def update(metadata, lang, siteNum, movieGenres, movieActors, art):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
basePageElements = getJSONfromPage(sceneURL)
detailsPageElements = basePageElements['video']
# Title
metadata.title = detailsPageElements['title']
# Summary
metadata.summary = PAutils.cleanHTML(detailsPageElements['description'])
# Studio
metadata.studio = 'Top Web Models'
# Tagline and Collection(s)
metadata.collections.clear()
if 'sites' in detailsPageElements:
tagline = re.sub(
r"(\w)([A-Z])", r"\1 \2",
json.loads(json.dumps(detailsPageElements['sites'][0]))['name'])
else:
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Date
date = detailsPageElements['release_date']
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements['tags']:
genreName = genreLink['name']
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements['models']:
actorName = actorLink['name']
actorPhotoURL = actorLink['thumb']
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art.append(detailsPageElements['thumb'])
art.append(basePageElements['file_poster'])
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteID) + sceneURL
tagline = metadata_id[2]
scenePoster = PAutils.Decode(metadata_id[3])
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h2[@class="scene-h2-heading"]')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//p[@class="indie-model-p"]')[0].text_content().strip()
# Studio
metadata.studio = 'Vivid Entertainment'
# Tagline and Collection(s)
metadata.collections.clear()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//h5[contains(text(), "Released:")]')[0].text_content().replace(
'Released:', '').strip()
if date:
date_object = datetime.strptime(date, '%b %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//h5[contains(text(),"Categories:")]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//h4[contains(text(),"Starring:")]/a'):
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = [scenePoster]
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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath('//h1')[0].text_content().strip()
# Summary
try:
metadata.summary = detailsPageElements.xpath('///span[@class="full"]')[0].text_content().strip()
except:
pass
# Studio
metadata.studio = 'Marc Dorcel'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
movieGenres.addGenre('French p**n')
movieName = detailsPageElements.xpath('//span[@class="movie"]/a')
if movieName:
metadata.collections.add(movieName[0].text_content().strip())
movieGenres.addGenre('Blockbuster Movie')
# Actors
movieActors.clearActors()
if 'p**n-movie' not in sceneURL:
actors = detailsPageElements.xpath('//div[@class="actress"]/a')
else:
actors = detailsPageElements.xpath('//div[@class="actor thumbnail "]/a/div[@class="name"]')
if actors:
if 'p**n-movie' not in sceneURL:
if len(actors) == 3:
movieGenres.addGenre('Threesome')
if len(actors) == 4:
movieGenres.addGenre('Foursome')
if len(actors) > 4:
movieGenres.addGenre('Orgy')
for actorLink in actors:
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Release Date
if 'p**n-movie' not in sceneURL:
date = detailsPageElements.xpath('//span[@class="publish_date"]')[0].text_content().strip()
else:
date = detailsPageElements.xpath('//span[@class="out_date"]')[0].text_content().replace('Year :', '').strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Director
director = metadata.directors.new()
try:
movieDirector = detailsPageElements.xpath('//span[@class="director"]')[0].text_content().replace(
'Director :', '').strip()
director.name = movieDirector
except:
pass
# Poster
art = []
xpaths = [
'//div[contains(@class, "photos")]//source/@data-srcset'
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
if ',' in img:
img = img.split(',')[-1].split()[0]
trash = '_' + img.split('_', 3)[-1].rsplit('.', 1)[0]
img = img.replace(trash, '', 1)
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
def update(metadata, siteID, movieGenres, movieActors):
path = PAutils.Decode(str(metadata.id).split("|")[0])
url = PAsearchSites.getSearchBaseURL(siteID) + path
detailsPageElements = HTML.ElementFromURL(url)
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="video-rating-and-details"]//h1[@class="heading heading--2 video-title"]'
)[0].text_content()
# Studio
metadata.studio = 'BadoinkVR'
# Summary
metadata.summary = detailsPageElements.xpath(
'//p[@class="video-description"]')[0].text_content().strip()
# Tagline and Collection
tagline = PAsearchSites.getSearchSiteName(siteID)
metadata.collections.clear()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
genres = detailsPageElements.xpath('//a[@class="video-tag"]')
if len(genres) > 0:
for genre in genres:
movieGenres.addGenre(genre.text_content())
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//a[contains(@class,"video-actor-link")]')
if len(actors) > 0:
for actorLink in actors:
actorName = actorLink.text_content()
actorPageURL = PAsearchSites.getSearchBaseURL(
siteID) + actorLink.get("href")
actorPage = HTML.ElementFromURL(actorPageURL)
actorPhotoURL = actorPage.xpath(
'//img[@class="girl-details-photo"]')[0].get("src").split('?')
movieActors.addActor(actorName, actorPhotoURL[0])
# Posters/Background
valid_names = list()
metadata.posters.validate_keys(valid_names)
metadata.art.validate_keys(valid_names)
posters = detailsPageElements.xpath(
'//div[contains(@class,"gallery-item")]')
posterNum = 1
for posterCur in posters:
posterURL = posterCur.get("data-big-image")
metadata.posters[posterURL] = Proxy.Preview(HTTP.Request(
posterURL, headers={
'Referer': 'http://www.google.com'
}).content,
sort_order=posterNum)
posterNum = posterNum + 1
backgroundURL = detailsPageElements.xpath(
'//img[@class="video-image"]')[0].get("src").split('?')
