Update Various Scrapers

Contents/Code/PAsiteList.py

@@ -1848,6 +1848,7 @@
     1754: ('MilfAF', 'https://www.milfaf.com', '/models/'),
     1755: ('Shady Spa', 'https://www.shadyspa.com', '/models/'),
     1756: ('Breed Me', 'https://www.breedme.com', '/models/'),
+    1757: ('MrLuckyRAW', 'https://www.mrluckyraw.com', '/search.php?query='),
 }
 
 abbreviations = (
@@ -2318,7 +2319,7 @@ def getProviderFromSiteNum(siteNum):
             provider = network1service
 
         # Spizoo
-        elif siteNum == 293 or (571 <= siteNum <= 577) or (1374 <= siteNum <= 1375):
+        elif siteNum == 293 or (571 <= siteNum <= 577) or (1374 <= siteNum <= 1375) or siteNum == 1757:
             provider = siteSpizoo
 
         # Private

Contents/Code/PAutils.py

@@ -387,7 +387,8 @@ def parseTitleSymbol(word, siteNum, symbol):
 
 
 def postParseTitle(output):
-    replace = [('“', '\"'), ('”', '\"'), ('’', '\''), ('W/', 'w/'), ('Aj', 'AJ')]
+    replace = [(r'“', '\"'), (r'”', '\"'), (r'’', '\''), (r'W/', 'w/'), (r'A\.\sJ\.', 'A.J.'), (r'T\.\sJ\.', 'T.J.'), (r'(?<!\S)AJ(?!\S)', 'A.J.')]
+    lower_exceptions = ['a', 'y', 'n', 'an', 'of', 'the', 'and', 'for', 'to', 'onto', 'but', 'or', 'nor', 'at', 'with', 'vs', 'com', 'co', 'org']
 
     # Add space after a punctuation if missing
     output = re.sub(r'(?=[\!|\:|\?|\.](?=(\w{2,}))\b)\S(?!(co\b|net\b|com\b|org\b|porn\b|E\d|xxx\b))', lambda m: m.group(0) + ' ', output, flags=re.IGNORECASE)
@@ -398,9 +399,9 @@ def postParseTitle(output):
     # Remove space between punctuation and word
     output = re.sub(r'(?<=[#\(])\s+', '', output)
     # Override lowercase if word follows a punctuation
-    output = re.sub(ur'(?<=!|:|\?|\.|-|\u2013)(\s)(\S)', lambda m: m.group(1) + m.group(2).upper(), output)
+    output = re.sub(ur'(?<!vs\.)(?<=!|:|\?|\.|-|\u2013)(\s)(\S)', lambda m: m.group(1) + m.group(2).upper(), output)
     # Override lowercase if word follows a parenthesis
-    output = re.sub(r'(?<=[\(|\&|\"|\[|\*|\~])(\w)', lambda m: m.group(0).upper() + m.group(1)[1:], output)
+    output = re.sub(r'(?<=[\(|\&|\"|\[|\*|\~])(\w)', lambda m: m.group(0).upper() + m.group(1)[1:] if m.group(1).lower() not in lower_exceptions else m.group(1), output)
     # Override lowercase if last word in section
     output = re.sub(r'\S+[\]\)\"\~\:]', lambda m: m.group(0)[0].capitalize() + m.group(0)[1:], output)
     # Override lowercase if last word
@@ -440,14 +441,14 @@ 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'
+        'ohmy', 'wont', 'whos', 'shouldnt', 'lasirena'
     )
     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'
+        'OhMy', 'Won\'t', 'Who\'s', 'Shouldn\'t', 'LaSirena'
     )
-    pattern = re.compile(r'\W')
+    pattern = re.compile(r'\d|\W')
     cleanWord = re.sub(pattern, '', word)
 
     if cleanWord.lower() in exceptions:

Contents/Code/networkLoveHerFilms.py

@@ -15,7 +15,7 @@ def search(results, lang, siteNum, searchData):
         else:
             score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
 
-        results.Append(MetadataSearchResult(id='%s|%d' % (curID, siteNum), name='%s [Love Her Feet] %s' % (titleNoFormatting, releaseDate), score=score, lang=lang))
+        results.Append(MetadataSearchResult(id='%s|%d' % (curID, siteNum), name='%s [%s] %s' % (titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum), releaseDate), score=score, lang=lang))
 
     return results
 

Contents/Code/networkTeamSkeet.py

@@ -115,7 +115,7 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
 
             genres.append(genreName)
 
-    genres.extend(PAutils.getDictValuesFromKey(genresDB, subSite))
+    genres.extend(PAutils.getDictValuesFromKey(genresDB, tagline))
 
     for genreLink in genres:
         genreName = genreLink

Contents/Code/siteATKGirlfriends.py

@@ -491,6 +491,7 @@ def getSceneInfo(searchTitle):
         'Rebecca Vanguard': 'sai003',
         'Reese Robbins': 'ree012',
         'Reina Heart': 'rei001',
+        'Renee Rose': 'ren057',
         'Renee Roulette': 'ren055',
         'Rhaya Shyne': 'rha001',
         'Rikki Rumor': 'rik006',

