def drawBbcCoUkNew(url): htmlContent = Downloader.getContentFromUrl(url=url) title = Decoder.extract('<p class="story-body__introduction">', "</p><div", htmlContent) if 'property="articleBody"' in htmlContent: body = Decoder.extract( 'property="articleBody"', " </div>", htmlContent, ) body = body.replace('<span class="off-screen">Image copyright</span>', "") body = body.replace('<span class="story-image-copyright">AFP</span>', "") body = body.replace('<span class="story-image-copyright">Reuters</span>', "") body = body.replace('<span class="off-screen">Image caption</span>', "") body = body.replace('<span class="off-screen">Media caption</span>', "") while '<span class="media-caption__text">' in body: line = Decoder.extractWithRegex('<span class="media-caption__text">', "</span>", body) body = body.replace(line, "") elif 'class="text-wrapper"' in htmlContent: # special content body = Decoder.extract('class="text-wrapper"', "</p>\n", htmlContent) dates = Decoder.extractWithRegex('<div class="date', "</div>", body) lastUpdate = Decoder.extractWithRegex('<p class="date ', "</p>", body) body = body.replace(dates, "") body = body.replace(lastUpdate, "") elif '<figcaption class="sp-media-asset' in htmlContent: body = Decoder.extract('<figcaption class="sp-media-asset', "</p><div ", htmlContent) if ">" in body: body = body[body.find(">") + 1 :] body = Decoder.removeHTML(body).replace(".", ".\n").replace(">", "") logger.debug("body is: " + body) drawNew(textContent=(body))
def getChannels(page): x = [] if str(page) == "0": page = Live9net.MAIN_URL html = Live9net.getContentFromUrl(page, "", Live9net.cookie, "") # print html if html.find("ESPN</") > -1: # it's a list, needs decode table = Decoder.extract("ESPN</", "<div>", html) x = Live9net.extractElements(table) logger.debug("live9 channels logic done!") else: iframeUrl = Decoder.extract('src="', '"></iframe>', html) html2 = Live9net.getContentFromUrl(iframeUrl, "", Live9net.cookie, page) # print html2 if html2.find('src="http://sawlive.tv/') > -1 or html2.find('src="http://www3.sawlive') > -1: if html2.find('src="http://sawlive.tv/') > -1: scriptSrc = Decoder.extractWithRegex("http://sawlive", '"></script>', html2).replace( '"></script>', "" ) else: scriptSrc = Decoder.extractWithRegex("http://www3.sawlive", '"></script>', html2).replace( '"></script>', "" ) finalRtmpUrl = Decoder.extractSawlive(scriptSrc, iframeUrl) element = {} element["link"] = finalRtmpUrl element["title"] = "Watch channel" element["permalink"] = True logger.debug("finished append element!") x.append(element) return x
def getChannels(page='0'): x = [] if str(page) == '0': page = Yomvies.CHANNELS_PAGE logger.debug("loading json data from: "+page) bruteJSON = Yomvies.getContentFromUrl(page,"",Yomvies.cookie,Yomvies.MAIN_URL) logger.debug("parsing string to json...") i = 0 for jsonChannel in bruteJSON.split('{"CodCadenaTv":'): if i>0: element = {} codTv = Decoder.extract('"','"',jsonChannel) element["title"] = Decoder.extract('"Nombre":"','"',jsonChannel) element["thumbnail"] = Decoder.extract('"Logo":"','"',jsonChannel).replace("\\","") m3u8Url = Decoder.extract('"PuntoReproduccion":"','"',jsonChannel).replace("{network}",Yomvies.NETWORK).replace("\\","") logger.debug("Appending channel: "+element["title"]+", with url: "+m3u8Url+", img: "+element["thumbnail"]) headers = 'Referer='+codTv element["link"] = m3u8Url+"|"+headers x.append(element) i+=1 else: link = Yomvies.extractTargetVideo(page) element = {} element["title"] = page element["link"] = link element["finalLink"] = True x.append(element) return x
def searchLists(param): url = ( "https://www.googleapis.com/customsearch/v1element?" "key=AIzaSyCVAXiUzRYsML1Pv6RwSG1gunmMikTzQqY" "&rsz=filtered_cse" "&num=20" "&hl=en" "&prettyPrint=false" "&source=gcsc" "&gss=.com" "&sig=8bdfc79787aa2b2b1ac464140255872c" "&cx=013305635491195529773:0ufpuq-fpt0" ) url += "&q=" + param + "&sort=date&googlehost=www.google.com&callback=google.search.Search.apiary846" results = Pastebin.getContentFromUrl(url) x = [] jsonString = Decoder.extract(',"results":', "]});", results) logger.debug(jsonString) for jsonResult in results.split('{"GsearchResultClass"'): element = {} link = Decoder.extract('"url":"', '","', jsonResult) if "pastebin.com" in link and "/raw/" not in link: link = link[: link.rfind("/")] + "/raw/" + link[link.rfind("/") + 1 :] title = Decoder.extract('"title":"', '","titleNoFormatting"', jsonResult) if "http" in link: logger.debug("appending result: " + title + ", url: " + link) element["title"] = title element["link"] = link x.append(element) return x
