values = {}
pattern = '<input.+?name="(?P<name>.*?)".+?value="(?P<value>.*?)"'
for n in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
form_values[n.group('name')] = n.group('value')
#print form_values
try:
#time.sleep(10)
resp = util.post(url, form_values)
except:
util.error('streamcloud: got http error fetching %s' % (url))
return False
r = re.search('file: "(.+?)",', resp)
if r:
return [r.group(1)]
def list_serie(self,url):
result = []
page = util.request(self._url(url))
data = util.substr(page,'<div class=\"content\">','<script')
for s in re.finditer('<strong.+?</ul>',data,re.IGNORECASE | re.DOTALL):
serie = s.group(0)
serie_name = re.search('<strong>([^<]+)',serie).group(1)
for e in re.finditer('<li.+?</li>',serie,re.IGNORECASE | re.DOTALL):
episode = e.group(0)
item = self.video_item()
ep_name = re.search('<a href=\"#[^<]+<span>(?P<id>[^<]+)</span>(?P<name>[^<]+)',episode)
if ep_name:
item['title'] = '%s %s %s' % (serie_name,ep_name.group('id'),ep_name.group('name'))
i = re.search('<div class=\"inner-item[^<]+<img src=\"(?P<img>[^\"]+).+?<a href=\"(?P<url>[^\"]+)',episode, re.IGNORECASE | re.DOTALL)
if i:
item['img'] = self._url(i.group('img'))
item['url'] = i.group('url')
if i and ep_name:
self._filter(result,item)
if self.reverse_eps:
result.reverse()
return result
def process_category(title, url):
page = util.request(url)
img_m = re.search(CATEGORY_IMG_RE, page, re.IGNORECASE)
img = img_m and self._url(img_m.group(1))
page = util.substr(page, LISTING_START, LISTING_END)
finditer = False
for m in re.finditer(LISTING_ITER_RE, page,
re.DOTALL | re.IGNORECASE):
finditer = True
# payed content
if m.group('playimg').find(YELLOW_IMG) != -1:
return
break
# no links
if not finditer:
return
item = self.dir_item()
item['title'] = title
item['url'] = url
item['img'] = img
with lock:
self._filter(list, item)
def list_favourites(self,url):
url = self._url(url)
page = util.request(url)
data = util.substr(page,'<div class=\"file-list file-list-vertical','<div id=\"layout-push')
result = []
for m in re.finditer('<div class=\"file-entry.+?<div class="preview.+?<div class=\"data.+?</div>',data, re.IGNORECASE|re.DOTALL):
entry = m.group(0)
item = self.video_item()
murl = re.search('<[hH]3><a href=\"(?P<url>[^\"]+)[^>]+>(?P<name>[^<]+)',entry)
item['url'] = murl.group('url')
item['title'] = murl.group('name')
mimg = re.search('<img src=\"(?P<img>[^\"]+)',entry)
if mimg:
item['img'] = mimg.group('img')
msize = re.search('<span class=\"file-size[^>]+>(?P<size>[^<]+)',entry)
if msize:
item['size'] = msize.group('size').strip()
mtime = re.search('<span class=\"duration[^>]+>(?P<time>[^<]+)',entry)
if mtime:
item['length'] = mtime.group('time').strip()
self._filter(result,item)
return result
def categories(self):
result = []
item = self.dir_item()
item['type'] = 'new'
item['url'] = "#new#"
result.append(item)
item = self.dir_item()
item['type'] = 'top'
item['url'] = "#top#"
result.append(item)
categories = []
page = util.request(self._url('/video'))
page = util.substr(page, CATEGORIES_START, CATEGORIES_END)
for item in re.finditer(CATEGORIES_ITER_RE, page,
re.DOTALL | re.IGNORECASE):
title = item.group('title')
url = self._url(item.group('url'))
categories.append((title, url))
self._fill_categories_parallel(result, categories)
sorted(result, key=lambda x: x['title'])
return result
def getMyAlbums(pathCookies):
session = initSession(pathCookies)
loginInfo = google.getLoginInfo(session)
result = []
content = session.get("https://photos.google.com/albums").text
dummy, i = util.substr("key: 'ds:2', isError: false , hash:", "return",
content)
data = json.loads(util.parseBrackets(content, i, ['[', ']']))
for row in data[0]:
metadata = row[12]['72930366'] ## ==9
sharedKey = metadata[5]
if sharedKey is not None:
if len(metadata) != 9:
continue
result.append({
'id':
row[0],
'sharedKey':
sharedKey,
'name':
metadata[1],
'thumb':
row[1][0],
'tsStart':
datetime.datetime.fromtimestamp(metadata[2][0] / 1000),
'tsEnd':
datetime.datetime.fromtimestamp(metadata[2][1] / 1000),
'owner':
loginInfo['name'],
'ownerFlag':
True,
'photosCount':
metadata[3],
})
# resultsorted = sorted(result, key=lambda k: k['name'], reverse=True)
return (result)