Contents/Code/siteMomComesFirst.py

@@ -95,5 +95,5 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
     'cory chase', 'abby somers', 'bailey base', 'kiki klout', 'victoria june', 'kendra heart', 'archie stone', 'jaime vine',
     'casca akashova', 'katie monroe', 'eve rebel', 'dakota burns', 'nikita reznikova', 'taylor blake', 'tricia oaks', 'artemisia love',
     'kyla keys', 'brianna rose', 'jordan max', 'jadan snow', 'kaylynn keys', 'lucy sunflower', 'jackie hoff', 'kenzie foxx',
-    'mirabella amore', 'heather vahn', 'natasha nice'
+    'mirabella amore', 'heather vahn', 'natasha nice', 'kat marie', 'miss brat', 'macy meadows', 'sydney paige', 'vanessa cage',
 }

Contents/Code/siteNewSensations.py

@@ -23,7 +23,8 @@ def search(results, lang, siteNum, searchData):
             try:
                 searchResult = HTML.ElementFromString(req.text)
 
-                titleNoFormatting = searchResult.xpath('(//div[@class="indScene"]/h1 | //div[@class="indSceneDVD"]/h1) | (//div[@class="indScene"]/h2 | //div[@class="indSceneDVD"]/h2)')[0].text_content().strip()
+                title = searchResult.xpath('(//div[@class="indScene"]/h1 | //div[@class="indSceneDVD"]/h1) | (//div[@class="indScene"]/h2 | //div[@class="indSceneDVD"]/h2)')[0].text_content().strip()
+                titleNoFormatting = PAutils.parseTitle(title, siteNum)
                 curID = PAutils.Encode(sceneURL)
 
                 score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
@@ -55,7 +56,8 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
 
     if sceneType == 'Scene':
         # Title
-        metadata.title = detailsPageElements.xpath('//div[@class="indScene"]/h1 | //div[@class="indScene"]/h2')[0].text_content().strip()
+        title = detailsPageElements.xpath('//div[@class="indScene"]/h1 | //div[@class="indScene"]/h2')[0].text_content().strip()
+        metadata.title = PAutils.parseTitle(title, siteNum)
 
         # Summary
         metadata.summary = detailsPageElements.xpath('//div[@class="description"]/h2/text() | //div[@class="description"]//span/following-sibling::text()')[0].replace('Description:', '').strip()
@@ -90,7 +92,7 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
     else:
         # Title
         title = detailsPageElements.xpath('//div[@class="indSceneDVD"]/h1')[0].text_content().strip()
-        metadata.title = title
+        metadata.title = PAutils.parseTitle(title, siteNum)
 
         # Summary
         metadata.summary = detailsPageElements.xpath('//div[@class="description"]/h2')[0].text_content().replace('Description:', '').strip()

Contents/Code/siteSpizoo.py

@@ -53,10 +53,8 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
     try:
         tagline = detailsPageElements.xpath('//i[@id="site"]/@value')[0].strip()
     except:
-        if 'rawattack' in sceneURL:
-            tagline = 'Raw Attack'
-        else:
-            tagline = 'Spizoo'
+        if 'Spizoo' not in PAsearchSites.getSearchSiteName(siteNum):
+            tagline = PAsearchSites.getSearchSiteName(siteNum)
     metadata.tagline = tagline
     metadata.collections.add(tagline)
 
@@ -104,7 +102,8 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
 
     # Posters
     xpaths = [
-        '//section[@id="photos-tour"]//img[contains(@class, "update_thumb thumbs")]/@src'
+        '//section[@id="photos-tour"]//img[contains(@class, "update_thumb thumbs")]/@src',
+        '//div[@class="content-block-video"]//img/@alt'
     ]
 
     for xpath in xpaths:
@@ -141,5 +140,5 @@ def update(metadata, lang, siteNum, movieGenres, movieActors, art):
 
 xPathDB = {
     ('293', '571', '572', '573', '574', '575', '576', '1374'): ['.//div[./h4[contains(., "date")]]/text()'],
-    '577': ['.//div[./h4[contains(., "date")]]/p/text()']
+    ('577', '1757'): ['.//div[./h4[contains(., "date")]]/p/text()']
 }

docs/sitelist.md

@@ -1297,6 +1297,7 @@ If you're having difficulty finding the SceneID, double-check [PAsiteList.py](..
   - IntimateLesbians
   - JessicaJaymesXXX
   - MrLuckyPOV
+  - MrLuckyRAW
   - PornGoesPro
   - PornstarTease
   - RawAttack