def extractTargetVideoJSON(page): title = '' link = '' thumbnail = '' headers = Youtube.buildHeaders() response = Youtube.getContentFromUrl(url=str(page + "?pbj=1"), headers=headers) logger.debug("response is: "+response) try: responseJ = Decoder.extract('ytplayer.config = ','};',response)+"}" #logger.debug("json extracted is: " + responseJ) jsonResponse = json.loads(responseJ) logger.debug("json loaded") bruteVideoInfo = jsonResponse["args"] logger.debug("obtained brute video info...") title = bruteVideoInfo["title"] url = bruteVideoInfo["adaptive_fmts"] url = Decoder.extract('url=',",",url) url = urllib.unquote(url) #url = url[:-1] thumbnail = bruteVideoInfo["thumbnail_url"] logger.debug("extracted final url: "+url) except: logger.error("error parsing video info") pass element = {} element["title"] = title element["link"] = link element["thumbnail"] = thumbnail element["finalLink"] = True return element
def extractChannel(html,referer): element = {} logger.debug('processing html...') if html.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="400" src="')>-1: element = Cineestrenostv.extractIframeChannel(html,referer) elif html.find('.php')>-1 and referer.find(".php")==-1: logger.debug("proccessing level 1, cookie: "+Cineestrenostv.cookie) iframeUrl = Decoder.extractWithRegex('http://','.php',html) if iframeUrl.find('"')>-1: iframeUrl = iframeUrl[0:iframeUrl.find('"')] html2 = Cineestrenostv.getContentFromUrl(iframeUrl,"",Cineestrenostv.cookie,referer) if html2.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="400" src="')>-1 or '<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" allowfullscreen width="653" height="403" src="' in html2: element = Cineestrenostv.extractIframeChannel(html2,iframeUrl) elif html.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="500" src="')>-1: iframeUrl = Decoder.extract('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="500" src="','"></iframe>',html) #same case with different width and height: TODO: change to regex!! html2 = Cineestrenostv.getContentFromUrl(iframeUrl,"","",referer) if html2.find('<th scope="col"><a href="/')>-1: partialLink = Decoder.extract('<th scope="col"><a href="/','"><font color="ffffff">',html2) completeLink = Cineestrenostv.MAIN_URL+"/"+partialLink html3 = Cineestrenostv.getContentFromUrl(completeLink,"",Cineestrenostv.cookie,iframeUrl) if html3.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="400" src="')>-1: element = Cineestrenostv.extractIframeChannel(html3,completeLink) elif referer.find("php")!=-1: referer = referer.replace("ñ","%C3%B1") html2 = Cineestrenostv.getContentFromUrl(referer,"",Cineestrenostv.cookie,referer) element = Cineestrenostv.extractIframeChannel(html2,referer) return element
def extractElements(table): x = [] i = 0 for value in table.split('<a '): logger.debug("loop: "+str(i)) if i>0: element = {} logger.debug("processing html: "+value) if value.find('<img ')==-1: title = Decoder.rExtract(">",'</a></li>',value) link = Decoder.extract("href=\"/",'"',value) if title == '</a': title = Decoder.extract('class="menu-item">','<',value).replace(" ","") element["title"] = title element["link"] = Skylinewebcamscom.MAIN_URL+link if len(title)>0 and link.find("#")==-1 and len(element["link"])>len(Skylinewebcamscom.MAIN_URL) and (title.find("<")==-1 and title.find(">")==-1): logger.debug("append: "+title+", link: "+element["link"]) x.append(element) else: logger.debug("discarted: "+title+", link: "+element["link"]) else: img = "http://"+Decoder.extract("data-original=\"//",'" ',value) title = Decoder.extract("class=\"title\">",'</span>',value) link = Decoder.extract("href=\"/",'"',value) element["title"] = title element["link"] = Skylinewebcamscom.MAIN_URL+link element["thumbnail"] = img element["permaLink"] = True if link.find(".html")>-1 and (title.find("<")==-1 and title.find(">")==-1): logger.debug("append: "+title+", link: "+element["link"]+", img: "+element["thumbnail"]) x.append(element) else: logger.debug("discarted: "+title+", link: "+element["link"]+", img: "+element["thumbnail"]) i+=1 return x
def extractElementsAlbum(table): x = [] i = 0 for value in table.split( '<li class="topListenedBox click js-lateral-info" onclick=\'albumClick(' ): if i > 0: element = {} title = Decoder.extract('<div class="topListenedBoxDiv">', '</div>', value).replace('<br>', " - ") link = Decoder.extract('","', '");\'>', value) img = Decoder.extract(' data-src="', '" ', value) element["title"] = title if link.find(".mp3") == -1: element["link"] = base64.standard_b64encode( Fildonet.ALBUM + link) else: element["link"] = link element["thumbnail"] = img logger.info("append3: " + title + ", link: " + element["link"] + ", thumbnail: " + element["thumbnail"]) x.append(element) i += 1 return x
