Python Decoder.extractWithRegex方法代码示例

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 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

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
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))

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractNewIframeChannel(html3,iframeUrl2):
     element = {}
     if html3.find("http://telefivegb.com/")>-1:
         logger.debug("found telefivegb.com link, using that link to...")
         newUrl = Decoder.extractWithRegex('http://telefivegb.com/','"',html3).replace('"',"")
     elif html3.find("http://verlatelegratis.net")>-1:
         logger.debug("found verlatelegratis.net link, using that link to...")
         newUrl = Decoder.extractWithRegex('http://verlatelegratis.net','"',html3).replace('"',"")
     html4 = Cineestrenostv.getContentFromUrl(newUrl,"",Cineestrenostv.cookie,iframeUrl2)
     if html4.find("http://www.playerhd1.pw/")>-1:
         logger.debug("found playerhd1.pw, using that link, continue...")
         element = Cineestrenostv.extractScriptPlayerHd1pw(html4,newUrl)
     else:
         logger.debug("possible redirect to his domains: "+html4+", try again..."+newUrl)
         element = Cineestrenostv.extractNewIframeChannel(html4,newUrl)
     return element

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 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 '&amp;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

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 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

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 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

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractChannel(html,page="http://www.vipgoal.net/"):
     element = {}
     if html.find('<script type="text/javascript" src="http://www.playerapp1.pw/channel.php?file=')>-1: #old part
         scriptUrl = Decoder.extractWithRegex('http://www.playerapp1.pw/channel.php?file=','"',html)
         html2 = Vigoal.getContentFromUrl(scriptUrl)
         lastUrl = Decoder.extractWithRegex('http://','" ',html2)
         lastUrl = lastUrl.replace('"',"")
         logger.debug("last url: "+lastUrl+", cookie="+Vigoal.cookie)
         html3 = Vigoal.getContentFromUrl(lastUrl,"",Vigoal.cookie,lastUrl)
         playerUrl = Decoder.decodeBussinessApp(html3,lastUrl)
         logger.debug("player url is: "+playerUrl)
         element["title"] = "Watch streaming"
         element["permalink"] = True
         element["link"] = playerUrl
     else: #unified with cinestrenostv, they are the same people, at least the same code works and the changes are at the same time xD
         logger.debug('Extracting channel from: '+page)
         element = Cineestrenostv.extractIframeChannel(html,page)
     return element

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractElements(table):
     x = []
     for value in table.split('\n'):
         if value.find("acestream://")>-1:
             element = {}
             element["title"] = unicode(Decoder.extract("// ",'(',value), errors='replace')
             element["link"] = Decoder.extractWithRegex("acestream:",'\"',value).replace('"',"")
             logger.debug("append: "+element["title"]+", link: "+element["link"])
             x.append(element)
     return x

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
    def extractSeasons(html,url):
        items = []
        #extract <a href='http://hdfull.tv/serie/homeland/temporada-1'>1</a>
        while html.find("<a href='"+url+"/temporada-")>-1:
            item = {}
            aHtml = Decoder.extractWithRegex("<a href='"+url+"/temporada-","</a>",html)
            html = html[html.find(aHtml)+len(aHtml):]
            item["permalink"] = Decoder.extractWithRegex(url+"/temporada-","'",aHtml)
            item["permalink"] = item["permalink"][0:item["permalink"].find("'")]
            item["title"] = Decoder.extract('>','</a>',aHtml)
            logger.debug("found title: "+item["title"]+", link: "+item["permalink"])
            if item["title"].find('<img class="tooltip" original-title="Temporada ')>-1:
                title = item["title"]
                item["title"] = Decoder.extract('original-title="','"',title)
                item["thumbnail"] = Decoder.extract('" src="','" />',title)
                logger.debug("procesed title: "+item["title"]+", thumbnail: "+item["permalink"])
                items.append(item)

        return items

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractTargetVideo(page):
     url = page.split('|')[0]
     referer = page[page.rfind("=")+1:]
     referer = 'http://ver.movistarplus.es/player/?canal='+referer+Yomvies.CHANNELS_SUBFIX
     logger.debug("yomvi url is: "+url+", with referer: "+referer)
     html = Yomvies.getContentFromUrl(url=url,referer=referer,launchLocation=True)
     logger.debug("obtained response for yomvi page: "+html)
     newUrl = url[:url.rfind("/")+1]+Decoder.extractWithRegex("#EXT-",".m3u8",html).split("\n")[1]
     html2 = Yomvies.getContentFromUrl(url=newUrl, referer=url, launchLocation=True)
     logger.debug("obtained second response for yomvi page: " + html2)
     return "http://127.0.0.1:46720?original-request=" + newUrl#+"&referer="+referer