def list_date(self, page):
result = []
images = []
page = util.substr(page, START_DATE, END_DATE)
for m in re.finditer(DATE_ITER_RE, page, re.IGNORECASE | re.DOTALL):
img = {
'remote': self._fix_url(m.group('img')),
'local': self._get_image_path(self._fix_url(m.group('img')))
}
item = self.video_item()
item['title'] = "%s (%s)" % (m.group('title'), m.group('time'))
item['img'] = img['local']
item['url'] = m.group('url')
item['menu'] = {
'$30070': {
'list': item['url'],
'action-type': 'list'
}
}
self._filter(result, item)
images.append(img)
self._get_images(images)
return result
def categories(self):
result = []
if os.path.isfile(self.clips_path):
os.remove(self.clips_path)
data = util.substr(util.request(self.base_url), CATEGORIES_START,
CATEGORIES_END)
for m in re.finditer(CATEGORIES_ITER_RE, data, re.DOTALL):
item = self.dir_item()
item['title'] = m.group('title')
item['url'] = self.plurl.format(m.group('id'), 0)
item['menu'] = {
u'Playlist': {
'play': self.plurl.format(m.group('id'), 0),
'title': m.group('title'),
'action-type': 'play'
}
}
result.append(item)
item = self.dir_item()
item['title'] = u'Historie tématických playlistů'
item['url'] = 'historie'
result.append(item)
return result
def login(self):
if self.username and self.password and len(self.username) > 0 and len(
self.password) > 0:
page = util.request(self.base_url + '?do=loginBox-loginpopup')
if page.find('href="/?do=loginBox-logout') > 0:
self.info('Already logged in')
return True
data = util.substr(page, '<td class=\"popup-lef', '</form')
m = re.search('<form action=\"(?P<url>[^\"]+)', data,
re.IGNORECASE | re.DOTALL)
if m:
login_url = self._url(m.group('url')).replace('&', '&')
data = util.post(
login_url, {
'username': self.username,
'password': self.password,
'pernament_login': '******',
'login': '******',
'redir_url': self.base_url + '?do=loginBox-login'
})
if data.find('href="/?do=loginBox-logout') > 0:
return True
return False
def getOtherAlbums(pathCookies):
session = initSession(pathCookies)
loginInfo = google.getLoginInfo(session)
result = []
content = session.get("https://photos.google.com/sharing").text
dummy, i = util.substr("key: 'ds:1'", "return", content)
data = json.loads(util.parseBrackets(content, i, ['[', ']']))
util.objToFile(str(data[0][0]),
pathCookies.replace('/cookies', '/data.txt'))
for row in data[0]:
owner = row[10][0][11][0]
if owner == loginInfo['name']:
continue
result.append({
'id':
row[6],
'sharedKey':
row[7],
'name':
row[1],
'thumb':
row[2][0],
'tsStart':
None,
'tsEnd':
None,
'photosCount':
row[3],
'tsCreated':
datetime.datetime.fromtimestamp(row[4] / 1000),
'owner':
row[10][0][11][0],
'ownerFlag':
False
})
return result
def searchVideos(searchStr, pathCookies):
session = initSession(pathCookies)
result = []
content = session.get( youtubeUrl + 'results' + '?' + urllib.urlencode({'search_query': searchStr, 'sp': 'EgIQAVAU'})).text
dummy, i = util.substr ('"itemSectionRenderer":{"contents"',':',content)
data = json.loads(util.parseBrackets(content, i, ['[',']']))
for item in data:
if 'videoRenderer' not in item.keys():
continue
content = {
'id': item['videoRenderer']['videoId'],
'name': item['videoRenderer']['title']['simpleText'],
'thumb': videoImage(item['videoRenderer']['videoId']),
'duration': '',
'publishedTime': '',
'viewCount': '',
'owner': '',
'privacy': 'Public',
}
try:
content['duration'] = item['videoRenderer']['lengthText']['simpleText']
except:
continue
try:
content['publishedTime'] = item['videoRenderer']['publishedTimeText']['simpleText']
except:
None
try:
content['viewCount'] = item['videoRenderer']['viewCountText']['simpleText'].replace(' views','')
except:
None
try:
content['owner'] = item['videoRenderer']['ownerText']['runs'][0]['text']
except:
None
result.append(content)
return (result)
def list(self, url):
result = []
data = util.request(self._url(url))
for m in re.finditer(
'<div class=mosaic-overlay[^<]+<a.+?href=\"(?P<url>[^\"]+)[^<]+<div[^>]+>(?P<name>[^<]+)(.+?)src=\"(?P<logo>[^\"]+)',
data, re.IGNORECASE | re.DOTALL):
item = self.video_item()
item['title'] = m.group('name')
item['img'] = self._url(m.group('logo'))
item['url'] = m.group('url')
self._filter(result, item)
navurl = url
index = url.find('?')
