Merge pull request #1952 from diamondpete/heavyonhotties

NewSite/Add Support for Heavy on Hotties

Contents/Code/PAactors.py

@@ -79,6 +79,7 @@ def processActors(self, metadata, siteNum):
 
                             if searchStudioIndex == 32 and actorName != 'QueenSnake':
                                 actorName = '%s QueenSnake' % actorName
+                            searchActorName = actorName.lower()
 
                             break
 

Contents/Code/PAdatabaseActors.py

@@ -186,6 +186,7 @@
     'Lea Lexis': ['Lea Lexus', 'Lea Lush', 'Leah Lush', 'Lee Lexus', 'Lea Lixus'],
     'Leana Lovings': ['Leanna Lovings'],
     'Lexi Anne Garza': ['Lexi Aaane', 'Lexi Anne'],
+    'Leyla Peachbloom': ['Layla Peachbloom', 'Leila Peachbloom', 'Leyla Bloom'],
     'Lia Lor': ['Brady Paige'],
     'Light Fairy': ['Flora Fairy', 'Lightfairy'],
     'Lilly Ford': ['Lilly Lit'],
@@ -6088,6 +6089,22 @@
         'Talon': ['Talon Valenti'],
         'Zeus': ['Jesus "Zeus"Munoz'],
     },
+    70: {  # Heavy on Hotties
+        'Alice Wonderbang': ['Sasha'],
+        'Ashley Stillar': ['Nicol'],
+        'Cindy White': ['Cindy'],
+        'Jana Maho': ['Angelia'],
+        'Josephine Jackson': ['Josephine'],
+        'Lilu Moon': ['Lilu4u'],
+        'Leony Dark': ['Leony'],
+        'Maggie Gold': ['Maggies'],
+        'Melissa Mandlikova': ['Pamela'],
+        'Natasha Sweet': ['Nadiya'],
+        'Olga Winter': ['Olga'],
+        'Suzie Sun': ['Suzy'],
+        'Teena Lipoldino': ['Teena'],
+        'Victoria Ferrera': ['Roksolana'],
+    },
 }
 
 ActorsStudioIndexes = {
@@ -6161,6 +6178,7 @@
     67: ['Data18'],
     68: ['Mofos'],
     69: ['Adult Empire'],
+    70: ['Heavy on Hotties'],
 }
 
 

Contents/Code/PAsiteList.py

@@ -189,6 +189,7 @@
 import sitePornbox
 import siteJesseLoadsMonsterFacials
 import networkGASM
+import siteHeavyOnHotties
 
 searchSites = {
     0: ('BlackedRaw', 'https://www.blackedraw.com', '/graphql'),
@@ -1977,6 +1978,7 @@
     1883: ('Voodooed', 'https://voodooed.com', '/?s='),
     1884: ('Vored', 'https://vored.com', '/?s='),
     1885: ('Latina MILF', 'https://letsdoeit.com', 'https://site-api.project1service.com'),
+    1886: ('Heavy on Hotties', 'https://www.heavyonhotties.com', '/'),
 }
 
 abbreviations = (
@@ -3314,4 +3316,8 @@ def getProviderFromSiteNum(siteNum):
         elif 1866 <= siteNum <= 1882:
             provider = networkGASM
 
+        # Heavy on Hotties
+        elif siteNum == 1886:
+            provider = siteHeavyOnHotties
+
     return provider

Contents/Code/PAutils.py

@@ -395,7 +395,7 @@ def postParseTitle(output):
     # Remove single period at end of title
     output = re.sub(r'(?<=[^\.].)(?<=\w)(?:\.)$', '', output)
     # Remove space between word and certain punctuation
-    output = re.sub(r'\s+(?=[.,!:\'\)])', '', output)
+    output = re.sub(r'\s+(?=[.,!\'\)]|(:(?!\))))', '', output)
     # Add space between word and opening quote
     output = re.sub(r'(?<=\S)([\"]\S+)', lambda m: ' ' + m.group(1), output)
     # Remove space between punctuation and word
@@ -467,12 +467,12 @@ def manualWordFix(word):
     exceptions = (
         'im', 'theyll', 'cant', 'ive', 'shes', 'theyre', 'tshirt', 'dont', 'wasnt', 'youre', 'ill', 'whats', 'didnt',
         'isnt', 'senor', 'senorita', 'thats', 'gstring', 'milfs', 'oreilly', 'bangbros', 'bday', 'dms', 'bffs',
-        'ohmy', 'wont', 'whos', 'shouldnt', 'lasirena'
+        'ohmy', 'wont', 'whos', 'shouldnt', 'lasirena', 'espanol'
     )
     corrections = (
         'I\'m', 'They\'ll', 'Can\'t', 'I\'ve', 'She\'s', 'They\'re', 'T-Shirt', 'Don\'t', 'Wasn\'t', 'You\'re', 'I\'ll', 'What\'s', 'Didn\'t',
         'Isn\'t', 'Señor', 'Señorita', 'That\'s', 'G-String', 'MILFs', 'O\'Reilly', 'BangBros', 'B-Day', 'DMs', 'BFFs',
-        'OhMy', 'Won\'t', 'Who\'s', 'Shouldn\'t', 'LaSirena'
+        'OhMy', 'Won\'t', 'Who\'s', 'Shouldn\'t', 'LaSirena', 'español'
     )
     pattern = re.compile(r'\d|\W')
     cleanWord = re.sub(pattern, '', word)