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
    def extractScriptLevel3(scriptUrl,referer=''):
        html4 = Cineestrenostv.getContentFromUrl(scriptUrl, "", Cineestrenostv.cookie, referer)
        finalIframeUrl = Decoder.extractWithRegex('http://', '%3D"', html4)
        finalIframeUrl = finalIframeUrl[0:len(finalIframeUrl) - 1]

        logger.debug("proccessing level 4, cookie: " + Cineestrenostv.cookie)

        finalHtml = Cineestrenostv.getContentFromUrl(finalIframeUrl, "", Cineestrenostv.cookie, referer)
        # print "final level5 html: "+finalHtml
        logger.debug("proccessing level 5, cookie: " + Cineestrenostv.cookie)
        playerUrl = Decoder.decodeBussinessApp(finalHtml, finalIframeUrl)
        return playerUrl

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def launchScriptLogic(scriptRegex,html,referer,iframeUrl):
     logger.debug("processing pre level 2... url: "+scriptRegex)
     firstScriptUrl = Decoder.extractWithRegex(scriptRegex,".js",html)
     if firstScriptUrl.find('"')>-1:
         firstScriptUrl = firstScriptUrl[0:firstScriptUrl.find('"')]
     if "'" in firstScriptUrl:
         firstScriptUrl = firstScriptUrl[0:firstScriptUrl.find("'")]
     scriptUrl = Cricfreetv.extractScriptIframeUrl(html,firstScriptUrl,referer)
     logger.debug("level 2, scriptUrl: "+scriptUrl+", cookie: "+Cricfreetv.cookie)
     lastIframeHtml = Cricfreetv.getContentFromUrl(scriptUrl,"",Cricfreetv.cookie,iframeUrl)
     #print lastIframeHtml
     file = Cricfreetv.seekIframeScript(lastIframeHtml,iframeUrl,scriptUrl)
     logger.debug("script logic finished!")
     return file

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
    def extractScriptDefaultLogic(htmlContent,referer,regex):
        element = {}
        logger.debug("proccessing level 3, cookie: "+Cineestrenostv.cookie)
        logger.debug("using regex: "+regex)

        scriptUrl = Decoder.extractWithRegex(regex,'"',htmlContent).replace('"',"")
        scriptUrl = scriptUrl[0:len(scriptUrl)-1]

        playerUrl = Cineestrenostv.extractScriptLevel3(scriptUrl,referer)

        logger.debug("DONE! player url is: "+str(playerUrl))

        #print "player url is: "+playerUrl
        element["title"] = "Watch streaming"
        element["permalink"] = True
        element["link"] = playerUrl

        return element

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractListVideos(html):
     x = []
     tableHtml = Decoder.extract('<div class="playlist-videos-container yt-scrollbar-dark yt-scrollbar">','</div><div id="content" class="  content-alignment" role="main">',html)
     i=0
     for rowHtml in tableHtml.split('<span class="index">'):
         if i>0:
             element = {}
             link = "/watch?"+Decoder.extract('href="/watch?', '"', rowHtml)
             title = Decoder.extract('<h4 class="yt-ui-ellipsis yt-ui-ellipsis-2">','</h4>', 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.strip()
             element["page"] = link
             element["finalLink"] = True
             element["thumbnail"] = image
             x.append(element)
         i+=1
     return x

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extractWithRegex [as 别名]
 def extractIframeValue(iframe,html,referer):
     file = ""
     if iframe.find("http:")!=0:
         iframe = Decoder.extract("<iframe src='","' ",html).replace("'","") #take into account .lower() characters, so is not ' SRC=
         if iframe.find("http:")!=0:
             iframe = Decoder.extract(' src="','"',html).replace('"',"")
     logger.debug("using iframeUrl: "+iframe)
     if iframe.find("filmon.")>-1: # i prefer this fix to change all logic, really, I boried about this provider and is a 'silly' provider
         logger.debug("Detected exceptional filmon.com|tv provider: "+iframe)
         file = Filmoncom.launchScriptLogic(iframe,referer)[0]["url"]
     else:
         html2 = Cricfreetv.getContentFromUrl(iframe,"",Cricfreetv.cookie,referer)
         #print html2
         if html2.find("http://www3.sawlive.tv/embed/")>-1:
             iframe2 = Decoder.extractWithRegex("http://www3.sawlive.tv/embed/",'"',html2).replace('"',"")
             logger.debug("detected a sawlive: "+iframe2+", from: "+iframe)
             #file = Live9net.getChannels(iframe2) #Live9net has the sawlive decoder, so it decodes target link
             file = Decoder.extractSawlive(iframe2,Cricfreetv.cookie,iframe)
         else:
             file = Cricfreetv.seekIframeScript(html2,referer,iframe)
     return file