if index > 0:
navurl = url[:index]
data = util.substr(data, '<div class=strana', '</div')
next = re.search('<a href=\"(?P<url>[^\"]+)\">\(>\)<', data,
re.IGNORECASE | re.DOTALL)
if next:
item = self.dir_item()
item['type'] = 'next'
item['url'] = navurl + next.group('url')
result.append(item)
return result
def list_page(self, page, start, end):
next = re.search('<a href=\"(?P<url>[^\"]+)\" class=\"ajax\">Další',
page)
page = util.substr(page, start, end)
result = []
for m in re.finditer('<article[^>]+(.+?)</article>', page,
re.IGNORECASE | re.DOTALL):
data = m.group(1)
url = re.search('<a href=\"([^\"]+)', data)
img = re.search(
'<div class=\"img[^<]+<img src=\"(?P<img>[^\"]+).+?alt=\"(?P<name>[^\"]+)',
data)
if img and url:
item = self.dir_item()
item['url'] = '#movie#' + url.group(1)
item['img'] = self._url(img.group('img'))
item['title'] = img.group('name')
self._filter(result, item)
if next:
item = self.dir_item()
item['type'] = 'next'
item['url'] = next.group('url').replace('&', '&')
result.append(item)
return result
def categories(self):
result = []
item = self.dir_item()
item['type'] = 'new'
item['url'] = '#newest#'
result.append(item)
data = util.request(self.base_url + '/kategorie/')
data = util.substr(data, '<ul id="cat"', '</div>')
pattern = '<a href="(?P<url>[^"]+)" title="(?P<name>[^"]+)">'
for m in re.finditer(pattern, data, re.IGNORECASE | re.DOTALL):
if m.group('url') == '#':
break
item = self.dir_item()
item['title'] = m.group('name')
item['url'] = m.group('url')
result.append(item)
over18 = __addon__.getSetting('over18')
if (over18 == 'true'):
item = self.dir_item()
item['title'] = 'erotika'
item['url'] = self.base_url + '/erotika'
result.append(item)
return result
def getMyVideos(session):
result = []
content = session.get(youtubeUrl + 'my_videos' + '?' +
urllib.urlencode({'o': 'U'})).text
dummy, i = util.substr('"VIDEO_LIST_DISPLAY_OBJECT"', ':', content)
data = json.loads(util.parseBrackets(content, i, ['[', ']']))
for item in data:
soup = BeautifulSoup(
util.unescape(item['html'].decode('unicode_escape')),
"html.parser")
ptag = soup.find(class_="vm-video-indicators")
privacy = 'Public'
if not ptag.find(class_='vm-unlisted').parent.has_attr('aria-hidden'):
privacy = 'Private'
if not ptag.find(class_='vm-private').parent.has_attr('aria-hidden'):
privacy = 'Private'
try:
duration = util.timeStrToSeconds(
soup.find(class_="video-time").get_text())
except:
duration = ''
result.append({
'id':
item['id'],
'name':
soup.find(class_="vm-video-title-content").get_text(),
'thumb':
videoImage(item['id']),
'duration':
duration,
'privacy':
privacy,
'user':
'******'
})
return (result)
def resolve(self, item, captcha_cb=None, select_cb=None):
result = []
item = item.copy()
url = item['url']
if url.endswith('live.html'):
url = url.replace('www.', '')
channel = urlparse.urlparse(url).netloc.split('.')[0]
if channel in 'plus':
channel = 'jojplus'
channel_quality_map = {
'joj': ('360', '540', '720'),
'jojplus': ('360', '540'),
'wau': ('360', '540')
}
for quality in channel_quality_map[channel]:
item = self.video_item()
item['quality'] = quality + 'p'
item[
'url'] = 'https://nn.geo.joj.sk/live/hls/' + channel + '-' + quality + '.m3u8'
result.append(item)
else:
data = util.request(url)
data = util.substr(
data, '<section class="s-section py-0 s-video-detail">',
'</section>')
iframe_url = re.search('<iframe src="([^"]+)"', data).group(1)
#print 'iframe_url = ', iframe_url
player_str = urllib2.urlopen(iframe_url).read()
#print player_str
labels_str = re.search(r'var labels = {(.+?)};', player_str,
re.DOTALL).group(1)
#print 'labels:', labels_str
renditions = re.search(r'renditions: \[(.+?)\]',
labels_str).group(1).replace("'",
"").split(',')
#print 'renditions: ', renditions
settings_str = re.search(r'var settings = {(.+?)};', player_str,
re.DOTALL).group(1)
#print 'settings:', settings_str
poster_url = re.search(r'poster: \"(.+?)\"', settings_str).group(1)
#print 'poster_url:', poster_url
bitrates_str = re.search(r'var src = {(.+?)};', player_str,
re.DOTALL).group(1)
#print 'bitrates:', bitrates_str
bitrates_url = re.search(r'"mp4": \[(.+?)\]', bitrates_str,
re.DOTALL).group(1)
bitrates_url = bitrates_url.replace("'",
"").replace('\n', '').replace(
' ', '').split(',')
for idx, url in enumerate(bitrates_url):
item = self.video_item()
item['img'] = poster_url
item['quality'] = renditions[idx]
item['url'] = url
result.append(item)
result.reverse()
if select_cb:
return select_cb(result)
return result
def list_show(self, url, list_series=False, list_episodes=False):
result = []
self.info("list_show %s" % (url))
data = util.request(url)
if list_series:
series_data = util.substr(
data, r'<select onchange="return selectSeason(this.value);">',
'</select>')
for serie_match in re.finditer(
r'<option value="(?P<season_id>\d+)?"\s(selected="selected")?>\s+(?P<title>[^<]+)\n',
series_data):
item = self.dir_item()
season_id = serie_match.group('season_id')
if not season_id:
season_id = ""
item['title'] = serie_match.group('title')
item['url'] = "%s?seasonId=%s" % (url.split('#')[0], season_id)
result.append(item)
if list_episodes:
episodes_data = util.substr(data, r'<section>', '</section>')
for article_match in re.finditer(
r'<article class="b-article title-xs article-lp">(.+?)</article>',
episodes_data, re.DOTALL):
article_dict = self._list_article(article_match.group(1))
if article_dict is not None:
item = self.video_item()
item.update(article_dict)
item['title'] += ' ' + item.get('subtitle', '')
result.append(item)
title_to_key = {
'Dátum': 'date',
'Názov epizódy': 'title',
'Sledovanosť': 'seen',
'Séria': 'season',
'Epizóda': 'episode'
}
headers_match = re.search(
'<div class="i head e-video-categories">(.+?)</div>',
episodes_data, re.DOTALL)
if headers_match is not None:
headers = []
for span_match in re.finditer('<span[^>]*>([^<]+)</span>',
headers_match.group(1)):
key = title_to_key.get(span_match.group(1))
if key is None:
print "undefined key", span_match.group(1)
headers.append("")
else:
headers.append(key)
archive_list_pattern = r'<a href="(?P<url>[^"]+)" title="(?P<title>[^"]+)[^>]+>\s+'
for key in headers:
if key in ("", "title"):
archive_list_pattern += r'^.+?$\s+'
else:
archive_list_pattern += r'<span>(?P<%s>[^<]*)</span>\s+' % key
for archive_list_match in re.finditer(archive_list_pattern,
episodes_data,
re.MULTILINE):
item = self.video_item()
groupdict = archive_list_match.groupdict()
if 'season' in groupdict and 'episode' in groupdict:
# joj sometimes don't provide season/episode numbers
# for latest episodes, so mark them as 0.
try:
season = int(archive_list_match.group('season'))
except Exception:
season = 0
try:
episode = int(archive_list_match.group('episode'))
except Exception:
episode = 0
item['title'] = "(S%02d E%02d) - %s" % (
season, episode, archive_list_match.group('title'))
else:
item['title'] = "(%s) - %s" % (
archive_list_match.group('date'),
archive_list_match.group('title'))
item['url'] = self._fix_url(
archive_list_match.group('url'))
result.append(item)
pagination_data = util.substr(data, '<nav>', '</nav>')
next_match = re.search(
r'a href="(?P<url>[^"]+)" aria-label="Ďalej"', pagination_data,
re.DOTALL)
if next_match:
item = self.dir_item()
item['type'] = 'next'
item['url'] = self._fix_url(next_match.group(1))
result.append(item)
return result
def list(self, url):
if url.find('#fm#') == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(url,
headers={
'X-Requested-With': 'XMLHttpRequest',
'Referer': url,
'Cookie': 'uloz-to-id=1561277170;'
})
script = util.substr(page, 'var kn', '</script>')
keymap = None
key = None
k = re.search('{([^\;]+)"', script, re.IGNORECASE | re.DOTALL)
if k:
keymap = json.loads("{" + k.group(1) + "\"}")
j = re.search('kapp\(kn\[\"([^\"]+)"', script,
re.IGNORECASE | re.DOTALL)
if j:
key = j.group(1)
if not (j and k):
self.error('error parsing page - unable to locate keys')
return []
burl = b64decode(
'I2h0dHA6Ly9kZWNyLWNlY2gucmhjbG91ZC5jb20vZGVjcnlwdC8/a2V5PSVzJnZhbHVlPSVz'
)
murl = b64decode(
'aHR0cDovL2RlY3ItY2VjaC5yaGNsb3VkLmNvbS9kZWNyeXB0Lw==')
data = util.substr(page, '<ul class=\"chessFiles', 'var kn =')
result = []
req = {'seed': keymap[key], 'values': keymap}
decr = json.loads(util.post_json(murl, req))
for li in re.finditer('<li data-icon=\"(?P<key>[^\"]+)', data,
re.IGNORECASE | re.DOTALL):
body = urllib.unquote(b64decode(decr[li.group('key')]))
m = re.search(
'<li.+?<div data-icon=\"(?P<key>[^\"]+)[^<]+<img(.+?)src=\"(?P<logo>[^\"]+)(.+?)<i class=\"fa fa-download(?P<info>.+?)class="fileReset"',
body, re.IGNORECASE | re.DOTALL)
if not m:
continue
value = keymap[m.group('key')]
info = m.group('info')
iurl = burl % (keymap[key], value)
item = self.video_item()
item['title'] = '.. title not found..'
title = re.search(
'<div class=\"fileName.+?<a[^>]+>(?P<title>[^<]+)', info,
re.IGNORECASE | re.DOTALL)
if title:
item['title'] = title.group('title')
size = re.search('<span class=\"fileSize[^>]+>(?P<size>[^<]+)',
info, re.IGNORECASE | re.DOTALL)
if size:
item['size'] = size.group('size').strip()
time = re.search('<span class=\"fileTime[^>]+>(?P<time>[^<]+)',
info, re.IGNORECASE | re.DOTALL)
if time:
item['length'] = time.group('time')
item['url'] = iurl
item['img'] = m.group('logo')
self._filter(result, item)
# page navigation
data = util.substr(page, '<div class=\"paginator', '</div')
mnext = re.search('<a href=\"(?P<url>[^\"]+)\" class="next', data)
if mnext:
item = self.dir_item()
item['type'] = 'next'
item['url'] = mnext.group('url')
result.append(item)
return result
def resolve(self, item, captcha_cb=None, select_cb=None):
item = item.copy()
util.init_urllib()
url = self._url(item['url'])
page = ''
try:
opener = OpenerDirector()
opener.add_handler(HTTPHandler())
opener.add_handler(UnknownHandler())
install_opener(opener)
request = Request(url)
request.add_header('User-Agent', util.UA)
response = urlopen(request)
page = response.read()
response.close()
except HTTPError as e:
traceback.print_exc()
return
data = util.substr(page, '<form method=post target=\"iframe_dwn\"',
'</form>')
action = re.search('action=(?P<url>[^>]+)', data,
re.IGNORECASE | re.DOTALL)
img = re.search('<img src=\"(?P<url>[^\"]+)', data,
re.IGNORECASE | re.DOTALL)
if img and action:
sessid = []
for cookie in re.finditer('(PHPSESSID=[^\;]+)',
response.headers.get('Set-Cookie'),
re.IGNORECASE | re.DOTALL):
sessid.append(cookie.group(1))
# we have to download image ourselves
image = util.request(self._url(img.group('url')),
headers={
'Referer': url,
'Cookie': sessid[-1]
})
img_file = os.path.join(self.tmp_dir, 'captcha.png')
util.save_data_to_file(image, img_file)
code = None
if captcha_cb:
code = captcha_cb({'id': '0', 'img': img_file})
if not code:
self.info('No captcha received, exit')
return
request = urllib.urlencode({'code': code})
req = Request(self._url(action.group('url')), request)
req.add_header('User-Agent', util.UA)
req.add_header('Referer', url)
req.add_header('Cookie', sessid[-1])
try:
resp = urlopen(req)
if resp.code == 302:
file_url = resp.headers.get('location')
else:
file_url = resp.geturl()
if file_url.find(action.group('url')) > 0:
msg = resp.read()
resp.close()
js_msg = re.search('alert\(\'(?P<msg>[^\']+)', msg,
