I’m not sure how to get this back into github, so I’m posting it here. This updates the AdultDVDEmpire plugin to handle split scenes; if a file has a scene name embedded in it (like “movie movie - Scene 1 - actress” or “1 - scene name”), the plugin uses the parent directory’s name as the movie title and attempts to parse the scene name to standardize it.
Known issues:
- Will probably be trouble if you have single files of scenes that aren’t in a directory with the name of the movie
- Couldn’t get each file’s title to reflect Movie : Scene # : Description; apparently setting the title for one file in a directory sets it for all of them
<br />
<br />
# AdultDVDEmpire<br />
import re<br />
<br />
# URLS<br />
ADE_BASEURL = 'http://www.adultdvdempire.com/'<br />
ADE_SEARCH_MOVIES = ADE_BASEURL + 'SearchTitlesPage.aspx?SearchString=%s'<br />
ADE_MOVIE_INFO = ADE_BASEURL + '%s/'<br />
<br />
def Start():<br />
HTTP.CacheTime = CACHE_1DAY<br />
HTTP.SetHeader('User-agent', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.2; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0)')<br />
<br />
class ADEAgent(Agent.Movies):<br />
name = 'Adult DVD Empire'<br />
languages = [Locale.Language.English]<br />
primary_provider = True<br />
<br />
def ParseScene(self,title,filename):<br />
Log("ParseScene: checking " + title)<br />
# Special case: if the filename has a number in brackets, that's the scene number, but Plex eats it<br />
# so we have to check the filename rather than title<br />
result = re.search(r"(\[\d{1,2}\])",filename)<br />
if result:<br />
sceneNumber = result.group(1)<br />
return "Scene " + sceneNumber<br />
<br />
# If it's an intro, credits, trailer, etc, use that name<br />
if re.search(r"(^intro$)",title,re.IGNORECASE):<br />
return "Intro"<br />
<br />
if re.search(r"(opening\scredits|open\scredits)",title,re.IGNORECASE):<br />
return "Opening credits"<br />
<br />
if re.search(r"(ending\scredits|end\scredits)",title,re.IGNORECASE):<br />
return "End credits"<br />
<br />
if re.search(r"^end$",title,re.IGNORECASE):<br />
return "End"<br />
<br />
if re.search(r"^credits$",title,re.IGNORECASE):<br />
return "Credits"<br />
<br />
result = re.match(r"(s?\d{1,2}\s|scene\s?\d{1,2}|sc?\s?\d{1,2}\s|\[\d{1,2}\])(.*)",title,re.IGNORECASE)<br />
if result:<br />
Log("Got scene match: " + result.group(1))<br />
scene = result.group(1)<br />
extra = result.group(2)<br />
# We have S01 or Scene1 or Sc1 or something, get the numbers<br />
result = re.search(r"(\d+)",scene)<br />
return "Scene " + scene.strip() + " : " + extra.strip()<br />
<br />
# If the title is in the form "Movie name - Scene XX", get scene name<br />
result = re.search(r"(.+)\s(scene\s?\d{1,2}|s\d{1,2}|sc\d{1,2})(?:\s|$|,)(.*)",title,re.IGNORECASE)<br />
if result:<br />
Log("Got embedded scene number" + result.group(2))<br />
scene = result.group(2)<br />
extra = result.group(3)<br />
result = re.search(r"(\d+)",scene)<br />
return "Scene " + scene.strip() + " : " + extra.strip()<br />
<br />
return False<br />
<br />
<br />
def search(self, results, media, lang):<br />
title = media.name<br />
Log("Processing " + title)<br />
if media.primary_metadata is not None:<br />
title = media.primary_metadata.title<br />
<br />
if title.startswith('The '):<br />
if title.count(':'):<br />
title = title.split(':',1)[0].replace('The ','',1) + ', The:' + title.split(':',1)[1]<br />
else:<br />
title = title.replace('The ','',1) + ', The'<br />
<br />
sceneName = self.ParseScene(title,media.items[0].parts[0].file.decode('utf-8'))<br />
if (sceneName):<br />
Log("Got scene name '" + sceneName + "', using parent dir name")<br />
file = media.items[0].parts[0].file.decode('utf-8')<br />