Contents/Code/siteHeavyOnHotties.py

@@ -0,0 +1,134 @@
+import PAsearchSites
+import PAutils
+
+
+def search(results, lang, siteNum, searchData):
+    directURL = '%s/movies/%s' % (PAsearchSites.getSearchBaseURL(siteNum), slugify(searchData.title))
+    searchResults = [directURL]
+    directURL = '%s/movies/%s' % (PAsearchSites.getSearchBaseURL(siteNum), '-'.join(searchData.title.lower().split(' ')[1:]))
+    searchResults.append(directURL)
+
+    titleNoActors = ' '.join(searchData.title.split(' ')[2:])
+    if titleNoActors.startswith('and '):
+        titleNoActors = ' '.join(titleNoActors.split(' ')[3:])
+    directURL = '%s/movies/%s' % (PAsearchSites.getSearchBaseURL(siteNum), slugify(titleNoActors.replace('\'', '')))
+    searchResults.append(directURL)
+
+    googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
+    for sceneURL in googleResults:
+        if '/movies/' in sceneURL and '/page-' not in sceneURL and sceneURL not in searchResults:
+            searchResults.append(sceneURL)
+
+    for sceneURL in searchResults:
+        try:
+            req = PAutils.HTTPRequest(sceneURL)
+            scenePageElements = HTML.ElementFromString(req.text)
+            titleNoFormatting = scenePageElements.xpath('//h1')[0].text_content().split(':', 1)[-1].strip().strip('\"')
+            curID = PAutils.Encode(sceneURL)
+
+            date = scenePageElements.xpath('//span[@class="released title"]/strong')
+            if date:
+                releaseDate = parse(date[0].text_content().strip()).strftime('%Y-%m-%d')
+            else:
+                releaseDate = searchData.dateFormat() if searchData.date else ''
+
+            displayDate = releaseDate if date else ''
+
+            if searchData.date and displayDate:
+                score = 100 - Util.LevenshteinDistance(searchData.date, releaseDate)
+            else:
+                score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
+
+            results.Append(MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate), name='%s [%s] %s' % (PAutils.parseTitle(titleNoFormatting, siteNum), PAsearchSites.getSearchSiteName(siteNum), displayDate), score=score, lang=lang))
+        except:
+            pass
+
+    return results
+
+
+def update(metadata, lang, siteNum, movieGenres, movieActors, art):
+    metadata_id = str(metadata.id).split('|')
+    sceneURL = PAutils.Decode(metadata_id[0])
+    sceneDate = metadata_id[2]
+    if not sceneURL.startswith('http'):
+        sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
+    req = PAutils.HTTPRequest(sceneURL)
+    detailsPageElements = HTML.ElementFromString(req.text)
+
+    # Title
+    metadata.title = PAutils.parseTitle(detailsPageElements.xpath('//h1')[0].text_content().split(':', 1)[-1].split(' - ')[-1].strip().strip('\"'), siteNum)
+
+    # Summary
+    summary = detailsPageElements.xpath('//div[@class="video_text"]')
+    if summary:
+        metadata.summary = summary[0].text_content().strip()
+
+    # Studio
+    metadata.studio = "Heavy on Hotties"
+
+    # Tagline and Collection(s)
+    metadata.collections.add(metadata.studio)
+
+    # Release Date
+    date = detailsPageElements.xpath('//span[@class="released title"]/strong')
+    if date:
+        date_object = parse(date[0].text_content().strip())
+        metadata.originally_available_at = date_object
+        metadata.year = metadata.originally_available_at.year
+    elif sceneDate:
+        date_object = parse(sceneDate)
+        metadata.originally_available_at = date_object
+        metadata.year = metadata.originally_available_at.year
+
+    # Actor(s)
+    for actorLink in detailsPageElements.xpath('//span[@class="feature title"]//a[contains(@href, "models")]'):
+        actorName = actorLink.text_content().strip()
+        actorPhotoURL = ''
+
+        actorURL = actorLink.xpath('./@href')[0]
+        if not actorURL.startswith('http'):
+            actorURL = '%s%s' % (PAsearchSites.getSearchBaseURL(siteNum), actorURL)
+        req = PAutils.HTTPRequest(actorURL)
+        actorPageElements = HTML.ElementFromString(req.text)
+
+        try:
+            actorPhotoURL = actorPageElements.xpath('//div[./h1]/img/@src')[0]
+            if not actorPhotoURL.startswith('http'):
+                actorPhotoURL = 'https:%s' % actorPhotoURL
+        except:
+            pass
+
+        movieActors.addActor(actorName, actorPhotoURL)
+
+    # Posters/Background
+    xpaths = [
+        '//video/@poster',
+    ]
+
+    for xpath in xpaths:
+        for img in detailsPageElements.xpath(xpath):
+            if not img.startswith('http'):
+                img = 'https:' + img
+
+            art.append(img)
+
+    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

@@ -669,6 +669,7 @@ If you're having difficulty finding the SceneID, double-check [PAsiteList.py](..
   - TGirl Japan Hardcore
   - TGirls.porn
   - TGirls.xxx
++ #### Heavy on Hotties | ✅
 + #### Hegre | ✓ - **Title only**
 + #### HentaiPros | ✅
 + #### HighTechVR Network | ❌