metadata.art[backgroundURL[0]] = Proxy.Preview(HTTP.Request(
backgroundURL[0], headers={
'Referer': 'http://www.google.com'
}).content,
sort_order=1)
# Date
try:
date = detailsPageElements.xpath(
'.//div[@class="video-details"]//p[@class="video-upload-date"]'
)[0].text_content().split(":")
dateFixed = date[1].strip()
Log('DateFixed: ' + dateFixed)
date_object = datetime.strptime(dateFixed, '%B %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
except:
Log("No date found")
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors, art):
metadata_id = str(metadata.id).split('|')
sceneTitle = PAutils.Decode(metadata_id[0])
sceneDescription = PAutils.Decode(metadata_id[2])
sceneDate = metadata_id[3]
sceneActors = metadata_id[4]
scenePoster = PAutils.Decode(metadata_id[5])
metadata.collections.clear()
movieGenres.clearGenres()
movieActors.clearActors()
# Title
metadata.title = sceneTitle
# Summary
metadata.summary = sceneDescription
# Studio
metadata.studio = 'PureCFNM'
# Tagline and Collection(s)
subSite = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = subSite
metadata.collections.add(subSite)
# Genres
if subSite.lower() == 'AmateurCFNM'.lower():
for genreName in ['CFNM']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'CFNMGames'.lower():
for genreName in ['CFNM', 'Femdom']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'GirlsAbuseGuys'.lower():
for genreName in ['CFNM', 'Femdom', 'Male Humiliation']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'HeyLittleDick'.lower():
for genreName in ['CFNM', 'Femdom', 'Small Penis Humiliation']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'LadyVoyeurs'.lower():
for genreName in ['CFNM', 'Voyeur']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'PureCFNM'.lower():
for genreName in ['CFNM']:
movieGenres.addGenre(genreName)
# Release Date
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
actors = sceneActors.split(',')
if actors:
if len(actors) == 2:
movieGenres.addGenre('Threesome')
elif len(actors) == 3:
movieGenres.addGenre('Foursome')
elif len(actors) > 3:
movieGenres.addGenre('Group')
for actorLink in actors:
actorName = actorLink.strip()
actorPhotoURL = ' '
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art.append(scenePoster)
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content, sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Studio
metadata.studio = 'Holly Randall Productions'
# Title
metadata.title = PAutils.Decode(metadata_id[2]).strip()
# Summary not available
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//ul[@class="tags"]/li/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Release Date
date_object = parse(PAutils.Decode(metadata_id[3]))
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//div[@class="info"]/p')[0].text_content().split('\n')[3].replace(
'Featuring:', '').split(',')
for actorLink in actors:
actorName = actorLink.strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//img[contains(@class, "update_thumb")]/@src0_3x',
]
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
art.append(PAsearchSites.getSearchBaseURL(siteNum) + poster)
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteID) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
art = []
# Title
metadata.title = detailsPageElements.xpath('//div[@class="fltWrap"]/h1/span')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath('//p[@class="description"]')[0].text_content().replace('Description:', '').strip()
# Studio
metadata.studio = 'ClubFilly'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath('//div[@class="fltRight"]')[0].text_content().replace('Release Date :', '').strip()
if date:
date_object = datetime.strptime(date, '%Y-%m-%d')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
movieGenres.addGenre('Lesbian')
# Actors
movieActors.clearActors()
actorText = detailsPageElements.xpath('//p[@class="starring"]')[0].text_content().replace('Starring:', '').strip()
actors = actorText.split(',')
if len(actors) > 0:
if len(actors) == 3:
movieGenres.addGenre('Threesome')
if len(actors) == 4:
movieGenres.addGenre('Foursome')
if len(actors) > 4:
movieGenres.addGenre('Orgy')
for actorLink in actors:
actorName = actorLink.strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//ul[@id="lstSceneFocus"]/li/img/@src'
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content, sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//div[contains(@class, "right-info")]//h1')[0].text_content().strip()
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Tagline and Collection
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(metadata.studio)
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Summary
description = detailsPageElements.xpath(
'//div[@class="description"]//span[contains(@class, "full")]')
if description:
metadata.summary = description[0].text_content().strip()
else:
metadata.summary = detailsPageElements.xpath(
'//div[@class="description"]')[0].text_content().strip()
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//div[@class="tag-list"]//a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actor in detailsPageElements.xpath(
'//div[contains(@class, "right-info")]//div[@class="info"]//a'):
actorName = actor.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
style = detailsPageElements.xpath('//div[@id="player"]/@style')[0]
img = style[style.find('\'') + 1:style.rfind('\'')].split('?', 1)[0]
art.append(img)
posters = detailsPageElements.xpath(
'//div[@class="gallery-item"]//a/@href')
for poster in posters:
img = poster.split('?', 1)[0]
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 and idx > 1:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchSearchURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
# Summary
summary_xpaths = [
'//div[@class="p-desc"]', '//div[contains(@class, "desc")]'
]
for xpath in summary_xpaths:
for summary in detailsPageElements.xpath(xpath):
metadata.summary = summary.text_content().replace(
'Read More »', '').strip()
break
# Studio
metadata.studio = 'Score Group'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
if Prefs['collections_addsitename']:
metadata.collections.add(metadata.tagline)
# Release Date
date = detailsPageElements.xpath('//div/span[@class="value"]')
if date:
date = date[1].text_content().strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath('//div/span[@class="value"]/a'):
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
if siteNum == 1344:
movieActors.addActor('Christy Marks', '')
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//div[@class="mb-3"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Posters/Background
art = []
match = re.search(r'posterImage: \'(.*)\'', req.text)
if match:
art.append(match.group(1))
xpaths = [
'//div[contains(@class, "thumb")]/img/@src',
'//div[contains(@class, "p-image")]/a/img/@src',
'//div[contains(@class, "dl-opts")]/a/img/@src',
'//div[contains(@class, "p-photos")]/div/div/a/@href',
'//div[contains(@class, "gallery")]/div/div/a/@href'
]
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
if not poster.startswith('http'):
poster = 'http:' + poster
if 'shared-bits' not in poster:
art.append(poster)
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
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
sceneID = 0
regex = re.search(r'-([0-9]{1,})\.', sceneURL)
if regex:
sceneID = int(regex.group(1))
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
titleDate = detailsPageElements.xpath('//title')[0].text_content().split(
'Released')
metadata.title = titleDate[0].strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@id="Bio"]')[0].text_content().strip()
# Studio
metadata.studio = 'First Time Videos'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = titleDate[-1].replace('!', '').strip()
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
genres = []
if tagline == 'FTVGirls':
genres = ['Teen', 'Solo', 'Public']
elif tagline == 'FTVMilfs':
genres = ['MILF', 'Solo', 'Public']
for genreName in genres:
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actors = []
for idx, actorLink in enumerate(
detailsPageElements.xpath('//div[@id="ModelDescription"]//h1')):
actorName = actorLink.text_content().replace('\'s Statistics',
'').strip()
actors.append(actorName)
regex = re.search(r'\s(%s [A-Z]\w{1,})\s' % actorName,
metadata.summary)
if regex:
actorName = regex.group(1)
actorPhotoURL = detailsPageElements.xpath(
'//div[@id="Thumbs"]/img/@src')[idx]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//img[@id="Magazine"]/@src',
'//div[@class="gallery"]//div[@class="row"]//@href',
'//div[@class="thumbs_horizontal"]//@href',
'//a[img[@class="t"]]/@href',
]
scenes = photoLookup(sceneID)
googleResults = PAutils.getFromGoogleSearch(' '.join(actors).strip(),
siteNum)
for photoURL in googleResults:
for scene in scenes:
if ('galleries' in photoURL or 'preview'
in photoURL) and (scene in photoURL or scene == 'none'):
req = PAutils.HTTPRequest(photoURL)
photoPageElements = HTML.ElementFromString(req.text)
for xpath in xpaths:
for img in photoPageElements.xpath(xpath):
art.append(img)
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors, art):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h1[@class="description"]/text()')[0].strip()
# Tagline and Collection(s)
metadata.collections.add(
detailsPageElements.xpath('//div[@class="studio"]//span/text()')
[1].strip())
if 'filthykings' in sceneURL:
metadata.collections.add(PAsearchSites.getSearchSiteName(siteNum))
# Studio
metadata.studio = 'AdultEmpireCash'
# Summary
summary = detailsPageElements.xpath('//div[@class="synopsis"]/p/text()')
if summary:
metadata.summary = summary[0].strip()
# Director
directorElement = detailsPageElements.xpath(
'//div[@class="director"]/text()')
if directorElement:
director = metadata.directors.new()
directorName = directorElement[0].strip()
director.name = directorName
# Release Date
date = detailsPageElements.xpath(
'//div[@class="release-date"]/text()')[0].strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//div[@class="video-performer"]//img'):
actorName = actorLink.get('title')
actorPhotoURL = actorLink.get('data-bgsrc')
movieActors.addActor(actorName, actorPhotoURL)
if 'filthykings' and '796896' in sceneURL:
movieActors.addActor('Alice Visby', '')
# Genres
movieGenres.clearGenres()
for genreName in detailsPageElements.xpath(
'//div[@class="tags"]//a/text()'):
movieGenres.addGenre(genreName)
# Posters
for poster in detailsPageElements.xpath(
'//div[@id="dv_frames"]//img/@src'):
img = poster.replace('320', '1280')
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 > 10:
# 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
def processActors(self, metadata):
for actorLink in self.actorsTable:
skip = False
# Save the potentional new Actor or Actress to a new variable, replace with a true space, and strip off any surrounding whitespace
actorName = actorLink['name'].replace('\xc2\xa0', ' ').replace(
',', '').strip().title()
actorPhoto = actorLink['photo'].strip()
actorName = ' '.join(actorName.split())
