Python Decoder.extract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 extract [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 extract [as 别名]
 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

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

# 需要导入模块: from core.decoder import Decoder [as 别名]
# 或者: from core.decoder.Decoder import extract [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 extract [as 别名]
 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("&nbsp;","")
                 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

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

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

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

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

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

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

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

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