def get_videos(self, datas):
url = datas.get('url')
page = datas.get('page', False)
if page:
page_txt = '&page=' + str(page)
else:
page_txt = ''
data = channel.get_url(self.main_url + '/mediatheek/tag/' + url +
page_txt)
regex = r""" id="video-(\d+)"><img src="([^"]+)" /></a>\s*<h5><a[^>]+>([^<]+)"""
for id, img, title in re.findall(regex, data):
vurl = channel.array2url(channel_id=self.channel_id,
url=id,
action='play_video')
channel.addLink(title, vurl, img)
next_page = re.search(
r"""\?page=(\d+)" class="pager-next active" title="Ga naar volg""",
data)
if next_page is not None:
page = next_page.group(1)
channel.addDir('Page nr ' + page,
self.icon,
channel_id=self.channel_id,
url=url,
action='show_videos',
page=page)
def get_videos(self, datas):
#from datetime import datetime
url = datas.get('url')
vid_id = datas.get('vid_id')
md5 = datas.get('md5')
if not vid_id:
vid_id, md5 = self.get_video_id(url)
if not vid_id:
return
page = datas.get('page', 1)
#http://www.rtbf.be/video/detail/ajax/av?page=1&timeFilter=all&orderBy=publish_view&videoId=1856226&returnMode=program&categoryId=&md5=00f9cfd447930fa1742d5d9f3e29e45cf083609f
data = channel.get_url(self.main_url + "/video/detail/ajax/av?page=" + str(page) + "&timeFilter=all&orderBy=publish_view&videoId=" + str(vid_id) + "&returnMode=program&categoryId=&md5=" + str(md5))
#data = channel.get_url(self.main_url + "/video/detail/ajax/av?page=" + str(page) + "&timeFilter=all&orderBy=more_recent&videoId=" + str(vid_id) + "&returnMode=program&categoryId=&md5=" + str(md5))
#regex = r"""video/detail_[^?]+\?id=(\d+)".+ src="([^"]+).+\n.+rel="">([^<]+).+\n.+\n.+\n.+<strong>([^<]+)"""
regex = r"""video/detail_[^?]+\?id=(\d+)".+ src="([^"]+).+\n.+>([^<]+)(.+\n){3,4}.+<strong>(\d\d/\d\d/\d{4})"""
#regex = r"""(?s)\?id=(\d+)&c[^>]+><img class="thumb" src="([^"]+).+?<h3><[^>]+>([^<]+)</a></h3>\s+<span[^>]+><a[^>]+>([^<]+)"""
for id, img, title, tt, date in re.findall(regex, data):
title = title + ' - ' + date
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(title.replace(''', "'").replace('"', '"'), vurl, img)
next_page = re.search(r"""rel="(\d+)">Suivante""", data)
if next_page is not None:
page = next_page.group(1)
channel.addDir('Page nr ' + page, self.icon, channel_id=self.channel_id, vid_id=vid_id, action='show_videos', page=page, md5=md5)
def get_video_news(self):
url = 'http://nieuws.vtm.be/herbekijk'
data = channel.get_url(url)
regex = r"""href="([^"]+)"><img src="([^"]+)[^<]+</a>\s+</div>\s+<div[^<]+</div>\s+<h3[^>]+>\s+<span>\s+<a href[^>]+>([^<]+)"""
for url, img, title in re.findall(regex, data):
vurl = channel.array2url(channel_id=self.channel_id, url=url, action='play_video', news='1')
channel.addLink(title, vurl, img)
def get_direct_videos(self):
url = 'http://www.rtl.be/rtltvi/page/les-directs-rtl-tvi/258.aspx'
data = channel.get_url(url)
regex = r"""OtherLiveItem(Big|)Img ><A href="http://www.rtl.be/[^/]+/[^/]+/[^/]+/(\d+)\.aspx"><img src="([^"]+)"[^>]+></A></DIV>\s+<[^>]+>([^<]+)</DIV>\s+<[^>]+>([^<]+)"""
for big, id, img, title, time in re.findall(regex, data):
title = channel.htmlentitydecode(title + ' - ' + time)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video', direct='1')
channel.addLink(title, vurl, img)
def get_direct_videos(self):
url = 'http://www.rtl.be/rtltvi/page/les-directs-rtl-tvi/258.aspx'
data = channel.get_url(url)
regex = r"""OtherLiveItem(Big|)Img ><A href="http://www.rtl.be/[^/]+/[^/]+/[^/]+/(\d+)\.aspx"><img src="([^"]+)"[^>]+></A></DIV>\s+<[^>]+>([^<]+)</DIV>\s+<[^>]+>([^<]+)"""
for big, id, img, title, time in re.findall(regex, data):
title = channel.htmlentitydecode(title + ' - ' + time)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video', direct='1')
channel.addLink(title, vurl, img)
def get_videos(self, datas):