re.IGNORECASE | re.DOTALL)
if js_msg:
raise ResolveException(js_msg.group('msg'))
self.error(msg)
raise ResolveException(
'Nelze ziskat soubor, zkuste to znovu')
resp.close()
if file_url.find('data') >= 0 or file_url.find(
'download_free') > 0:
item['url'] = file_url
return item
self.error('wrong captcha, retrying')
return self.resolve(item, captcha_cb, select_cb)
except HTTPError:
traceback.print_exc()
return
def resolve(self, item, captcha_cb=None, select_cb=None):
original_yt = self.original_yt
self.info('original_yt ' + str(original_yt) + ' ' +
str(type(original_yt)))
result = []
resolved = []
item = item.copy()
url = self._url(item['url'])
data = util.substr(util.request(url), 'async type', '</script>')
# print ('data start ----')
# print (data)
# print ('data end ----')
playlist = re.search(
'''new mfJWPlayer.+?(?P<jsondata>playlist:.+?)events:''', data,
re.MULTILINE | re.DOTALL)
# print ('playlist start ----')
# print (playlist)
# print ('playlist end ----')
jsondata = re.sub(
' +', ' ', '{%s' %
playlist.group('jsondata').replace('file:', '"file":').replace(
'label:', '"label":').replace('kind:', '"kind":').replace(
'default:', '"default":').replace(
'true', '"true"').replace('],', ']')) + '}'
# print ('jsondata start ----')
# print (jsondata)
# print ('jsondata end ----')
jsondata = demjson.decode(jsondata)
for playlist_item in jsondata['playlist']:
playlist_item['file'] = playlist_item['file'].replace(
'time_continue=1&', '')
#self.info(playlist_item['file'])
if original_yt:
e = 'watch?v='
edx = playlist_item['file'].find(e)
video_id = playlist_item['file'][edx + len(e):]
vid = YDStreamExtractor.getVideoInfo(
playlist_item['file'], quality=3
) #quality is 0=SD, 1=720p, 2=1080p, 3=Highest Available
video_url = [vid.streams()[0]]
# self.info(video_url)
subs = playlist_item['tracks']
if video_url and subs:
for i in video_url:
i['subs'] = self.base_url[:-1] + subs[0]['file']
resolved += video_url[:]
if not resolved:
raise ResolveException('Video nenalezeno')
for i in resolved:
item = self.video_item()
try:
item['title'] = i['title']
except KeyError:
pass
item['url'] = i['xbmc_url']
if original_yt:
item[
'url'] = "plugin://plugin.video.youtube/?action=play_video&videoid=" + video_id
item['quality'] = i['ytdl_format']['height']
item['surl'] = i['ytdl_format']['webpage_url']
item['subs'] = i['subs']
item['headers'] = {}
# self.info(item)
try:
item['fmt'] = i['fmt']
except KeyError:
pass
result.append(item)
if len(result) > 0 and select_cb:
# self.info(result)
return select_cb(result)
# print ('==resolve==')
# print (result)
return result
class FastshareContentProvider(ContentProvider):
def __init__(self,username=None,password=None,filter=None,tmp_dir='.'):
ContentProvider.__init__(self,'fastshare.cz','http://www.fastshare.cz/',username,password,filter,tmp_dir)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookielib.LWPCookieJar()))
urllib2.install_opener(opener)
def capabilities(self):
return ['search','resolve']
def search(self,keyword):
return self.list('?term='+urllib.quote(keyword))
def list(self,url):
result = []
page = util.request(self._url(url))
data = util.substr(page,'<div class=\"search','<footer')
for m in re.finditer('<div class=\"search-result-box(.+?)</a>',data,re.IGNORECASE | re.DOTALL ):
it = m.group(1)
link = re.search('<a href=([^ ]+)',it,re.IGNORECASE | re.DOTALL)
name = re.search('title=\"([^\"]+)',it,re.IGNORECASE | re.DOTALL)
img = re.search('<img src=\"([^\"]+)',it,re.IGNORECASE | re.DOTALL)
size = re.search('<div class=\"fs\">([^<]+)',it,re.IGNORECASE | re.DOTALL)
time = re.search('<div class=\"vd\">([^<]+)',it,re.IGNORECASE | re.DOTALL)
if name and link:
item = self.video_item()
item['title'] = name.group(1)
if size:
item['size'] = size.group(1).strip()
if time:
item['length'] = time.group(1).strip()
item['url'] = self._url(link.group(1))
item['img'] = self._url(img.group(1))
self._filter(result,item)
next = re.search('<a href=\"(?P<url>[^\"]+)[^>]+>dal',data,re.IGNORECASE | re.DOTALL)
if next:
item = self.dir_item()
item['type'] = 'next'
item['url'] = next.group('url')
result.append(item)
return result
def resolve(self,item,captcha_cb=None,select_cb=None):
item = item.copy()
util.init_urllib()
url = self._url(item['url'])
page = ''
try:
opener = urllib2.OpenerDirector()
opener.add_handler(urllib2.HTTPHandler())
opener.add_handler(urllib2.UnknownHandler())
urllib2.install_opener(opener)
request = urllib2.Request(url)
request.add_header('User-Agent',util.UA)
response= urllib2.urlopen(request)
page = response.read()
response.close()
except urllib2.HTTPError, e:
traceback.print_exc()
return
data = util.substr(page,'<form method=post target=\"iframe_dwn\"','</form>')