def getChannels(page): x = [] start = False if str(page) == '0': start = True page=Sports4u.MAIN_URL html = Sports4u.getContentFromUrl(page,"",Sports4u.cookie,"") #print html if start and 'live-channels-list">' in html: #it's a list, needs decode table = Decoder.extract('live-channels-list">','</li><br>',html) logger.debug("using menu table: "+table) x = Sports4u.extractElements(table) logger.debug("channel list logic done!") else: iframeUrl = Decoder.extract('<iframe frameborder="0" marginheight="0" marginwidth="0" height="490" ','"></iframe>',html) iframeUrl = Decoder.extract('src="','"',iframeUrl) logger.debug("iframeUrl is: "+iframeUrl) html2 = Sports4u.getContentFromUrl(url=iframeUrl,referer=page) logger.debug("html is: "+html2) file = Cricfreetv.seekIframeScript(html2,page,iframeUrl) logger.debug("Finished file logic, obtained file: "+file) element = {} element["link"] = file element["title"] = "Watch streaming" x.append(element) return x
def extractFinalRtmpUrl(url,referer): rtmpUrl = "" html = Mamahdcom.getContentFromUrl(url,"",Mamahdcom.cookie,referer) if 'file:\'' in html: file = Decoder.extract("file:'",'\',',html) rtmp = file[0:file.rfind("/") + 1] playpath = file[file.rfind("/") + 1:] swfUrl = "" secureToken = "SECURET0KEN#yw%.?()@W!" if url.find("hdcast.org") > -1: swfUrl = "http://player.hdcast.org/jws/jwplayer.flash.swf" rtmpUrl = rtmp + " playPath=" + playpath + " swfUrl=" + swfUrl + " pageUrl=" + url + " flashver=WIN/2019,0,0,226 live=true timeout=14 token=" + secureToken logger.debug("built final rtmp link: " + rtmpUrl) elif 'allowtransparency="true" src=' in html: logger.debug("using second way...") secondIframe = Decoder.extract('allowtransparency="true" src=', ' ', html).replace("&","&") logger.debug("found second way url: " + secondIframe+", referer: "+url) headers = { "User-Agent": Downloader.USER_AGENT, "Accept-Language": "en-US,en;q=0.8,es-ES;q=0.5,es;q=0.3", "Upgrade-Insecure-Requests" : "1", "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "Referer": url } html2 = Mamahdcom.getContentFromUrl(url=secondIframe,headers=headers) logger.debug("html2 is: "+html2) if 'file:"' in html2: rtmpUrl = Decoder.extract('file:"', '",', html2) logger.debug("using m3u8 for: "+rtmpUrl) return rtmpUrl
def getChannels(page): x = [] logger.debug("using tvshowme...") if str(page) == '0': page=Tvshowme.MAIN_URL html = Tvshowme.getContentFromUrl(page,"",Tvshowme.cookie,"") table = Decoder.extract('<span class="yawp_wim_title">Latest 150 Posts</span> <ul>','</ul>',html) x = Tvshowme.extractElements(table) elif page=="search": #display keyboard, it will wait for result keyboard = XBMCUtils.getKeyboard() keyboard.doModal() text = "" if (keyboard.isConfirmed()): text = keyboard.getText() page = "http://www.tvshow.me/?s="+urllib.quote(text) html = Tvshowme.getContentFromUrl(url=page) logger.debug(html) table = Decoder.extract('<div id="content"', '<h3 class="assistive-text">', html) logger.debug("table is: "+table) x = Tvshowme.extractLinks2(table) else: html = Tvshowme.getContentFromUrl(page, "", Tvshowme.cookie, Tvshowme.MAIN_URL) logger.debug(html) table = Decoder.extract('<div id="content"', '</article>', html) x = Tvshowme.extractLinks(table) return x
def getChannels(page): x = [] if str(page) == '0': html = Mamahdcom.getContentFromUrl(Mamahdcom.MAIN_URL,"",Mamahdcom.cookie,"") else: html = Mamahdcom.getContentFromUrl(page,"",Mamahdcom.cookie,"") #print html if page=='0': #menu table = Decoder.extract('<div class="standard row channels">','</div>',html) logger.debug("table is: "+table) x = Mamahdcom.extractElements(table) logger.debug("mamahd channels logic done!") else: iframeHtml = Decoder.extract("<iframe ","</iframe>",html) iframeUrl = Decoder.extract('src="','"',iframeHtml) html2 = Mamahdcom.getContentFromUrl(url=iframeUrl,referer=page) logger.debug("obtained html from iframe: "+iframeUrl+"; html: "+html2) if 'src="http://hdcast.org' in html2: logger.debug("found script, launching logic...") scriptUrl = Decoder.extract('<script type="text/javascript" src="','"></script>',html2) logger.debug("extracting script url... from: "+scriptUrl) iframeUrl2 = Mamahdcom.extractScriptIframeUrl(html2,scriptUrl,iframeUrl) logger.debug("script url extracted: "+iframeUrl2) finalRtmpUrl = Mamahdcom.extractFinalRtmpUrl(iframeUrl2,iframeUrl) logger.debug("rtmp extracted is: "+finalRtmpUrl) element = {} element["link"] = finalRtmpUrl element["title"] = "Watch channel" element["permaLink"] = True logger.debug("finished append element!") x.append(element) return x