pathList = file.split("/")<br />
pathList.pop()<br />
parentPath = pathList.pop()<br />
Log("Parent path: " + parentPath)<br />
# We don't want to pass in the year if it's there<br />
title = re.sub(r'\(\d{4}\)','',parentPath)<br />
# Replace dots and underscores with spaces<br />
title = re.sub(r'[\s\.]',' ',title)<br />
Log("Got title " + title)<br />
<br />
# If our title includes metadata, remove it<br />
result = re.search(r"(.*?)(cheggit|bdrip|dvdrip|xxx\sdvdrip|720|split\s?scene|\(split|xvid)",title,re.IGNORECASE)<br />
if result:<br />
Log("Stripping scene info: " + result.group(2))<br />
title = result.group(1)<br />
Log("New title: " + title)<br />
<br />
# Special case: if our title has " 1" at the end, trim that<br />
result = re.search(r"(.*)\s1",title)<br />
if result:<br />
Log("Removing trailing '1'")<br />
title = result.group(1)<br />
Log("New title: " + title)<br />
<br />
query = String.URLEncode(String.StripDiacritics(title.replace('-','')))<br />
<br />
for movie in HTML.ElementFromURL(ADE_SEARCH_MOVIES % query).xpath('//div[contains(@class,"ListItem_ItemTitle")]/a'):<br />
curName = movie.text_content().strip()<br />
curID = movie.get('href').split('/',2)[1]<br />
score = 100 - Util.LevenshteinDistance(title.lower(), curName.lower())<br />
if score >= 85:<br />
if curName.count(', The'):<br />
curName = 'The ' + curName.replace(', The','',1)<br />
if curName.count(', A'):<br />
curName = 'A ' + curName.replace(', A','',1)<br />
if sceneName:<br />
# ISSUE: If you set one file's title to hold the scene name, all files in that dir are <br />
# affected (you end up with 5 files called "movie : scene 5") <br />
#curName = curName + " : " + sceneName<br />
Log("Setting full title to " + curName)<br />
<br />
results.Append(MetadataSearchResult(id = curID, name = curName, score = score, lang = lang))<br />
<br />
results.Sort('score', descending=True)<br />
<br />
def update(self, metadata, media, lang):<br />
html = HTML.ElementFromURL(ADE_MOVIE_INFO % metadata.id)<br />
Log("Current metadata title: " + metadata.title)<br />
Log("Current media title: " + media.title)<br />
metadata.title = media.title<br />
<br />
# Get Thumb and Poster<br />
try:<br />
img = html.xpath('//div[@id="ctl00_ContentPlaceHolder_ctl00_pnl_Default"]/a/img[contains(@src,"m.jpg")]')[0]<br />
thumbUrl = img.get('src')<br />
thumb = HTTP.Request(thumbUrl)<br />
posterUrl = img.get('src').replace('m.jpg','h.jpg')<br />
metadata.posters[posterUrl] = Proxy.Preview(thumb)<br />
except:<br />
pass<br />
<br />
# Get tagline<br />
try: metadata.tagline = html.xpath('//span[@class="Item_InfoTagLine"]')[0].text_content().strip()<br />
except: pass<br />
<br />
# Summary.<br />
try:<br />
metadata.summary = html.xpath('//div[@class="Item_InfoContainer"]')[0].text_content().replace(' ','').strip()<br />
if metadata.summary.find(metadata.tagline) != -1:<br />
metadata.summary = metadata.summary.replace(metadata.tagline, '').strip()<br />
except: pass<br />
<br />
# Other data.<br />
data = {}<br />
for div in html.xpath('//div[@class="Item_ProductInfoSectionConatiner"]/div'):<br />
name, value = div.text_content().split(':')<br />
data[name.strip()] = value.strip()<br />
<br />
if data.has_key('Rating'):<br />
metadata.content_rating = data['Rating']<br />
<br />
if data.has_key('Studio'):<br />
metadata.studio = data['Studio']<br />
<br />
if data.has_key('Release Date'):<br />
try:<br />
metadata.originally_available_at = Datetime.ParseDate(data['Release Date']).date()<br />
metadata.year = metadata.originally_available_at.year<br />
except: pass<br />
Using the script above it doesn’t even get the metadata for me.