# Skip an actor completely; this could be used to filter out male actors if desired
if actorName == 'Bad Name':
skip = True
elif actorName == 'Test Model Name':
skip = True
if not skip:
searchStudioIndex = None
for studioIndex, studioList in PAdatabaseActors.ActorsStudioIndexes.items(
):
if metadata.studio in studioList:
searchStudioIndex = studioIndex
break
searchActorName = actorName.lower()
if searchStudioIndex is not None and searchStudioIndex in PAdatabaseActors.ActorsReplaceStudios:
for newActorName, aliases in PAdatabaseActors.ActorsReplaceStudios[
searchStudioIndex].items():
if searchActorName == newActorName.lower(
) or searchActorName in map(str.lower, aliases):
actorName = newActorName
if searchStudioIndex == 32 and actorName != 'QueenSnake':
actorName = '%s QueenSnake' % actorName
break
for newActorName, aliases in PAdatabaseActors.ActorsReplace.items(
):
if searchActorName == newActorName.lower(
) or searchActorName in map(str.lower, aliases):
actorName = newActorName
break
if ',' in actorName:
for newActor in actorName.split(','):
actorName = newActor.strip()
actorPhoto = actorDBfinder(actorName)
Log('Actor: %s %s' % (actorName, actorPhoto))
role = metadata.roles.new()
role.name = actorName
role.photo = actorPhoto
else:
req = None
if actorPhoto:
req = PAutils.HTTPRequest(actorPhoto,
'HEAD',
bypass=False)
if not req or not req.ok:
actorPhoto = actorDBfinder(actorName)
if actorPhoto:
actorPhoto = PAutils.getClearURL(actorPhoto)
Log('Actor: %s %s' % (actorName, actorPhoto))
role = metadata.roles.new()
role.name = actorName
role.photo = actorPhoto
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneID = int(metadata_id[0])
sceneType = metadata_id[2]
sceneIDName = 'clip_id' if sceneType == 'scenes' else 'movie_id'
sceneDate = metadata_id[3]
apiKEY = getAPIKey(siteNum)
url = PAsearchSites.getSearchSearchURL(
siteNum
) + '?x-algolia-application-id=TSMKFA364Q&x-algolia-api-key=' + apiKEY
data = getAlgolia(url, 'all_' + sceneType,
'filters=%s=%d' % (sceneIDName, sceneID),
PAsearchSites.getSearchBaseURL(siteNum))
detailsPageElements = data[0]
data = getAlgolia(url, 'all_scenes',
'query=%s' % detailsPageElements['url_title'],
PAsearchSites.getSearchBaseURL(siteNum))
data = sorted(data, key=lambda i: i['clip_id'])
scenesPagesElements = list(enumerate(data, 1))
# Title
title = None
if sceneType == 'scenes' and len(scenesPagesElements) > 1:
for idx, scene in scenesPagesElements:
if scene['clip_id'] == sceneID:
title = '%s, Scene %d' % (detailsPageElements['title'], idx)
break
if not title:
title = detailsPageElements['title']
metadata.title = title
# Summary
metadata.summary = detailsPageElements['description'].replace(
'</br>', '\n').replace('<br>', '\n')
# Studio
metadata.studio = detailsPageElements['network_name']
# Tagline and Collection(s)
metadata.collections.clear()
for collectionName in ['studio_name', 'serie_name']:
if collectionName in detailsPageElements:
metadata.collections.add(detailsPageElements[collectionName])
if (':' in detailsPageElements['title'] or '#'
in detailsPageElements['title']) and len(scenesPagesElements) > 1:
if 'movie_title' in detailsPageElements:
metadata.collections.add(detailsPageElements['movie_title'])
# Release Date
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements['categories']:
genreName = genreLink['name']
if genreName:
movieGenres.addGenre(genreName)
if sceneType == 'movies':
for idx, scene in scenesPagesElements:
for genreLink in scene['categories']:
genreName = genreLink['name']
if genreName:
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
female = []
male = []
for actorLink in detailsPageElements['actors']:
actorName = actorLink['name']
actorData = getAlgolia(url, 'all_actors',
'filters=actor_id=' + actorLink['actor_id'],
PAsearchSites.getSearchBaseURL(siteNum))[0]
if 'pictures' in actorData and actorData['pictures']:
max_quality = sorted(actorData['pictures'].keys())[-1]
actorPhotoURL = 'https://images-fame.gammacdn.com/actors' + actorData[
'pictures'][max_quality]
else:
actorPhotoURL = ''
if actorLink['gender'] == 'female':
female.append((actorName, actorPhotoURL))
else:
male.append((actorName, actorPhotoURL))
combined = female + male
for actor in combined:
movieActors.addActor(actor[0], actor[1])
# Posters
art = []
if not PAsearchSites.getSearchBaseURL(siteNum).endswith(
('girlsway.com', 'puretaboo.com')):
art.append(
'https://images-fame.gammacdn.com/movies/{0}/{0}_{1}_front_400x625.jpg'
.format(detailsPageElements['movie_id'],
detailsPageElements['url_title'].lower().replace('-',
'_')))
if 'url_movie_title' in detailsPageElements:
art.append(
'https://images-fame.gammacdn.com/movies/{0}/{0}_{1}_front_400x625.jpg'
.format(
detailsPageElements['movie_id'],
detailsPageElements['url_movie_title'].lower().replace(
'-', '_')))
if 'pictures' in detailsPageElements and detailsPageElements['pictures']:
max_quality = detailsPageElements['pictures']['nsfw']['top'].keys()[0]
pictureURL = 'https://images-fame.gammacdn.com/movies/' + detailsPageElements[
'pictures'][max_quality]
if sceneType == 'movies':
art.append(pictureURL)
else:
art.insert(0, pictureURL)
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 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
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 = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h1//span[@class="title"]')[0].text_content().strip()
# Summary
try:
metadata.summary = detailsPageElements.xpath(
'//div[@class="content-information-description"]//p'
)[0].text_content().strip()
except:
pass