def extractAllVideosFromHtml(html): x = [] tableHtml = Decoder.extract('class="item-section">','<div class="branded-page-box search-pager',html) i=0 for rowHtml in tableHtml.split('<div class="yt-lockup-dismissable yt-uix-tile">'): if i>0: logger.debug("row html is: "+rowHtml) element = {} link = "/watch?"+Decoder.extract('href="/watch?', '"', rowHtml) title = Decoder.extract(' title="','"', rowHtml) if 'youtube.com' not in link: link = Youtube.MAIN_URL+link logger.debug("link: " + link + ", title is: " + title) image = Decoder.extractWithRegex('https://i.ytimg.com/','"',rowHtml).replace('"','') element["title"] = title element["page"] = link if '&list=' not in link: element["finalLink"] = True element["thumbnail"] = image x.append(element) i+=1 #add next if pagination exists if '<div class="branded-page-box search-pager spf-link ">' in html: bruteHtmlPaginate = Decoder.rExtract('<div class="branded-page-box search-pager spf-link ">','<div class="branded-page-v2-secondary-col">',html) title = Decoder.rExtract(">","</span></a>",bruteHtmlPaginate) title = title[:len(title)-2] link = Decoder.rExtract('href="','" class="yt-uix-button', bruteHtmlPaginate) if 'youtube.com' not in link: link = Youtube.MAIN_URL + link element = {} element["title"] = title element["page"] = link logger.debug("link: " + link + ", title is: " + title) x.append(element) return x
def getWidthAndHeightParams(html): subUrl = "" if html.find("; v_width=")>-1: width = Decoder.extract("; v_width=",";",html) height = Decoder.extract("; v_height=",";",html) subUrl = "&vw="+width+"&vh="+height logger.debug("width-height subUrl now is: "+subUrl) return subUrl
def getWidthAndHeightParams(html): subUrl = "" if html.find("; width='")>-1: width = Decoder.extract("; width='","'",html) height = Decoder.extract("; height='","'",html) subUrl = "&width="+width+"&height="+height elif html.find("; v_height=")>-1: width = Decoder.extract("; v_width=",";",html) height = Decoder.extract("; v_height=",";",html) subUrl = "&vw="+width+"&vh="+height return subUrl
def extractElements(table): x = [] for fieldHtml in table.split('<li>'): if fieldHtml.find("<a href=")>-1: element = {} element["link"] = Decoder.extract('<a href="','"',fieldHtml) element["title"] = Decoder.extract('alt="','">',fieldHtml) element["thumbnail"] = Decoder.extract('src="','" ',fieldHtml) logger.debug("found title: "+element["title"]+", link: "+element["link"]+", thumbnail: "+element["thumbnail"]) if len(element["title"])>0: x.append(element) return x
def extractScriptIframeUrl(html,scriptUrl,referer): iframeUrl = "" logger.debug("extracting script iframe... url: "+scriptUrl) scriptContent = Mamahdcom.getContentFromUrl(scriptUrl,"",Mamahdcom.cookie,referer) #print scriptContent iframeUrl = Decoder.extract('src="',"'",scriptContent) logger.debug("brute iframeUrl is: "+iframeUrl) if iframeUrl.find("?u=")>-1: if '<script type="text/javascript"> fid="' in html: id = Decoder.extract('<script type="text/javascript"> fid="','"; ',html) iframeUrl = iframeUrl+id+Mamahdcom.getWidthAndHeightParams(html) return iframeUrl
def extractElements(table): x = [] for fieldHtml in table.split('</a>'): logger.debug("using html: "+fieldHtml) element = {} element["link"] = Decoder.extract('href="','"',fieldHtml) element["title"] = Decoder.extract("<span>","</span>",fieldHtml) element["thumbnail"] = Decoder.extract('<img src="','"',fieldHtml) element["permaLink"] = True logger.debug("found title: "+element["title"]+", link: "+element["link"]+", thumb: "+element["thumbnail"]) if "http" in element["link"]: x.append(element) return x
def extractLinks2(html): x = [] i=0 for value in html.split('<h2 class="entry-title ">'): if i>1: logger.debug("partial html is: "+value) element = {} title = Decoder.extract(' title="','"', value) link = Decoder.extract('href="','"', value) element["title"] = title.replace("Permalink to ","").replace("–","-") element["link"] = link x.append(element) i+=1 return x
def extractIframeChannel(contentHtml,referer): logger.debug("proccessing level 2, cookie: "+Cineestrenostv.cookie) iframeUrl2 = "dummy url" if contentHtml.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="653" height="403" src="')>-1: iframeUrl2 = Decoder.extract('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="653" height="403" src="','"></iframe>',contentHtml).replace("ñ","%C3%B1") #same case with different width and height: TODO: change to regex!! elif contentHtml.find('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="400" src="')>-1: iframeUrl2 = Decoder.extract('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" width="650" height="400" src="','"></iframe>',contentHtml).replace("ñ","%C3%B1") #normal cases, standar width and height elif '<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" allowfullscreen width="653" height="403" src="' in contentHtml: iframeUrl2 = Decoder.extract('<iframe scrolling="no" marginwidth="0" marginheight="0" frameborder="0" allowfullscreen width="653" height="403" src="','"></iframe>', contentHtml).replace("ñ", "%C3%B1") # normal cases, standar width and height if iframeUrl2!="dummy url": html3 = Cineestrenostv.getContentFromUrl(iframeUrl2,"","",referer) return Cineestrenostv.mainLogicExtractIframeChannel(html3,iframeUrl2) else: return Cineestrenostv.mainLogicExtractIframeChannel(contentHtml,referer)
