Update sitePornbox.py

Contents/Code/PAsiteList.py

@@ -191,6 +191,7 @@
 import networkPKJMedia
 import networkBellesa
 import siteBrandNewAmateurs
+import sitePornbox
 
 searchSites = {
     0: ('BlackedRaw', 'https://www.blackedraw.com', '/graphql'),
@@ -1894,6 +1895,7 @@
     1798: ('Plants vs Cunts', 'https://plantsvscunts.com', '/?s='),
     1799: ('Brand New Amateurs', 'https://brandnewamateurs.com', '/models'),
     1800: ('Hot Wives Cheating', 'https://hotwivescheating.com/', '/MemberSceneSearch?q='),
+    1801: ('Pornbox', 'https://www.pornbox.com', '/autocomplete/'),
 }
 
 abbreviations = (
@@ -2087,6 +2089,7 @@
     ('^no ', 'NaughtyOffice '),
     ('^np ', 'NubilesPorn '),
     ('^nrg ', 'NaughtyRichGirls '),
+    ('^nrx ', 'Pornbox '),
     ('^nubc ', 'NubilesCasting '),
     ('^nubet ', 'NubilesET '),
     ('^nubilef ', 'NubileFilms '),
@@ -3240,4 +3243,8 @@ def getProviderFromSiteNum(siteNum):
         elif siteNum == 1799:
             provider = siteBrandNewAmateurs
 
+        # Pornbox
+        elif siteNum == 1801:
+            provider = sitePornbox
+
     return provider

Contents/Code/PAutils.py

@@ -436,6 +436,29 @@ def preParseTitle(input):
     return output
 
 
+def cleanSummary(summary):
+    replace = [(r'“', '\"'), (r'”', '\"'), (r'’', '\''), (r'W/', 'w/'), (r'A\.\sJ\.', 'A.J.'), (r'T\.\sJ\.', 'T.J.'), (r'(?<!\S)AJ(?!\S)', 'A.J.'), ('\xc2\xa0', ' ')]
+
+    # Initialize to first word only being capitalized
+    summary = summary.lower().capitalize()
+    # Replace common issues
+    for value in replace:
+        summary = re.sub(value[0], value[1], summary, flags=re.IGNORECASE)
+    # Add space after a punctuation if missing
+    summary = re.sub(r'(?=[\!|\:|\?|\.](?=(\w{1,}))\b)\S(?!(co\b|net\b|com\b|org\b|porn\b|E\d|xxx\b))', lambda m: m.group(0) + ' ', summary, flags=re.IGNORECASE)
+    # Remove space between word and punctuation
+    summary = re.sub(r'\s+(?=[.,!:\'\)])', '', summary)
+    # Remove space between punctuation and word
+    summary = re.sub(r'(?<=[#\(])\s+', '', summary)
+    # Override lowercase if word follows a punctuation
+    summary = re.sub(ur'(?<!vs\.)(?<=!|:|\?|\.)(\s)(\S)', lambda m: m.group(1) + m.group(2).upper(), summary)
+    # Add period to end of summary if no other punctuation present
+    if re.search(r'.$(?<=(!|\.|\?))', summary) is None:
+        summary = summary + '.'
+
+    return summary
+
+
 def manualWordFix(word):
     exceptions = (
         'im', 'theyll', 'cant', 'ive', 'shes', 'theyre', 'tshirt', 'dont', 'wasnt', 'youre', 'ill', 'whats', 'didnt',

Contents/Code/siteAnalVids.py

@@ -38,8 +38,6 @@ def search(results, lang, siteNum, searchData):
 
             if sceneID and int(sceneID) == searchResult['source_id']:
                 score = 100
-            elif searchData.date:
-                score = 100 - Util.LevenshteinDistance(searchData.date, releaseDate)
             else:
                 score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
 

