TEst Ora in Onda con Json

specials/filmontv.py

@@ -5,13 +5,18 @@
 import datetime
 import glob
 import time
-import xml.etree.ElementTree as ET
+# import xml.etree.ElementTree as ET
-from core import filetools, downloadtools
+from core import filetools, downloadtools, jsontools, scrapertools
 from core.item import Item
 from platformcode import logger, config
 import gzip
 
-host = "http://www.epgitalia.tv/xml/guide2.gzip"
+host = "http://www.epgitalia.tv/xml/guide.gzip"
+now = datetime.datetime.now()
+fileName = config.get_temp_file('guidatv-') + now.strftime('%Y %m %d')
+archiveName = fileName + '.gz'
+# xmlName = fileName + '.xml'
+jsonName = fileName + '.json'
 
 
 def mainlist(item):
@@ -20,17 +25,13 @@ def mainlist(item):
 
     itemlist.append(Item(title='Film in onda oggi', channel=item.channel, action='peliculas', contentType='movie'))
     itemlist.append(Item(title='Serie Tv in onda oggi', channel=item.channel, action='peliculas', contentType='tvshow'))
-    itemlist.append(Item(title='Guida tv per canale', channel=item.channel, action='listaCanali'))
+    # itemlist.append(Item(title='Guida tv per canale', channel=item.channel, action='listaCanali'))
     itemlist.append(Item(title='Canali live (Rai Play)', channel=item.channel, action='live'))
 
     return itemlist
 
 
 def getEpg():
-    now = datetime.datetime.now()
-    fileName = config.get_temp_file('guidatv-') + now.strftime('%Y %m %d')
-    archiveName = fileName + '.gz'
-    xmlName = fileName + '.xml'
     if not filetools.exists(archiveName):
         logger.info('downloading epg')
         # cancello quelli vecchi
@@ -38,71 +39,40 @@ def getEpg():
             filetools.remove(f, silent=True)
         # inmemory = io.BytesIO(httptools.downloadpage(host).data)
         downloadtools.downloadfile(host, archiveName)
-        logger.info('opening gzip and writing xml')
+    if filetools.exists(archiveName) and not filetools.exists(jsonName):
+        logger.info('opening gzip and writing Json')
         fStream = gzip.GzipFile(archiveName, mode='rb')
         guide = fStream.read()
-        with open(xmlName, 'w') as f:
+        write_json(guide)
-            f.write(guide)
 
-    guide = open(xmlName).read()
+    with open(jsonName) as f:
-    return ET.fromstring(guide)
+        json = jsontools.load(f.read())
+    return json
 
 
 def peliculas(item):
     itemlist = []
-    xml = getEpg()
+    start = time.time()
-
+    json_file = getEpg()
-    for prog in xml.findall('programme[credits]'):  # se hanno il cast probabilmente si tratta di un contenuto cinematografico
+    logger.info('PARSE TIME: ' + str(time.time() - start))
-        title = prog.find('title')
+    start = time.time()
-        if title is not None:
+    if item.contentType == 'movie':
-            title = title.text.replace(' - 1^TV', '')
+        json = json_file['movies']
-            # non mostro 2 volte lo stesso film
+    else:
-            for it in itemlist:
+        json = json_file['tvshows']
-                if it.contentTitle == title:
+    for title, value in json.items():
-                    break
+         if 'infoLabels' in value:
-            else:
+            infoLabels = value['infoLabels']
-                episode = prog.find('episode-num')
+            itemlist.append(Item(
-                if episode is not None:
+                    channel=item.channel,
-                    episode = ' (' + episode.text + ')'
+                    search_text=title,
-                else:
+                    title=title + (' - ' + value['episode'] if 'episode' in value else ''),
-                    episode = ''
+                    plot=value['plot'],
-                if (episode and item.contentType == 'tvshow') or (not episode and item.contentType == 'movie'):
+                    thumbnail=value['thumbnail'],
-                    desc = prog.find('desc')
+                    contentType=item.contentType,
-                    if desc is not None:
+                    infoLabels=infoLabels
-                        desc = desc.text
+                ))
-                    actors = prog.find('credits')
+    logger.info('BUILD ITEMLIST: ' + str(time.time() - start))
-                    if actors is not None:
-                        actors = [(actor.text, actor.attrib['role'] if 'role' in actor.attrib else '') for actor in actors]
-                    date = prog.find('date')
-                    if date is not None:
-                        date = date.text
-                    genres = prog.find('category')
-                    if genres is not None:
-                        genres = ','.join([cat.text for cat in genres])
-                    thumbnail = prog.find('icon')
-                    if thumbnail is not None:
-                        thumbnail = thumbnail.attrib['src']
-                    country = prog.find('country')
-                    if country is not None:
-                        country = country.text
-
-                    itemlist.append(Item(
-                        channel=item.channel,
-                        action='new_search',
-                        title=title,
-                        search_text=title,
-                        mode=item.contentType,
-                        year=date if date else '-',
-                        thumbnail=thumbnail if thumbnail else '',
-                        contentType=item.contentType,
-                        infoLabels={
-                            'title': title,
-                            'plot': desc if desc else '',
-                            'casta': actors if actors else '',
-                            'genre': genres if genres else '',
-                            'country': country if country else ''
-                        }
-                    ))
     # tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
     return itemlist
 