def extractElements(table,domain): x = [] i = 0 for value in table.split('"name"'): if i>0: element = {} title = Decoder.extract('"','"',value).replace('- ','') link = Decoder.extract('shortcut":"','"',value) element["title"] = title element["link"] = domain+"/channel/"+link+"/frame" logger.debug("append: "+title+", link: "+element["link"]) x.append(element) i+=1 return x
def extractElements(table): x = [] i = 0 for value in table.split('<li>'): logger.debug("loop: "+str(i)) if i>0: element = {} title = Decoder.extract(">",'</a></li>',value) link = Decoder.extract("href=\"",'"',value) element["title"] = title element["link"] = base64.b64encode(str(Zonasportsme.MAIN_URL+link)) logger.debug("append: "+title+", link: "+element["link"]) x.append(element) i+=1 return x
def extractElementsArtist(html): x = [] i=0 for value in html.split('<li class="topListenedBox click js-lateral-info " >'): if i>0: element = {} title = Decoder.extract('<div class="topListenedBoxDiv click js-lateral-info ">','</div>',value) element["title"] = title element["link"] = base64.standard_b64encode(Fildonet.ARTIST+title) if value.find('data-src="')!=-1: element["thumbnail"] = Fildonet.MAIN_URL+Decoder.extract('data-src="','" ',value) logger.info("append1: "+title+", link: "+element["link"]) x.append(element) i+=1 return x
def extractElements(page,tableHtml): x = [] i = 0 for value in tableHtml.split('<a '): if i>0: element = {} title = Decoder.extract(">","</a>",value) link = Decoder.extract("href=\"","\"",value) element["title"] = page+" ver. "+title element["link"] = page[0:1]+"00/"+link if "://" not in element["link"]: element["link"] = RTVE.MAIN_URL+element["link"] logger.debug("append: "+element["title"]+", link: "+element["link"]) x.append(element) i+=1 return x
def parseListSongs(songs,html): x = [] #jsonSongs = json.load(songs) for elementHtml in html.split("<Channel "): element = {} title = Decoder.extract('name="','"',elementHtml) channel = Decoder.extract('<RTMP>','</RTMP>',elementHtml) url = Decoder.extract("<URL>","</URL>",elementHtml) element["title"] = title element["link"] = channel+" playpath="+(url.replace(' ','%20'))+" pageUrl="+R977Musiccom.MAIN_URL+" swfUrl="+R977Musiccom.REFERER element["finalLink"] = True if element["link"].find("rtmp")==0: logger.info("found element: "+element["title"]+", with link: "+element["link"]) x.append(element) return x
def extractElementsAlbum(table): x = [] i = 0 for value in table.split('<div class="album">'): if i>0: element = {} title = Decoder.extract(' alt="','"/>',value) link = Decoder.extract('<a href="','" ',value) img = Decoder.extract('src="','" ',value) element["title"] = title element["link"] = Redmp3cc.MAIN_URL+link element["thumbnail"] = Redmp3cc.MAIN_URL+img logger.info("append: "+title+", link: "+element["link"]) x.append(element) i+=1 return x
def extractLinks(html): x = [] i=0 for value in html.split(' href='): if i>1: element = {} title = Decoder.extract('>','</a>', value).replace("–","-") link = Decoder.extract('"','"', value) element["title"] = title element["link"] = link element["finalLink"] = True if "<img" not in title and "tvshow.me" not in link: logger.debug("append: " + title + ", link: " + element["link"]) x.append(element) i+=1 return x
def extractIframe(html,referer): iframeUrl = '' if '<iframe frameborder="0" marginheight="0" allowfullscreen="true" marginwidth="0" height="555" src="' in html: iframeUrl = Decoder.extract('<iframe frameborder="0" marginheight="0" allowfullscreen="true" marginwidth="0" height="555" src="','"',html) elif '<iframe frameborder="0" marginheight="0" marginwidth="0" height="490" src="' in html: iframeUrl = Decoder.extract('<iframe frameborder="0" marginheight="0" marginwidth="0" height="490" src="','"',html) if "'" in iframeUrl: iframeUrl = iframeUrl[0:iframeUrl.find("'")] logger.debug("level 1, iframeUrl: "+iframeUrl+", cookie: "+Cricfreetv.cookie) if iframeUrl!='': html = Cricfreetv.getContentFromUrl(iframeUrl,"",Cricfreetv.cookie,referer) file = Cricfreetv.seekIframeScript(html,referer,iframeUrl) item = {} item["title"] = referer item["link"] = file return item
def getChannels(page): x = [] if str(page) == '0': page=Acetvru.MAIN_URL html = Acetvru.getContentFromUrl(page,"",Acetvru.cookie,"") html = Decoder.extract('var playlist = [',']',html) x = Acetvru.extractElements(html) return x
def extractElements(table): x = [] for fieldHtml in table.split(' href="'): if fieldHtml.find("<li>")>-1 or fieldHtml.find(' <img src="')>-1: element = {} element["link"] = Zoptvcom.MAIN_URL+fieldHtml[0:fieldHtml.find('"')] if fieldHtml.find(' <img src="')>-1: element["title"] = Decoder.extract("<span>","</span>",fieldHtml) element["thumbnail"] = Zoptvcom.MAIN_URL+Decoder.extract('<img src="','"> <span>',fieldHtml) logger.debug("found thumbnail: "+element["thumbnail"]) else: element["title"] = fieldHtml[fieldHtml.find('">')+2:].replace("<li>","").replace("</li>","").replace("</a>","").replace("<a","").rstrip(os.linesep) logger.debug("found title: "+element["title"]+", link: "+element["link"]) if len(element["title"])>0: x.append(element) return x