url = datas.get('url')
data = channel.get_url(self.main_url + url)
regex = r"""class="contentheading"[^>]+>([^<]+)</td>\s+</tr>\s+</table>\s+<table[^>]+>\s+<tr>\s+<td[^>]+>\s+<p><a href="([^"]+)[^>]+><img.+? src="([^"]+)"""
for title, vurl, img in re.findall(regex, data):
title = title.strip()
vurl = channel.array2url(channel_id=self.channel_id, url=vurl, action='play_video')
channel.addLink(title, vurl, self.main_url + img)
def get_videos(self, datas):
url = datas.get('url')
data = channel.get_url(self.main_url + url)
regex = r"""class="contentheading"[^>]+>([^<]+)</td>\s+</tr>\s+</table>\s+<table[^>]+>\s+<tr>\s+<td[^>]+>\s+<p><a href="([^"]+)[^>]+><img.+? src="([^"]+)"""
for title, vurl, img in re.findall(regex, data):
title = title.strip()
vurl = channel.array2url(channel_id=self.channel_id,
url=vurl,
action='play_video')
channel.addLink(title, vurl, self.main_url + img)
def get_video_news(self):
url = 'http://nieuws.vtm.be/herbekijk'
data = channel.get_url(url)
regex = r"""href="([^"]+)"><img src="([^"]+)[^<]+</a>\s+</div>\s+<div[^<]+</div>\s+<h3[^>]+>\s+<span>\s+<a href[^>]+>([^<]+)"""
for url, img, title in re.findall(regex, data):
vurl = channel.array2url(channel_id=self.channel_id,
url=url,
action='play_video',
news='1')
channel.addLink(title, vurl, img)
def parse_lives(data):
regex = r"""href="http://www.rtbf.be/livecenter/([^"]+)"><img class="[^"]+" src="([^"]+)" alt="([^"]+).""" #*\3.*\3.*class="date">([^<]+).*is-live.*\1
for url, icon, name in re.findall(regex, data, flags=re.DOTALL):
print "found"
vurl = channel.array2url(channel_id=self.channel_id,
url=url,
action='play_live')
channel.addLink(
name.replace(''', "'").replace('"', '"'), vurl,
icon) # + ' - ' + date
def get_videos(self, datas):
url = datas.get('url')
if datas.get('direct', False):
self.get_direct_videos()
return
data = channel.get_url(self.main_url + self.channel_id + url)
regex = r"""<img src="([^"]+)"[^>]*><A class=[^']+'(\d+)[^>]+>[a-z0-9A-Z\s]+<BR>([^<]+)"""
ids = []
for img, id, title in re.findall(regex, data):
if id in ids:
continue
ids.append(id)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(channel.htmlentitydecode(title), vurl, img)
regex = r"""<A href="/""" + self.channel_id + """/video/(\d+)\.aspx[^"]*"[^>]*><img src="([^"]+?)"[^>]*></A>\s*?<H3>([^<]+)</H3>"""
for id, img, title in re.findall(regex, data):
if id in ids:
continue
ids.append(id)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(channel.htmlentitydecode(title), vurl, img)
def get_videos(self, datas):
url = datas.get('url')
if datas.get('direct', False):
self.get_direct_videos()
return
data = channel.get_url(self.main_url + self.channel_id + url)
regex = r"""<img src="([^"]+)"[^>]*><A class=[^']+'(\d+)[^>]+>[a-z0-9A-Z\s]+<BR>([^<]+)"""
ids = []
for img, id, title in re.findall(regex, data):
if id in ids:
continue
ids.append(id)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(channel.htmlentitydecode(title), vurl, img)
regex = r"""<A href="/""" + self.channel_id + """/video/(\d+)\.aspx[^"]*"[^>]*><img src="([^"]+?)"[^>]*></A>\s*?<H3>([^<]+)</H3>"""
for id, img, title in re.findall(regex, data):
if id in ids:
continue
ids.append(id)
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(channel.htmlentitydecode(title), vurl, img)
def get_videos(self, datas):
url = datas.get('url')
page = datas.get('page', False)
if page:
page_txt = '&page=' + str(page)
else:
page_txt = ''
data = channel.get_url(self.main_url + '/mediatheek/tag/' + url + page_txt)
regex = r""" id="video-(\d+)"><img src="([^"]+)" /></a>\s*<h5><a[^>]+>([^<]+)"""
for id, img, title in re.findall(regex, data):
vurl = channel.array2url(channel_id=self.channel_id, url=id, action='play_video')
channel.addLink(title, vurl, img)
next_page = re.search(r"""\?page=(\d+)" class="pager-next active" title="Ga naar volg""", data)