# Studio
metadata.studio = 'Karups'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = detailsPageElements.xpath(
'//h1//span[@class="sup-title"]//span')[0].text_content().strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//span[@class="date"]/span[@class="content"]')[0].text_content(
).replace(tagline, '').replace('Video added on', '').strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
if tagline == 'KarupsHA':
genres = ['Amateur']
if tagline == 'KarupsPC':
genres = []
if tagline == 'KarupsOW':
genres = ['MILF']
for genre in genres:
movieGenres.addGenre(genre)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath('//span[@class="models"]//a'):
actorName = actorLink.text_content().strip()
actorPageURL = actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPageElements = HTML.ElementFromString(req.text)
actorPhotoURL = actorPageElements.xpath(
'//div[@class="model-thumb"]//img/@src')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//div[@class="video-player"]//video/@poster',
'//img[@class="poster"]/@src', '//div[@class="video-thumbs"]//img/@src'
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
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
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = '%s/membersarea/%s' % (PAsearchSites.getSearchBaseURL(siteID),
PAutils.Decode(metadata_id[0]))
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//title')[0].text_content().split('-')[0].strip()
# Studio
metadata.studio = 'FuelVirtual'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//td[@class="plaintext"]/a[@class="model_category_link"]'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
movieGenres.addGenre('18-Year-Old')
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//div[@id="description"]//td[@align="left"]/a')
if actors:
if len(actors) == 3:
movieGenres.addGenre('Threesome')
if len(actors) == 4:
movieGenres.addGenre('Foursome')
if len(actors) > 4:
movieGenres.addGenre('Orgy')
for actorLink in actors:
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = ['//a[@class="jqModal"]/img/@src']
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
img = PAsearchSites.getSearchBaseURL(siteID) + img
art.append(img)
photoPageUrl = sceneURL.replace('vids', 'highres')
req = PAutils.HTTPRequest(photoPageUrl)
photoPage = HTML.ElementFromString(req.text)
for img in photoPage.xpath('//a[@class="jqModal"]/img/@src'):
img = PAsearchSites.getSearchBaseURL(siteID) + 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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
art = []
metadata.collections.clear()
movieGenres.clearGenres()
movieActors.clearActors()
# Title
metadata.title = detailsPageElements.xpath(
'//h2[@class="wxt7nk-4 fSsARZ"]')[0].text_content().replace(
'SML-', '').replace('Trailer', '').strip()
# Studio
metadata.studio = 'TrueAmateurs'
# Tagline and Collection(s)
metadata.tagline = metadata.studio
metadata.collections.add(metadata.tagline)
# Genres
for genreLink in detailsPageElements.xpath(
'//div[@class="tjb798-2 flgKJM"]/span[1]/a'):
genreName = genreLink.text_content().replace(',', '').strip().lower()
movieGenres.addGenre(genreName)
# Release Date
date = detailsPageElements.xpath(
'//div[@class="tjb798-3 gFvmpb"]/span[last()]')
if date:
date = date[0].text_content().strip().replace('Release Date:', '')
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
try:
actors = detailsPageElements.xpath('//a[@class="wxt7nk-6 czvZQW"]')
if actors:
if len(actors) == 3:
movieGenres.addGenre('Threesome')
if len(actors) == 4:
movieGenres.addGenre('Foursome')
if len(actors) > 4:
movieGenres.addGenre('Orgy')
for actorLink in actors:
actorPageURL = actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = 'http:' + actorPage.xpath(
'//div[@class="profilePic_in"]//img/@src')[0]
movieActors.addActor(actorName, actorPhotoURL)
except:
pass
# Posters
art = []
xpaths = ['//div[@class="tg5e7m-2 evtSOm"]/img/@src']
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
art.append(poster)
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneID = metadata_id[0]
detailsPageElements = getDataFromAPI(
PAsearchSites.getSearchSearchURL(siteNum), 'identifier',
sceneID)['hits']['hits'][0]['_source']
# Title
metadata.title = detailsPageElements['name']
# Summary
metadata.summary = detailsPageElements['description']
# Studio
metadata.studio = detailsPageElements['studio']['name'].title()
# Tagline and Collection(s)
metadata.collections.add(metadata.studio)
seriesScene = detailsPageElements['series']['name']
if seriesScene:
metadata.collections.add(seriesScene.title())
# Release Date
date = detailsPageElements['releaseDate']
date_object = datetime.strptime(date, '%Y-%m-%d')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements['actors']:
actorName = actorLink['name']
actorPhotoURL = 'https://i.bang.com/pornstars/%d.jpg' % actorLink['id']
movieActors.addActor(actorName, actorPhotoURL)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements['genres']:
genreName = genreLink['name']
movieGenres.addGenre(genreName)
# Posters
dvdID = detailsPageElements['dvd']['id']
art = ['https://i.bang.com/covers/%d/front.jpg' % dvdID]
for img in detailsPageElements['screenshots']:
art.append('https://i.bang.com/screenshots/%d/movie/1/%d.jpg' %
(dvdID, img['screenId']))
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 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
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 = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath('//h1')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath('//div[contains(@class, "u-mb--six ")]')[0].text_content().strip()