def getChannels(page): x = [] if page == '0': page = RedeneobuxCom.LIST_PAGE results = RedeneobuxCom.getContentFromUrl(page) i=0 for result in results.split('<div class="media">'): if i>0: element = {} img = Decoder.extract('<img src=\'',"'",result) link = Decoder.extract('location.href=\'', "'", result) title = Decoder.extract('\' alt=\'', "'", result) if "http" in link: logger.debug("appending result: "+title+", url: "+link) element["title"] = title element["link"] = link element["thumbnail"] = img x.append(element) i+=1 else: content = RedeneobuxCom.getContentFromUrl(url=page,referer=RedeneobuxCom.LIST_PAGE) logger.debug("list content is: " + content) url = Decoder.extractWithRegex('http'," ",content).replace(" ","") logger.debug("url is: " + url) if 'adf' in url: listUrl = Decoder.decodeAdfly(url) logger.debug("list obtained is: "+listUrl) m3uContent = Downloader.getSimpleDownload(listUrl) #simple urllib2 download logger.debug("content: "+m3uContent) i=0 for lineContent in m3uContent.split('#EXTINF:'): if i>0: title = Decoder.extract(',','\n',lineContent) lineContent = lineContent[lineContent.find("\n"):] urlContent = Decoder.extractWithRegex('http://',"\n",lineContent).replace('\n','') element = {} element["title"] = title element["link"] = urlContent#+"|"+Downloader.getHeaders(listUrl) element["thumbnail"] = '' element["finalLink"] = True if "://" in urlContent: logger.debug("added: " + title + ", content: " + urlContent) x.append(element) i+=1 return x
def extractElements(table): x = [] element = {} element["title"] = "Search" element["link"] = "search" x.append(element) i=0 for value in table.split('<li>'): if i>0: element = {} title = Decoder.extract('/">','</a>',value).replace("–","-") link = Decoder.extract('<a href="','"',value) element["title"] = title element["link"] = link logger.debug("append: "+title+", link: "+element["link"]) x.append(element) i+=1 return x
def extractMainChannels(html): x = [] i = 0 for value in html.split('guide-item yt-uix-sessionlink yt-valign spf-link'): if i>0 and value.find("href=\"")>-1 and value.find('title="')>-1: element = {} title = Decoder.extract('title="','"',value) link = Youtube.MAIN_URL+Decoder.extract('href="','"',value) element["title"] = title element["page"] = link if value.find('<img src="')>-1: element["thumbnail"] = Decoder.extract('<img src="','"',value) logger.debug("thumbnail: "+element["thumbnail"]) logger.debug("append: "+title+", link: "+element["page"]) if "Home" not in title and "Movies" not in title: x.append(element) i+=1 return x
def extractElementsArtist(html): x = [] i = 0 for value in html.split( '<li class="topListenedBox click js-lateral-info " >'): if i > 0: element = {} title = Decoder.extract( '<div class="topListenedBoxDiv click js-lateral-info ">', '</div>', value) element["title"] = title element["link"] = base64.standard_b64encode(Fildonet.ARTIST + title) if value.find('data-src="') != -1: element["thumbnail"] = Fildonet.MAIN_URL + Decoder.extract( 'data-src="', '" ', value) logger.info("append1: " + title + ", link: " + element["link"]) x.append(element) i += 1 return x
def getChannels(page, cookie=''): x = [] print page if str(page) == '0': page = Radionet.MAIN_URL stations_lists = Radionet.getContentFromUrl( "http://www.radio.net/stations/", "", Radionet.cookie, Radionet.REFERER) x = Radionet.parseListStations(stations_lists) else: html = Radionet.getContentFromUrl(page, "", cookie, Radionet.REFERER) element = {} element["title"] = Decoder.extract('"seoTitle":"', '",', html) element["link"] = Decoder.extract('"streamUrl":"', '",', html) element["thumbnail"] = Decoder.extract('"logo100x100":"', '",', html) element["finalLink"] = True x.append(element) return x
def getCatalogSearchMenu(params=[]): text = "" page = 1 if type(params) is list: logger.debug("text") for element in params: logger.debug("text %s" % str(element)) if "text" in element: text = element["text"] if "page" in element: page = element["page"] url = 'https://www.lexaloffle.com/bbs/lister.php?use_hurl=1&cat=7&sub=2&page=%s&sub=2&mode=carts&orderby=featured&search=%s' % ( page, text) http = urllib3.PoolManager() logger.debug("lexaoffle url is: %s" % url) r = http.request('GET', url, preload_content=False) html = r.data.decode() bruteCards = Decoder.extract('pdat=[', '];', html) cards = [] for bruteCardLine in bruteCards.split(",``],"): logger.debug("line is %s" % bruteCardLine) if '[' in bruteCardLine: element = {} bruteCardLine = bruteCardLine[:bruteCardLine.find('],')] name = Decoder.extract(', `', '`,', bruteCardLine) id = Decoder.extract("['", "'", bruteCardLine) link = 'https://www.lexaloffle.com/bbs/get_cart.php?cat=7&play_src=0&lid=%s' % id out = re.sub('[^A-Za-z0-9.\-,\ ]+', '', name) + ".p8.png" out = ROMS_PATH + "/pico8/" + out command = 'curl "%s" --create-dirs --output "%s" \n' % (link, out) element["external"] = command element["action"] = 'command-exit' element["title"] = name cards.append(element) #back element = {} element["title"] = "Back" element["action"] = 'function' element["external"] = 'getCatalogMenu' cards.append(element) return cards