action = re.search('action=(?P<url>[^>]+)',data,re.IGNORECASE | re.DOTALL)
img = re.search('<img src=\"(?P<url>[^\"]+)',data,re.IGNORECASE | re.DOTALL)
if img and action:
sessid=[]
for cookie in re.finditer('(PHPSESSID=[^\;]+)',response.headers.get('Set-Cookie'),re.IGNORECASE | re.DOTALL):
sessid.append(cookie.group(1))
# we have to download image ourselves
image = util.request(self._url(img.group('url')),headers={'Referer':url,'Cookie':sessid[-1]})
img_file = os.path.join(self.tmp_dir,'captcha.png')
util.save_data_to_file(image,img_file)
code = None
if captcha_cb:
code = captcha_cb({'id':'0','img':img_file})
if not code:
self.info('No captcha received, exit')
return
request = urllib.urlencode({'code':code})
req = urllib2.Request(self._url(action.group('url')),request)
req.add_header('User-Agent',util.UA)
req.add_header('Referer',url)
req.add_header('Cookie',sessid[-1])
try:
resp = urllib2.urlopen(req)
if resp.code == 302:
file_url = resp.headers.get('location')
else:
file_url = resp.geturl()
if file_url.find(action.group('url')) > 0:
msg = resp.read()
resp.close()
js_msg = re.search('alert\(\'(?P<msg>[^\']+)',msg,re.IGNORECASE | re.DOTALL)
if js_msg:
raise ResolveException(js_msg.group('msg'))
self.error(msg)
raise ResolveException('Nelze ziskat soubor, zkuste to znovu')
resp.close()
if file_url.find('data') >=0 or file_url.find('download_free') > 0:
item['url'] = file_url
return item
self.error('wrong captcha, retrying')
return self.resolve(item,captcha_cb,select_cb)
except urllib2.HTTPError:
traceback.print_exc()
return
def login(pathCookies, email, password):
session = initSession()
######## Step 1 #########
content = session.get('https://accounts.google.com/Login').text
dummy, i = util.substr('window.WIZ_global_data', '= ', content)
data = json.loads(util.parseBrackets(content, i, ['{', '}']))
data = data['OewCAd']
p1 = data = data.split(',')[3].replace('"', '').replace(']', '')
soap = BeautifulSoup(content, "html.parser")
data = soap.find("div",
{"id": "view_container"
})['data-initial-setup-data'].replace('%.@.', '[')
data = json.loads(data)
data = data[13]
p2 = json.dumps(data).replace('"', '')
######## Step 2 #########
session.headers.update({
'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
'Google-Accounts-XSRF': '1',
'Referer': 'https://accounts.google.com/',
'X-Same-Domain': '1'
})
data = {
# 'continue': 'https://myaccount.google.com/',
'continue':
'https://accounts.google.com/ManageAccount',
'f.req':
'["' + email + '","' + p2 +
'",[],null,"IL",null,null,2,false,true,[null,null,[2,1,null,1,"https://accounts.google.com/ServiceLogin?requestPath=%2FLogin&Page=PasswordSeparationSignIn",null,[],4],1,[null,null,[]],null,null,null,true],"'
+ email + '"]',
'azt':
p1,
'deviceinfo':
'[null,null,null,[],null,"IL",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
'gmscoreversion':
'undefined',
'checkConnection':
'youtube:841:0',
'checkedDomains':
'youtube',
'pstMsg':
'1'
}
content = session.post(
'https://accounts.google.com/_/signin/sl/lookup?hl=en&_reqid=73079&rt=j',
data=data).text
data = json.loads(content.replace(")]}'", "").replace("\n", ""))
data = data[0][0][2]
p3 = json.dumps(data).replace('"', '')
######## Step 3 #########
data = {
'continue': 'https://accounts.google.com/ManageAccount',
# 'continue': 'https://myaccount.google.com/',
'f.req': '["' + p3 + '",null,1,null,[1,null,null,null,["' + password +
'",null,true]],[null,null,[2,1,null,1,"https://accounts.google.com/ServiceLogin?requestPath=%2FLogin&Page=PasswordSeparationSignIn",null,[],4],1,[null,null,[]],null,null,null,true]]',
'azt': p1,
'deviceinfo':
'[null,null,null,[],null,"IL",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
'gmscoreversion': 'undefined',
'checkConnection': 'youtube:841:0',
'checkedDomains': 'youtube',
'pstMsg': '1'
}
content = session.post(
'https://accounts.google.com/_/signin/sl/challenge?hl=en&_reqid=173079&rt=j',
data=data).text
if 'SID' not in str(session.cookies):
raise Exception('Unable to login: Invalid credentials')
######## Step 4 #########
util.resetHeaders(session)
content = session.get('https://www.youtube.com/my_videos?o=U').text
dummy, i = util.substr("yt.setConfig('GOOGLE_HELP_PRODUCT_DATA'", ', ',
content)
data = json.loads(util.parseBrackets(content, i, ['{', '}']))
channel = data['channel_external_id']
soap = BeautifulSoup(content, "html.parser")
name = soap.find("div", class_='yt-masthead-picker-name').get_text()
### Save login data ###
loginInfo = email + '&' + channel + '&' + name + '&' + str(time.time())
util.setCookie(session, 'www.google.com', 'MyLoginInfo', loginInfo)
util.saveCookies(session, pathCookies)
def list_show(self, url, categories=True, episodes=True):
result = []
data = util.request(url)
if categories:
categories_data = util.substr(
data, '<section class="col-md-12 videoarchiv_navi">',
'</section>')
categories_data = util.substr(
categories_data,
'<div class="collapse navbar-collapse" id="bs-example-navbar-collapse-2">',
'</div>')
for i in re.findall(r'<li>(.+?)</li>', categories_data, re.DOTALL):
item = self.dir_item()
item['url'] = self._url(
re.search(r'<a href="([^"]+)', i).group(1))
item['title'] = re.search(r'title="([^"]+)', i).group(1)
result.append(item)
if episodes:
row_list = []
row_pattern = re.compile(
r'<div class="item row ">(.+?)</div>\s+</div>', re.DOTALL)
purl = urlparse(url)
if not 'page=' in purl.query:
# latest episode
episodes_data = util.substr(
data, '<section class="col-md-12 info_new row">',
'</section>')
row_match = row_pattern.search(episodes_data)
if row_match:
row_list.append(row_match.group(1))
# other episodes
episodes_data = util.substr(
data, '<section class="col-md-12 article-view homepage">',
'</section>')
row_list += row_pattern.findall(episodes_data)
for row in row_list:
title_and_url_match = re.search(
r'<a href="(?P<url>[^"]+") title="(?P<title>[^"]+)', row)
if not title_and_url_match:
self.error('list_show - cannot get video item from "%s"' %
row.strip())
continue
item = self.video_item()
item['url'] = self._url(title_and_url_match.group('url'))
item['title'] = title_and_url_match.group('title')
img_match = re.search(r'<img.+?src="([^"]+)', row)
if img_match:
item['img'] = self._url(img_match.group(1))
countdown_match = re.search(
r'<span class="archiv-countdown">.+?</i>([^<]+)', row)
if countdown_match:
item['countdown'] = countdown_match.group(1).strip()
time_match = re.search(r'<div class="time">([^<]+)', row)
if time_match:
length_str, date_str = time_match.group(1).split('•')
item['length'] = length_str.strip()
item['date'] = date_str.strip()
result.append(item)
next_match = re.search(r'<li class="pager-next"><a href="([^"]+)',
data)
if next_match:
result.append(
self.dir_item(url=self._url(next_match.group(1)),
type='next'))
return result
class UloztoContentProvider(ContentProvider):
def __init__(self, username=None, password=None, filter=None):
ContentProvider.__init__(self, 'ulozto.cz', 'https://www.ulozto.cz/',
username, password, filter)
self.search_type = ''
self.cp = urllib2.HTTPCookieProcessor(cookielib.LWPCookieJar())
self.rh = UloztoHTTPRedirectHandler()
self.rh.throw = False
self.rh.location = None
self.init_urllib()
def init_urllib(self):
opener = urllib2.build_opener(self.cp, self.rh)
urllib2.install_opener(opener)
def capabilities(self):
return ['login', 'search', 'resolve', 'categories']
def categories(self):
result = []
if not self.login():
return result
data = util.request(self.base_url + 'm/' + self.username)
fav = re.search(
'<li id=\"fmFavoritesFolder.+?href=\"(?P<url>[^\"]+)[^>]*>(?P<title>[^<]+)',
data, re.IGNORECASE | re.DOTALL)
if fav:
item = self.dir_item()
item['url'] = '#fm#' + fav.group('url')
item['title'] = fav.group('title')
result.append(item)
myfiles = re.search(
'<a class=\"fmHomeFolder.+?href=\"(?P<url>[^\"]+)[^>]*>(?P<title>[^<]+)',
data, re.IGNORECASE | re.DOTALL)
if myfiles:
item = self.dir_item()
item['url'] = '#fm#' + myfiles.group('url')
item['title'] = myfiles.group('title')
result.append(item)
return result
def search(self, keyword):
return self.list(self.base_url + 'hledej/?' + self.search_type + 'q=' +
urllib.quote(keyword))
def login(self):
if self.username and self.password and len(self.username) > 0 and len(
self.password) > 0:
self.info('Login user=%s, pass=*****' % self.username)
self.rh.throw = False
page = util.request(self.base_url + 'login?key=logreg')
if page.find('href="/?do=web-logout') > 0:
self.info('Already logged in')
return True
data = util.substr(page, '<li class=\"menu-username', '</li')
m = re.search('key=(?P<key>[^\"]+)\"', data,
re.IGNORECASE | re.DOTALL)
token = re.search(
'<input type=\"hidden\" name=\"_token_\".+?value=\"([^\"]+)"',
page, re.IGNORECASE | re.DOTALL)
if m and token:
login_url = self.base_url + 'login?key=' + m.group(
'key') + '&do=loginForm-submit'
data = util.post(
login_url, {
'username': self.username,
'password': self.password,
'remember': 'on',
'login': '******',
'_token_': token.group(1)
})
if data.find('href="/?do=web-logout') > 0:
self.info('Login successfull')
return True
self.info('Login failed')
return False
def list_folder(self, url):
self.login()
result = []
page = util.request(self._url(url))
page = util.substr(page, '<div id=\"fmItems', '</ul')
for m in re.finditer('<div class=\"fmFolder(.+?)</em', page,
re.IGNORECASE | re.DOTALL):
data = m.group(1)
item = self.dir_item()
item['url'] = '#fm#' + re.search('data-href=\"([^\"]+)',
data).group(1)