@@ -184,7 +154,7 @@ def guidatv(item):
                 infoLabels={
                     'title': title,
                     'plot': desc if desc else '',
-                    'casta': actors if actors else '',
+                    'castandrole': tuple(actors) if actors else '',
                     'genre': genres if genres else '',
                     'country': country if country else ''
                 }
@@ -201,3 +171,71 @@ def new_search(item):
 def live(item):
     from channels import raiplay
     return raiplay.dirette(raiplay.mainlist(Item())[0])
+
+def write_json(f):
+
+    titles = []
+    channel_dict = {}
+    channel_dict['movies'] = {}
+    channel_dict['tvshows'] = {}
+
+    channel = ''
+    title = ''
+    episode = ''
+    plot = ''
+    thumbnail = ''
+    actors = []
+    director = ''
+    year = ''
+    genres = []
+    country = ''
+    start = ''
+    stop = ''
+
+
+    for line in f.splitlines():
+        if '<programme' in line: start, stop, channel = scrapertools.find_single_match(line, r'start="(\d+)[^"]*" stop="(\d+)[^"]*" channel="([^"]+)"')
+        elif '<title' in line: title = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<desc' in line: plot = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<actor' in line:
+            match = scrapertools.find_single_match(line, r'(?:role="([^"]*)")?>([^<]+)<')
+            actors.append([match[1], match[0]])
+        elif '<director' in line: director = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<date' in line: year = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<category' in line: genres.append(scrapertools.find_single_match(line, r'>([^<]+)<'))
+        elif '<country' in line: country = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<episode-num' in line: episode = scrapertools.find_single_match(line, r'>([^<]+)<')
+        elif '<icon' in line: thumbnail = scrapertools.find_single_match(line, r'src="([^"]+)"')
+        elif '</programme' in line and title and title not in titles and actors:
+            titles.append(title)
+            if episode:
+                t = channel_dict['tvshows']
+            else:
+                t = channel_dict['movies']
+            t[title] = {}
+            t[title]['infoLabels'] = {'castandrole':actors, 'director':director, 'genres':genres, 'country':country, 'year':year}
+            t['start'] = start
+            t['stop'] = stop
+            t['episode'] = episode
+            t[title]['title'] = title
+            t[title]['channel_name'] = channel
+            t[title]['thumbnail'] = thumbnail
+            t[title]['plot'] = plot
+
+            channel = ''
+            title = ''
+            episode = ''
+            plot = ''
+            thumbnail = ''
+            actors = []
+            director = ''
+            year = ''
+            genres = []
+            country = ''
+            start = ''
+            stop = ''
+
+    # f = json.dumps(channel_dict)
+    with open(jsonName, 'w') as json_file:
+        json_file.write(jsontools.dump(channel_dict, sort_keys=False))
+        json_file.close()