def extractElementsPlayer(html): x = [] i = 0 for value in html.split("<li class='hotSongsItem' songid="): if i > 0: element = {} title = Decoder.extract("songname='", "'", value) + " - " + Decoder.extract( "songartist='", "'", value) link = Decoder.extract("songmp3='", "'", value) element["title"] = title if link.find(".mp3") == -1: element["link"] = base64.standard_b64encode( Fildonet.MAIN_URL + link) else: element["link"] = link element["thumbnail"] = Fildonet.PLAY logger.info("append2: " + title + ", link: " + element["link"]) x.append(element) i += 1 return x
def extractElements(table,html=""): x = [] splitter = 'data-playlist-id="' splitter2 = 'Flash Player">' splitter3 = "new_player_block.nss_load_playlist('" for fieldHtml in table.split('<li '): if fieldHtml.find(splitter)>-1: element = {} playlistId = Decoder.extract(splitter,'" >',fieldHtml) title = Decoder.extract(splitter2,'</a>',fieldHtml).strip() url = Decoder.extract(splitter3,"' + jQuery(",fieldHtml).replace("&","&") rel = Decoder.rExtract('" rel="','">'+title+"</a>",html) url = R977Musiccom.MAIN_URL+url+rel+"&userId=0" element["title"] = title element["link"] = base64.standard_b64encode(url) logger.info("found title: "+element["title"]+", link: "+element["link"]) if len(element["title"])>0: #TODO: now we tries to extract the content from json 'html' x.append(element) return x
def parseListStations(html): x = [] html = Decoder.extract('<div class="col-sm-7 col-md-8 station-list">', 'aside class="col-sm-5 col-md-4">', html) for elementHtml in html.split( '<a class="stationinfo-info-toggle" href="" ng-click="toggle()"></a>' ): element = {} link = Decoder.extract('<a href="//', '" class="stationinfo-link">', elementHtml) title = Decoder.extract('<strong>', '</strong>', elementHtml) img = Decoder.extract('<img src="', '"', elementHtml) element["title"] = title element["link"] = link element["thumbnail"] = img if element["link"].find("http") != 0: element["link"] = "http://" + element["link"] if element["title"].find('</div>') == -1: logger.info("found element: " + element["title"] + ", with link: " + element["link"]) x.append(element) return x
def getChannels(page,cookie=''): x = [] referer = R977Musiccom.REFERER #print page if str(page) == '0': page=R977Musiccom.MAIN_URL html = R977Musiccom.getContentFromUrl(page,"",R977Musiccom.cookie,referer) stations_lists = R977Musiccom.getContentFromUrl("http://www.977music.com/ajax/stations_list_xml.php","",R977Musiccom.cookie,referer) #print "station list: "+stations_lists else: page = base64.standard_b64decode(page) logger.info("launching petition from page: "+page) #extract id id = Decoder.extract("?id=","&",page) songId = Decoder.extract("song_id=","&",page) if cookie=='': logger.info("launching to get an virgin cookie...") R977Musiccom.getContentFromUrl(R977Musiccom.MAIN_URL,"","","") #get a right cookie cookie = R977Musiccom.cookie else: logger.info("Detected a cookie: "+cookie) #logger.info("using always the same cookie: "+cookie) logger.info("simulating get referer (swf)... cookie: "+cookie) flashPlayer = R977Musiccom.getContentFromUrl(referer,"",cookie,R977Musiccom.MAIN_URL) logger.info("obtaining songs...") songs = R977Musiccom.getContentFromUrl("http://www.977music.com/ajax/rest/playlist.php/"+id+"/","",cookie,R977Musiccom.MAIN_URL,True) #print "songs: "+str(songs) logger.info("now is the vital petition, launching... ") html = R977Musiccom.getContentFromUrl(page,'',cookie,referer) x = R977Musiccom.parseListSongs(songs,html) #print "html: "+html if html.find('<div class="list_box">')>-1: #it's a list, needs decode table = Decoder.extract('<div class="list_box">','</ul>',html) x = R977Musiccom.extractElements(table,html) #print "done!" return x
def extractElementsPlayer(html): x = [] i = 0 for value in html.split('<div class="player"'): if i>0: element = {} title = Decoder.extract('data-title="','">',value) link = Decoder.extract('data-mp3url="','" ',value) element["title"] = title element["link"] = Redmp3cc.MAIN_URL+link if value.find('<img src="')!=-1: element["thumbnail"] = Redmp3cc.MAIN_URL+Decoder.extract('<img src="','" ',value) logger.info("append: "+title+", link: "+element["link"]) x.append(element) i+=1 if len(x)>0 and html.find(' class="button">Next page')!=-1: nextLink = "search.html/"+Decoder.rExtract('/mp3-','" class="button">Next page',html) nextText = "Next page" element = {} element["link"] = nextLink element["title"] = nextText logger.info("append next search with link: "+nextLink) x.append(element) return x