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Tagline and Collection(s)
metadata.collections.clear()
metadata.tagline = metadata.studio
metadata.collections.add(metadata.studio)
# Release Date
date = detailsPageElements.xpath('//span[@class="date-display-single"] | //span[@class="u-inline-block u-mr--nine"] | //div[@class="video-meta-date"] | //div[@class="date"]')[0].text_content().strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//a[contains(@href, "/list/category/")]'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath('//a[contains(@href, "/pornstars/model/")]'):
actorPageURL = PAsearchSites.getSearchBaseURL(siteNum) + actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorName = actorLink.text_content().strip()
actorPhotoURL = actorPage.xpath('//div[contains(@class, "u-ratio--model-poster")]//img/@data-src')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters/Background
art = []
xpaths = [
'//div[contains(@class, "splash-screen")]/@style',
'//a[contains(@class, "u-ratio--lightbox")]/@href',
]
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
if poster.startswith('background-image'):
poster.split('url(')[1].split(')')[0]
art.append(poster)
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 and idx > 1:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors, art):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = 'http:' + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
movieGenres.clearGenres()
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="section"]//h1')[0].text_content().strip().title()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[4]/div/div[2]/div/div/div[2]/div[2]/p')[0].text_content().strip(
)
# Studio
metadata.studio = 'SinsLife'
# Release Date
date = detailsPageElements.xpath(
'//div[4]/div/div[2]/div/div/div[2]/div[1]/div/div[1]'
)[0].text_content().strip("Release Date:")
if date:
date_object = datetime.strptime(date, '%B %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//div[4]/div/div[2]/div/div/div[2]/div[3]/ul/li/a/..')
if actors:
if len(actors) == 3:
movieGenres.addGenre('Threesome')
if len(actors) == 4:
movieGenres.addGenre('Foursome')
if len(actors) > 4:
movieGenres.addGenre('Orgy')
for actorLink in actors:
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
try:
twitterBG = detailsPageElements.xpath(
'//div[4]/div/div[2]/div/div/div[1]/div[2]/div/div[1]/img')[0].get(
'src')
twitterBG = 'https:' + twitterBG
art.append(twitterBG)
except:
pass
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath('//h1')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath('//div[@class="customcontent"]//div')[0].text_content().strip()
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.studio = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath('//div[@class="date"]')[0].text_content().strip()
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
genres = detailsPageElements.xpath('//h4')[0].text_content().split(',')
for genreLink in genres:
genreName = genreLink.strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//div[@class="customcontent"]//h3')[0].text_content().split(',')
for actorLink in actors:
actorName = actorLink.replace(' ', '').strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
for idx in range(1, 4):
img = detailsPageElements.xpath('//center/img/@src')[0]
img = '%s/%sthumb_%d.jpg' % (PAsearchSites.getSearchBaseURL(siteNum), img.replace('thumb_1.jpg', ''), idx)
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
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="videoDetails clear"]/p')[0].text_content().strip()
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.studio = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//div[@class="featuring clear"]//li[./a]'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
# Posters
art = []
xpaths = [
'//div[@class="player"]/script',
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
match = re.search(r'(?<=(poster=")).*?(?=")', img.text_content())
if match:
img = match.group(0)
if 'http' not in img:
img = PAsearchSites.getSearchBaseURL(siteNum) + 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 height > 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
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = metadata.id.split('|')
sceneURL = PAutils.Decode(metadata_id[0])
scenePoster = PAutils.Decode(metadata_id[2])
if 'http' not in scenePoster:
scenePoster = PAsearchSites.getSearchSiteName(siteNum) + scenePoster
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="trailerArea"]/h3')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="trailerContent"]/p')[0].text_content().strip()
# Studio
metadata.studio = 'Meana Wolf'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//div[@class="videoContent"]/ul/li[2]')[0].text_content().replace(
'ADDED:', '').strip()
if date:
date_object = datetime.strptime(date, '%B %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieActors.clearActors()
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//div[@class="videoContent"]/ul/li[position()=last()]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
for actorLink in detailsPageElements.xpath(
'//div[@class="videoContent"]/ul/li[3]/a'):
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
try:
actorPageURL = actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = actorPage.xpath(
'//div[@class="modelBioPic"]/img/@src0_3x')[0]
if 'http' not in actorPhotoURL:
actorPhotoURL = PAsearchSites.getSearchBaseURL(