Contents/Code/sitePornbox.py

@@ -0,0 +1,148 @@
+import PAsearchSites
+import PAutils
+
+
+def search(results, lang, siteNum, searchData):
+    sceneID = None
+    sourceID = None
+    parts = searchData.title.split()
+    if unicode(parts[0], 'UTF-8').isdigit():
+        sourceID = parts[0]
+        searchData.title = searchData.title.replace(sourceID, '', 1).strip()
+
+        sceneURL = '%s/contents/%s' % (PAsearchSites.getSearchBaseURL(siteNum), sourceID)
+        curID = PAutils.Encode(sceneURL)
+
+        req = PAutils.HTTPRequest(sceneURL)
+
+        if req.ok:
+            scenePageElements = req.json()
+            titleNoFormatting = PAutils.parseTitle(scenePageElements['scene_name'], siteNum)
+
+            date = scenePageElements['publish_date']
+            if date:
+                releaseDate = parse(date).strftime('%Y-%m-%d')
+            else:
+                releaseDate = searchData.dateFormat() if searchData.date else ''
+
+            displayDate = releaseDate if date else ''
+
+            score = 100
+
+            results.Append(MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate), name='%s [Pornbox] %s' % (titleNoFormatting, displayDate), score=score, lang=lang))
+
+    req = PAutils.HTTPRequest(PAsearchSites.getSearchSearchURL(siteNum) + searchData.title)
+    searchResults = req.json()
+
+    for searchResult in searchResults:
+        if searchResult['type'] == 'scene':
+            titleNoFormatting = PAutils.parseTitle(searchResult['name'], siteNum)
+            match = re.search(r'\w+\d$', titleNoFormatting)
+            if match:
+                sceneID = match.group(0)
+                titleNoFormatting = re.sub(r'\w+\d$', '', titleNoFormatting).strip()
+                titleNoFormatting = '[%s] %s' % (sceneID, titleNoFormatting)
+
+            sceneURL = '%s/contents/%s' % (PAsearchSites.getSearchBaseURL(siteNum), searchResult['source_id'])
+            curID = PAutils.Encode(sceneURL)
+
+            releaseDate = searchData.dateFormat() if searchData.date else ''
+
+            if sceneID and sceneID.lower() == searchData.title.lower():
+                score = 100
+            elif sourceID and int(sourceID) == searchResult['source_id']:
+                score = 100
+            else:
+                score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
+
+            results.Append(MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate), name='%s [Pornbox]' % (titleNoFormatting), score=score, lang=lang))
+
+    return results
+
+
+def update(metadata, lang, siteNum, movieGenres, movieActors, art):
+    metadata_id = metadata.id.split('|')
+    sceneURL = PAutils.Decode(metadata_id[0])
+    if not sceneURL.startswith('http'):
+        sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
+    req = PAutils.HTTPRequest(sceneURL)
+    detailsPageElements = req.json()
+
+    # Title
+    metadata.title = PAutils.parseTitle(detailsPageElements['scene_name'], siteNum)
+
+    # Summary
+    try:
+        metadata.summary = PAutils.cleanSummary(detailsPageElements['small_description'])
+    except:
+        pass
+
+    # Studio
+    metadata.studio = 'Pornbox'
+
+    # Tagline and Collection(s)
+    tagline = detailsPageElements['studio']
+    metadata.tagline = tagline
+    metadata.collections.add(tagline)
+
+    # Release Date
+    date = detailsPageElements['publish_date']
+    date_object = parse(date)
+    metadata.originally_available_at = date_object
+    metadata.year = metadata.originally_available_at.year
+
+    # Genres
+    for genreLink in detailsPageElements['niches']:
+        genreName = genreLink['niche']
+
+        movieGenres.addGenre(genreName)
+
+    # Actor(s)
+    actors = []
+    if 'models' in detailsPageElements:
+        actors.extend(detailsPageElements['models'])
+    if 'male_models' in detailsPageElements:
+        actors.extend(detailsPageElements['male_models'])
+    for actorLink in actors:
+        actorName = actorLink['model_name']
+        actorPhotoURL = ''
+
+        actorPageURL = '%s/model/info/%s' % (PAsearchSites.getSearchBaseURL(siteNum), actorLink['model_id'])
+        req = PAutils.HTTPRequest(actorPageURL)
+        actorPageElements = req.json()
+
+        if actorPageElements['headshot']:
+            actorPhotoURL = actorPageElements['headshot']
+
+        movieActors.addActor(actorName, actorPhotoURL)
+
+    # Posters/Background
+    art.append(detailsPageElements['player_poster'])
+
+    for x in range(1, len(detailsPageElements['screenshots'])):
+        # Only grab every 10th image for videos with over 50 images
+        if len(detailsPageElements['screenshots']) > 50 and x % 10 == 0:
+            art.append(detailsPageElements['screenshots'][x]['xga_size'])
+        elif len(detailsPageElements['screenshots']) <= 50:
+            art.append(detailsPageElements['screenshots'][x]['xga_size'])
+
+    Log('Artwork found: %d' % len(art))
+    for idx, posterUrl in enumerate(art, 1):
+        if not PAsearchSites.posterAlreadyExists(posterUrl, metadata):
+            # Download image file for analysis
+            try:
+                image = PAutils.HTTPRequest(posterUrl)
+                im = StringIO(image.content)
+                resized_image = Image.open(im)
+                width, height = resized_image.size
+                # Add the image proxy items to the collection
+                if width > 1:
+                    # Item is a poster
+                    metadata.posters[posterUrl] = Proxy.Media(image.content, sort_order=idx)
+                if width > 100:
+                    # Item is an art item
+                    metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
+            except:
+                pass
+
+    return metadata

docs/sitelist.md

@@ -63,6 +63,7 @@ If you're having difficulty finding the SceneID, double-check [PAsiteList.py](..
   - Forbidden Fruits Films
   - Horny Household
   - Hot Wife Fun
+  - Hot Wives Cheating
   - JaysPOV
   - Joanna Angel
   - Jodi West
@@ -1048,6 +1049,7 @@ If you're having difficulty finding the SceneID, double-check [PAsiteList.py](..
   - SlutsAroundTown
 + #### Playboy Plus | ✅
 + #### PlumperPass | ✅
++ #### Pornbox | ✅
 + #### PornCZ | ✓ - **Title or Actor**
   - Amateri Premium
   - Amateur From Bohemia