def search(text): start = 'window["ytInitialData"] = ' end = ";" page = Youtube.SEARCH_URL % urllib.parse.quote_plus(text) logger.debug("search url is: %s" % page) html = Youtube.getContentFromUrl(page) logger.debug("now extracting json search results...") jsonString = Decoder.extract(start,end,html) logger.debug("done, loading json...") jsonList = json.loads(jsonString) with open('/tmp/data.json', 'w') as outfile: json.dump(jsonList, outfile) logger.debug("parsed and saved!") listed = Youtube.extractVideosSearchFromJSON(jsonList) logger.debug("json to lists done") return listed
def getChannels(page,cookie='',referer=''): x = [] html = "" if str(page) == '0': x = Redmp3cc.getMainSections() elif str(page) == 'songs.html': page=Redmp3cc.MAIN_URL+"/" html = Downloader.getContentFromUrl(page,"",cookie,"") x = Redmp3cc.extractElementsPlayer(html) elif str(page).find('search.html')!=-1: if str(page).find('search.html/')==-1: keyboard = xbmc.Keyboard("") keyboard.doModal() text = "" if (keyboard.isConfirmed()): text = keyboard.getText() x = Redmp3cc.search(text) else: text = Decoder.rExtract('search.html/','/',page) page = int(page[page.rfind('/')+1:]) x = Redmp3cc.search(text,page) elif str(page).find(".html")!=-1: if str(page) == 'albums.html'!=-1: page = Redmp3cc.MAIN_URL html = Downloader.getContentFromUrl(page,"",cookie,"") x = Redmp3cc.extractElementsAlbum(html) else: html = Downloader.getContentFromUrl(page,"",cookie,"") x = Redmp3cc.extractElementsPlayer(html) else: logger.info("page is: "+page) response = Redmp3cc.getContentFromUrl(page,"",cookie,Redmp3cc.MAIN_URL,True) #logger.info("will be used a mp3 url: "+Decoder.extract('<a href="','">here',response)) host = response[response.find("://")+len("://"):] if host.find("/")>-1: host = host[0:host.find("/")] cookie = Redmp3cc.cookie referer = page logger.info("cookie is: "+cookie+", referer is: "+referer) headers = downloadtools.buildMusicDownloadHeaders(host,cookie,referer) filename= Decoder.extract('filename=','&',response) #ROOT_DIR = xbmcaddon.Addon(id='org.harddevelop.kodi.juke').getAddonInfo('path') ROOT_DIR = xbmc.translatePath('special://temp/') logger.info("using special root folder: "+ROOT_DIR) downloadtools.downloadfile(response,ROOT_DIR+"/"+filename,headers,False,True) x.append(Redmp3cc.buildDownloadedFile(xbmc.makeLegalFilename(ROOT_DIR+"/"+filename))) return x
def getCatalogMenu(params=[]): page = 1 if type(params) is list: logger.debug("page") for element in params: logger.debug("page %s" % str(element)) if "page" in element: page = element["page"] #/bbs/cposts/sc/ http = urllib3.PoolManager() url = "https://www.lexaloffle.com/bbs/lister.php?use_hurl=1&cat=7&sub=2&page=%s&mode=carts&orderby=featured" % page logger.debug("lexaoffle url is: %s" % url) r = http.request('GET', url, preload_content=False) html = r.data.decode() bruteCards = Decoder.extract('pdat=[', '];', html) cards = [] if page > 1: element = {} element["title"] = "next p. %s" % (int(page) - 1) element["action"] = "function" element["external"] = 'getCatalogMenu' element["params"] = [{'page': int(page) - 1}] cards.append(element) for bruteCardLine in bruteCards.split(",``],"): logger.debug("line is %s" % bruteCardLine) if '[' in bruteCardLine: element = {} bruteCardLine = bruteCardLine[:bruteCardLine.find('],')] name = Decoder.extract(', `', '`,', bruteCardLine) id = Decoder.extract("['", "'", bruteCardLine) link = 'https://www.lexaloffle.com/bbs/get_cart.php?cat=7&play_src=0&lid=%s' % id out = re.sub('[^A-Za-z0-9.\-,\ ]+', '', name) + ".p8.png" out = ROMS_PATH + "/pico8/" + out command = 'curl "%s" --create-dirs --output "%s" \n' % (link, out) element["external"] = command element["action"] = 'command-exit' element["title"] = name cards.append(element) #next page if len(cards) > 0: element = {} element["title"] = "next p. %s" % (int(page) + 1) element["action"] = "function" element["external"] = 'getCatalogMenu' element["params"] = [{'page': int(page) + 1}] cards.append(element) element = {} element["title"] = "Search" element["action"] = 'function-text' element["external"] = 'getCatalogSearchMenu' element["params"] = [{'webpage': link, 'final': False}] #TODO append getCatalogSearchMenu search cards.append(element) #back element = {} element["title"] = "Back" if int(page) != 1: element["action"] = 'function' element["external"] = 'getCatalogMenu' else: element["action"] = 'menu' element["external"] = 'webpages' cards.append(element) return cards