siteNum) + actorPhotoURL
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = [scenePoster]
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
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h2[@class="title"]/text()')[0]
# Summary
metadata.summary = detailsPageElements.xpath(
'//meta[@name="description"]/@content')[0]
# Studio
metadata.studio = 'Girls Rimming'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
actors = []
genres = detailsPageElements.xpath(
'//meta[@name="keywords"]/@content')[0].split(',')
for genreLink in genres:
genreName = genreLink.strip()
if ' Id ' in genreName:
actors.append(genreName)
else:
movieGenres.addGenre(genreName.title())
movieGenres.addGenre('Rim Job')
# Actors
movieActors.clearActors()
for actorLink in actors:
actorLink = actorLink.split(' Id ')
actorName = actorLink[0].strip()
actorPhotoURL = ''
actorPageURL = '%s/tour/models/%s.html' % (
PAsearchSites.getSearchBaseURL(siteNum), actorName.lower().replace(
' ', '-'))
data = PAutils.HTTPRequest(actorPageURL)
if not data or data == 'Page not found':
googleResults = PAutils.getFromGoogleSearch(actorName, siteNum)
for actorURL in googleResults:
actorURL = actorURL.lower()
if ('/models/' in actorURL):
data = PAutils.HTTPRequest(actorURL)
break
actorPage = HTML.ElementFromString(data.text)
actorPhotoURL = actorPage.xpath(
'//div[contains(@class, "model_picture")]//img/@src0_3x')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = [
detailsPageElements.xpath('//div[@id="fakeplayer"]//img/@src0_3x')[0]
]
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
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
try:
metadata.title = detailsPageElements.xpath(
'//a[@class="title"]')[0].text_content().strip()
except:
metadata.title = detailsPageElements.xpath(
'//meta[@property="og:title"]')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="entry_content"]/p')[0].text_content().strip()
# Studio
metadata.studio = 'MomPOV'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//div[@class="date_holder"]')[0].text_content().strip()
if date:
date_object = datetime.strptime(date, '%b %Y %d')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
movieGenres.addGenre('MILF')
# Actors
movieActors.clearActors()
# Posters
art = []
xpaths = ['//div[@id="inner_content"]/div[1]/a/img/@src']
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
art.append(poster)
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 and height >= width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.starstswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
art = []
metadata.collections.clear()
movieGenres.clearGenres()
movieActors.clearActors()
# Title
metadata.title = detailsPageElements.xpath('//h1//span')[0].text_content().strip().title().replace('Xxx', 'XXX')
# Studio
metadata.studio = 'Wicked Pictures'
# Release Date
date = detailsPageElements.xpath('//li[@class="updatedOn"] | //li[@class="updatedDate"]')[0].text_content().replace('Updated', '').replace('|', '').strip()
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Scene update
if '/video/' in url:
# Genres
for genreLink in detailsPageElements.xpath('//div[contains(@class, "sceneColCategories")]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
for actorLink in detailsPageElements.xpath('//div[contains(@class, "sceneColActors")]//a'):
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
try:
actorPageURL = urlBase + actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = actorPage.xpath('//img[@class="actorPicture"]/@src')[0]
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
script_text = detailsPageElements.xpath('//script')[7].text_content()
# Background
alpha = script_text.find('picPreview":"')
omega = script_text.find('"', alpha + 13)
previewBG = script_text[alpha + 13:omega].replace(r'\/', '/')
art.append(previewBG)
# Get dvd page for some info
dvdPageURL = urlBase + detailsPageElements.xpath('//div[@class="content"]//a[contains(@class,"dvdLink")]/@href')[0]
req = PAutils.HTTPRequest(dvdPageURL)
dvdPageElements = HTML.ElementFromString(req.text)
# Tagline and Collection(s)
tagline = dvdPageElements.xpath('//h3[@class="dvdTitle"]')[0].text_content().strip().title().replace('Xxx', 'XXX')
metadata.tagline = tagline
metadata.collections.add(tagline)
# Summary
try:
metadata.summary = dvdPageElements.xpath('//p[@class="descriptionText"]')[0].text_content().strip()
except:
pass
# Director
director = metadata.directors.new()
try:
directors = dvdPageElements.xpath('//ul[@class="directedBy"]')
for dirname in directors:
director.name = dirname.text_content().strip()
except:
pass
# DVD cover
dvdCover = dvdPageElements.xpath('//img[@class="dvdCover"]/@src')[0]
art.append(dvdCover)
# Extra photos for the completist
photoPageURL = urlBase + detailsPageElements.xpath('//div[contains(@class, "picturesItem")]//a')[0].get('href').split('?')[0]
req = PAutils.HTTPRequest(photoPageURL)
photoPageElements = HTML.ElementFromString(req.text)
# good 2:3 poster picture
poster = photoPageElements.xpath('//div[@class="previewImage"]//img/@src')[0]
art.append(poster)
# more Pictures
extraPix = photoPageElements.xpath('//li[@class="preview"]//a[@class="imgLink pgUnlocked"]/@href')
for pictureURL in extraPix:
art.append(pictureURL)
# Full DVD update
else:
# Genres
for genreLink in detailsPageElements.xpath('//p[@class="dvdCol"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
for actorLink in detailsPageElements.xpath('//div[@class="actorCarousel"]//a'):
actorName = actorLink.xpath('.//span')[0].text_content().strip()
