import org.apache.commons.lang.StringEscapeUtils
import org.serviio.library.metadata.*
import org.serviio.library.online.*
import org.serviio.util.*
/**
* Content URL extractor plugin for ZDF-Mediathek
*
* @author OAR
*
* Version : 3.0
*/
class ZDF extends WebResourceUrlExtractor {
final EXTRACTOR_NAME = 'ZDF-Mediathek'
final EXTRACTOR_VERSION = 3
final EXTRACTOR_TIMEOUT = 40
final USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36'
final URL_BASE = 'http://www.zdf.de'
final URL_METABASE = URL_BASE + '/ZDFmediathek/xmlservice/v2/web/beitragsDetails?ak=web&id='
final URL_ASSETBASE = URL_BASE + '/ptmd/vod/mediathek/'
final DATE_FORMAT = 'dd.MM.yyyy HH:mm'
final KEY_VIDEO = 'VIDEO'
final KEY_THUMB = 'THUMB'
final KEY_EXPIRE = 'EXPIRE'
final KEY_ASSET_HIGH = 'ASSET_H'
final KEY_ASSET_MED = 'ASSET_M'
final KEY_ASSET_LOW = 'ASSET_L'
final VALID_FEED_URL = '^http[s]?://www\\.zdf\\.de/.+'
final THEME_TITLE = '(?ms).*?([^<]*)'
final THEME_PAGING = '(?ms)\\s*.*? wriCache = new HashMap()
String[] assetHigh = [VIDEO_HIGH1, VIDEO_HIGH2]
String[] assetMed = [VIDEO_MED1, VIDEO_MED2]
String[] assetLow = [VIDEO_LOW1, VIDEO_LOW2]
@Override
String getExtractorName() {
return EXTRACTOR_NAME
}
@Override
int getVersion() {
return EXTRACTOR_VERSION
}
@Override
boolean extractorMatches(URL feedUrl) {
return feedUrl ==~ VALID_FEED_URL
}
@Override
int getExtractItemsTimeout() {
return EXTRACTOR_TIMEOUT
}
@Override
WebResourceContainer extractItems(URL resourceUrl, int maxItemsToRetrieve) {
// check wriCache for outdated entries
def now = System.currentTimeMillis()
def nowDate = new Date(now)
def List toDelete = []
wriCache.each {
def itemExpireDate = Date.parse(DATE_FORMAT, it.value.getAdditionalInfo().get(KEY_EXPIRE))
if (itemExpireDate < nowDate) toDelete.add(it.key)
}
toDelete.each {
wriCache.remove(it)
}
def expireDate = new Date(now + getOnlineFeedExpiryInterval()*3600000)
//def expireDate = new Date(now + 48*3600000) // debug
def expire = expireDate.format(DATE_FORMAT)
def webPage
def matcher
def title
def lastReq = ''
def entries = new HashMap()
def requestURL = resourceUrl
def tryRequest = true
while (tryRequest) {
try {
webPage = openURL(requestURL, USER_AGENT)
}
catch (ex) {
log(ex.toString())
return null
}
// theme title
if (title == null) {
matcher = webPage =~ THEME_TITLE
title = StringEscapeUtils.unescapeHtml(matcher[0][1].toString())
}
// items
matcher = webPage =~ THEME_ITEMS_ID
for (def i = 0; i < matcher.getCount() && entries.size() < maxItemsToRetrieve; i++) {
def id = matcher[i][1].toString()
if (wriCache.containsKey(id)) {
if (!entries.containsKey(id)) entries.put(id, wriCache.get(id))
} else {
def item = buildItem(id, expire)
if (item != null) {
wriCache.put(id, item)
entries.put(id, item)
}
}
}
//check for next page
tryRequest = false
if (entries.size() < maxItemsToRetrieve) {
matcher = webPage =~ THEME_PAGING
if(matcher.find()) {
def nextReq = StringEscapeUtils.unescapeHtml(matcher[0][1].toString())
if(lastReq != nextReq) {
lastReq = nextReq
requestURL = new URL(URL_BASE + nextReq)
tryRequest = true
}
}
}
}
// container
def container = new WebResourceContainer()
container.setTitle(title)
container.setThumbnailUrl(THEME_ICON)
container.setItems(new ArrayList(entries.values()))