item['title'] = re.search('data-name=\"([^\"]+)', data).group(1)
item['img'] = re.search('<img src=\"([^\"]+)', data).group(1)
result.append(item)
for m in re.finditer('<div class=\"fmFile(.+?)</em>', page,
re.IGNORECASE | re.DOTALL):
data = m.group(1)
item = self.video_item()
item['url'] = re.search('data-href=\"([^\"]+)', data).group(1)
item['title'] = '%s.%s' % (
re.search('data-name=\"([^\"]+)', data).group(1),
re.search('data-ext=\"([^\"]+)', data).group(1))
item['img'] = re.search('<img src=\"([^\"]+)', data).group(1)
result.append(item)
return result
@cached(1)
def list(self, url):
if url.find('#fm#') == 0:
return self.list_folder(url[5:])
url = self._url(url)
page = util.request(url,
headers={
'X-Requested-With': 'XMLHttpRequest',
'Referer': url,
'Cookie': 'uloz-to-id=1561277170;'
})
script = util.substr(page, 'var kn', '</script>')
keymap = None
key = None
k = re.search('{([^\;]+)"', script, re.IGNORECASE | re.DOTALL)
if k:
keymap = json.loads("{" + k.group(1) + "\"}")
j = re.search('kapp\(kn\[\"([^\"]+)"', script,
re.IGNORECASE | re.DOTALL)
if j:
key = j.group(1)
if not (j and k):
self.error('error parsing page - unable to locate keys')
return []
burl = b64decode(
'I2h0dHA6Ly9kZWNyLWNlY2gucmhjbG91ZC5jb20vZGVjcnlwdC8/a2V5PSVzJnZhbHVlPSVz'
)
murl = b64decode(
'aHR0cDovL2RlY3ItY2VjaC5yaGNsb3VkLmNvbS9kZWNyeXB0Lw==')
data = util.substr(page, '<ul class=\"chessFiles', 'var kn =')
result = []
req = {'seed': keymap[key], 'values': keymap}
decr = json.loads(util.post_json(murl, req))
for li in re.finditer('<li data-icon=\"(?P<key>[^\"]+)', data,
re.IGNORECASE | re.DOTALL):
body = urllib.unquote(b64decode(decr[li.group('key')]))
m = re.search(
'<li.+?<div data-icon=\"(?P<key>[^\"]+)[^<]+<img(.+?)src=\"(?P<logo>[^\"]+)(.+?)<i class=\"fa fa-download(?P<info>.+?)class="fileReset"',
body, re.IGNORECASE | re.DOTALL)
if not m:
continue
value = keymap[m.group('key')]
info = m.group('info')
iurl = burl % (keymap[key], value)
item = self.video_item()
item['title'] = '.. title not found..'
title = re.search(
'<div class=\"fileName.+?<a[^>]+>(?P<title>[^<]+)', info,
re.IGNORECASE | re.DOTALL)
if title:
item['title'] = title.group('title')
size = re.search('<span class=\"fileSize[^>]+>(?P<size>[^<]+)',
info, re.IGNORECASE | re.DOTALL)
if size:
item['size'] = size.group('size').strip()
time = re.search('<span class=\"fileTime[^>]+>(?P<time>[^<]+)',
info, re.IGNORECASE | re.DOTALL)
if time:
item['length'] = time.group('time')
item['url'] = iurl
item['img'] = m.group('logo')
self._filter(result, item)
# page navigation
data = util.substr(page, '<div class=\"paginator', '</div')
mnext = re.search('<a href=\"(?P<url>[^\"]+)\" class="next', data)
if mnext:
item = self.dir_item()
item['type'] = 'next'
item['url'] = mnext.group('url')
result.append(item)
return result
@cached(48)
def decr_url(self, url):
if url.startswith('#'):
ret = json.loads(util.request(url[1:]))
if ret.has_key('result'):
url = b64decode(ret['result'])
url = self._url(url)
return url
def resolve(self, item, captcha_cb=None):
item = item.copy()
url = item['url']
if url.startswith('http://www.ulozto.sk'):
url = self.base_url + url[20:]
url = self.decr_url(url)
url = self._url(url)
if url.startswith('#'):
util.error('[uloz.to] - url was not correctly decoded')
return
self.init_urllib()
self.login()
self.info('Resolving %s' % url)
if not item.has_key('vip'):
item['vip'] = False
vip = item['vip']
if vip:
page = util.request(url)
else:
try:
request = urllib2.Request(url)
response = urllib2.urlopen(request)
page = response.read()
response.close()
except urllib2.HTTPError, e:
traceback.print_exc()
return
if page.find('Stránka nenalezena!') > 0:
self.error('page with movie was not found on server')
return
if vip:
data = util.substr(page, '<h3>Neomezené stahování</h3>', '</div')
m = re.search('<a(.+?)href=\"(?P<url>[^\"#]+)\"', data,
re.IGNORECASE | re.DOTALL)
if m:
try:
self.rh.throw = True
resp = urllib2.urlopen(
urllib2.Request(self._url(m.group('url'))))
except RedirectionException:
# this is what we need, our redirect handler raises this
pass
except urllib2.HTTPError:
# this is not OK, something went wrong
traceback.print_exc()
self.error(
'Cannot resolve stream url, server did not redirected us'
)
self.info('POST url:' + post_url)
return
stream = self.rh.location
item['url'] = self._fix_stream_url(stream)
item['surl'] = url
return item
else:
data = util.substr(page, '<h3>Omezené stahování</h3>', '<script')
m = re.search('<form(.+?)action=\"(?P<action>[^\"]+)\"', data,
re.IGNORECASE | re.DOTALL)
if m:
self.rh.throw = True
stream_url = self._get_file_url_anonymous(
page, self._url(m.group('action')), response.headers,
captcha_cb)
if stream_url:
item['url'] = stream_url
item['surl'] = url
return item