if next_page is not None:
page = next_page.group(1)
channel.addDir('Page nr ' + page, self.icon, channel_id=self.channel_id, url=url, action='show_videos', page=page)
def get_videos(self, datas):
url = datas.get('url')
print url
if url == 'http://vtm.be/het-nieuws/video':
print 'Nieuw'
return self.get_video_news()
data = channel.get_url(url)
regex = r"""<a href="([^"]+)">([^<]+)</a></h3>\s+<time[^>]+>([^<]+).+?<a href="\1"><img src="([^"]+)"""
for url, title, date, img in re.findall(regex, data, re.DOTALL):
title = title + ' - ' + date
vurl = channel.array2url(channel_id=self.channel_id, url=url, action='play_video')
channel.addLink(title, vurl, img)
next_page = re.search(r"""href="([^?]+\?page=(\d+))">volgende""", data)
if next_page is not None:
url = next_page.group(1)
page = str(int(next_page.group(2)) + 1)
channel.addDir('Page nr ' + page, self.icon, channel_id=self.channel_id, action='show_videos', url=url)
def get_videos(self, datas):
#from datetime import datetime
url = datas.get('url')
vid_id = datas.get('vid_id')
md5 = datas.get('md5')
if not vid_id:
vid_id, md5 = self.get_video_id(url)
if not vid_id:
return
page = datas.get('page', 1)
#http://www.rtbf.be/video/detail/ajax/av?page=1&timeFilter=all&orderBy=publish_view&videoId=1856226&returnMode=program&categoryId=&md5=00f9cfd447930fa1742d5d9f3e29e45cf083609f
data = channel.get_url(
self.main_url + "/video/detail/ajax/av?page=" + str(page) +
"&timeFilter=all&orderBy=publish_view&videoId=" + str(vid_id) +
"&returnMode=program&categoryId=&md5=" + str(md5))
#data = channel.get_url(self.main_url + "/video/detail/ajax/av?page=" + str(page) + "&timeFilter=all&orderBy=more_recent&videoId=" + str(vid_id) + "&returnMode=program&categoryId=&md5=" + str(md5))
#regex = r"""video/detail_[^?]+\?id=(\d+)".+ src="([^"]+).+\n.+rel="">([^<]+).+\n.+\n.+\n.+<strong>([^<]+)"""
regex = r"""video/detail_[^?]+\?id=(\d+)".+ src="([^"]+).+\n.+>([^<]+)(.+\n){3,4}.+<strong>(\d\d/\d\d/\d{4})"""
#regex = r"""(?s)\?id=(\d+)&c[^>]+><img class="thumb" src="([^"]+).+?<h3><[^>]+>([^<]+)</a></h3>\s+<span[^>]+><a[^>]+>([^<]+)"""
for id, img, title, tt, date in re.findall(regex, data):
title = title + ' - ' + date
vurl = channel.array2url(channel_id=self.channel_id,
url=id,
action='play_video')
channel.addLink(
title.replace(''', "'").replace('"', '"'), vurl, img)
next_page = re.search(r"""rel="(\d+)">Suivante""", data)
if next_page is not None:
page = next_page.group(1)
channel.addDir('Page nr ' + page,
self.icon,
channel_id=self.channel_id,
vid_id=vid_id,
action='show_videos',
page=page,
md5=md5)
def get_videos(self, datas):
url = datas.get('url')
print url
if url == 'http://vtm.be/het-nieuws/video':
print 'Nieuw'
return self.get_video_news()
data = channel.get_url(url)
regex = r"""<a href="([^"]+)">([^<]+)</a></h3>\s+<time[^>]+>([^<]+).+?<a href="\1"><img src="([^"]+)"""
for url, title, date, img in re.findall(regex, data, re.DOTALL):
title = title + ' - ' + date
vurl = channel.array2url(channel_id=self.channel_id,
url=url,
action='play_video')
channel.addLink(title, vurl, img)
next_page = re.search(r"""href="([^?]+\?page=(\d+))">volgende""", data)
if next_page is not None:
url = next_page.group(1)
page = str(int(next_page.group(2)) + 1)
channel.addDir('Page nr ' + page,
self.icon,
channel_id=self.channel_id,
action='show_videos',
url=url)
def parse_lives(data):
regex = r"""href="http://www.rtbf.be/livecenter/([^"]+)"><img class="[^"]+" src="([^"]+)" alt="([^"]+).""" #*\3.*\3.*class="date">([^<]+).*is-live.*\1
for url, icon, name in re.findall(regex, data, flags=re.DOTALL):
print "found"
vurl = channel.array2url(channel_id=self.channel_id, url=url, action='play_live')
channel.addLink(name.replace(''', "'").replace('"', '"') , vurl, icon) # + ' - ' + date