return container
}
@Override
ContentURLContainer extractUrl(WebResourceItem item, PreferredQuality requestedQuality) {
def info = item.getAdditionalInfo()
def matchArr
def mapKey
def videoURL
switch (requestedQuality) {
case PreferredQuality.HIGH:
matchArr = assetHigh
mapKey = KEY_ASSET_HIGH
break
case PreferredQuality.MEDIUM:
matchArr = assetMed
mapKey = KEY_ASSET_MED
break
default:
matchArr = assetLow
mapKey = KEY_ASSET_LOW
break
}
if (info.containsKey(mapKey))
videoURL = info.get(mapKey)
else {
def link = info.get(KEY_VIDEO)
def asset
try {
asset = openURL(new URL(link), USER_AGENT)
}
catch (ex) {
log(ex.toString())
return null
}
videoURL = getVideoUrl(asset, matchArr)
if (videoURL == null) return null
info.put(mapKey, videoURL)
}
def container = new ContentURLContainer()
container.setContentUrl(videoURL)
container.setThumbnailUrl(info.get(KEY_THUMB))
container.setFileType(MediaFileType.VIDEO)
def expire = info.get(KEY_EXPIRE)
container.setExpiresOn(Date.parse(DATE_FORMAT, expire))
container.setCacheKey(item.getCacheKey() + mapKey)
container.setLive(false)
container.setUserAgent(USER_AGENT)
return container
}
private WebResourceItem buildItem(String id, String expire) {
def itemMeta
try {
itemMeta = openURL(new URL(URL_METABASE + id), USER_AGENT)
}
catch (ex) {
log(ex.toString())
return null
}
// metadata
def matcher = itemMeta =~ ITEM_TITLE
def title = matcher[0][1].toString()
matcher = itemMeta =~ ITEM_BASENAME
def base = matcher[0][1].toString()
matcher = itemMeta =~ ITEM_STREAMVERSION
def version = ''
if (matcher.find()) version = '/' + matcher[0][1].toString()
def assetURL = URL_ASSETBASE + base + version
matcher = itemMeta =~ ITEM_THUMB
def thumb = matcher[0][1].toString()
def map = new HashMap()
map.put(KEY_VIDEO, assetURL)
map.put(KEY_THUMB, thumb)
map.put(KEY_EXPIRE, expire)
def item = new WebResourceItem()
item.setTitle(title)
item.setAdditionalInfo(map)
matcher = itemMeta =~ ITEM_RELEASE
if (matcher.find()) {
def release = matcher[0][1].toString()
item.setReleaseDate(Date.parse(DATE_FORMAT, release))
}
item.setCacheKey(ITEM_CACHEPREFIX + id)
return item
}
private String getVideoUrl(String asset, String[] check) {
def matcher
def videoURL
for (def test in check) {
matcher = asset =~ test
if (matcher.find()) {
videoURL = matcher[0][1].toString()
break
}
}
return videoURL
}
static void main(args) {
// this is just to test
ZDF extractor = new ZDF();
URL videoLink = new URL("http://www.zdf.de/ZDFmediathek/suche?flash=off&sucheText=terra-x");
println "Name : " + extractor.getExtractorName();
println "Version : " + extractor.getVersion();
println "TestMatch : " + extractor.extractorMatches(videoLink);
WebResourceContainer container = extractor.extractItems(videoLink, 50);
for (def i = 0; i < container.getItems().size(); i++) {
extractor.extractUrl(container.getItems()[i], PreferredQuality.HIGH); println "**** HIGH ****"
}
extractor.extractUrl(container.getItems()[0], PreferredQuality.MEDIUM);println "**** MEDIUM ****"
extractor.extractUrl(container.getItems()[0], PreferredQuality.LOW);println "**** LOW ****"
// Test Cache
container = extractor.extractItems(videoLink, 10);
extractor.extractUrl(container.getItems()[0], PreferredQuality.HIGH);println "**** HIGH ****"
}
}