actorPhotoURL = ''
try:
actorPhotoURL = actorLink.xpath('.//img/@src')[0].get("src")
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
# Tagline/collections
tagline = 'Wicked Pictures'
metadata.tagline = tagline
metadata.collections.add(tagline)
# Summary
try:
metadata.summary = detailsPageElements.xpath('//p[@class="descriptionText"]')[0].text_content().strip()
except:
pass
# Director
director = metadata.directors.new()
try:
directors = detailsPageElements.xpath('//ul[@class="directedBy"]')
for dirname in directors:
director.name = dirname.text_content().strip()
except:
pass
# Backgrounds
scenePreviews = detailsPageElements.xpath('//div[@class="sceneContainer"]//img[contains(@id,"clip")]/@data-original')
for scenePreview in scenePreviews:
previewIMG = scenePreview.split('?')[0]
art.append(previewIMG)
# DVD cover
dvdCover = detailsPageElements.xpath('//img[@class="dvdCover"]/@src')[0]
art.append(dvdCover)
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content, sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
Log('******UPDATE CALLED*******')
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
detailsPageElements = HTML.ElementFromURL(sceneURL)
movieGenres.clearGenres()
# Studio
metadata.studio = 'LittleCaprice'
# Title
metadata.title = detailsPageElements.xpath(
'//h1[@class="entry-title"]')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="et_pb_text et_pb_module et_pb_bg_layout_light et_pb_text_align_left"]/p'
)[0].text_content().strip()
#Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//meta[@property="article:published_time"]')[0].get("content").split(
"T")[0]
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//div[contains(@class,"et_pb_text_align_left")]/ul/li[contains(.,"Models")]/a'
)
if actors:
if len(actors) == 3:
movieGenres.addGenre("Threesome")
if len(actors) == 4:
movieGenres.addGenre("Foursome")
if len(actors) > 4:
movieGenres.addGenre("Orgy")
for actorLink in actors:
actorPageURL = actorLink.get("href")
actorPage = HTML.ElementFromURL(actorPageURL)
actorName = actorLink.text_content().strip()
actorPhotoURL = actorPage.xpath(
'//img[@class="model-page"]')[0].get("src")
actorPhotoURL = actorPhotoURL.replace("media.", '')
if 'http' not in actorPhotoURL:
actorPhotoURL = PAsearchSites.getSearchBaseURL(
siteID) + actorPhotoURL
movieActors.addActor(actorName, actorPhotoURL)
### Posters and artwork ###
art = []
# Video trailer background image
try:
twitterBG = detailsPageElements.xpath(
'//meta[@property="og:image"]/@content')[0]
art.append(twitterBG)
except:
pass
# Photos
photos = detailsPageElements.xpath(
'//span[@class="et_pb_image_wrap "]/img/@src')
for photoLink in photos:
art.append(PAsearchSites.getSearchBaseURL(siteID) + photoLink)
# Scene photos page
try:
photoPageUrl = PAsearchSites.getSearchBaseURL(
siteID
) + detailsPageElements.xpath(
'//div[contains(@class, "et_pb_text_align_left")]/ul/li[contains(., "Pictures:")]/a/@href'
)[0]
photoPage = HTML.ElementFromURL(photoPageUrl)
for unlockedPhoto in photoPage.xpath(
'//div[@class="et_pb_gallery_image landscape"]/a/@href'):
if not unlockedPhoto.startswith('http'):
unlockedPhoto = PAsearchSites.getSearchBaseURL(
siteID) + unlockedPhoto
art.append(unlockedPhoto)
except:
pass
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:
img_file = urllib.urlopen(posterUrl)
im = StringIO(img_file.read())
resized_image = Image.open(im)
width, height = resized_image.size
#Add the image proxy items to the collection
if width > 1 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(HTTP.Request(
posterUrl,
headers={
'Referer': 'http://www.google.com'
}).content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(HTTP.Request(
posterUrl,
headers={
'Referer': 'http://www.google.com'
}).content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteID) + sceneURL
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteID)
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="col-xs-12 video-title"]//h3')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="col-sm-6 col-md-6 vidpage-info"]/text()')[4].strip()
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//div[@class="videopage-tags"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//div[@class="col-xs-6 col-sm-4 col-md-3"]'):
actorName = actorLink.xpath(
'.//div[@class="vidpage-mobilePad"]//a//strong/text()')[0].strip()
actorPhotoURL = ''
try:
actorPhotoURL = actorLink.xpath(
'.//img[@class="img-responsive imgHover"]/@src')[0]
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
# Photos
art = []
try:
posterURL = detailsPageElements.xpath(
'//div[@class="col-xs-12 col-sm-6 col-md-6 vidCover"]//img/@src'
)[0]
art.append(posterURL)
except:
pass
for photo in detailsPageElements.xpath(
'//div[@class="vid-flex-container"]//span'):
photoLink = photo.xpath('.//img/@rsc')[0].replace('_thumb', '')
art.append(photoLink)
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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteID) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
javID = detailsPageElements.xpath('//dt[text()="DVD ID:"]/following-sibling::dd[1]')[0].text_content().strip()
if javID.startswith('--'):
javID = detailsPageElements.xpath('//dt[text()="Content ID:"]/following-sibling::dd[1]')[0].text_content().strip()
if ' ' in javID:
javID = javID.upper.replace(' ', '-')
# Title
JavTitle = detailsPageElements.xpath("//cite[@itemprop='name']")[0].text_content().strip()
# Undoing the Self Censoring R18.com does to their tags and titles
if '**' in JavTitle:
JavTitle = JavTitle.replace('R**e', 'Rape')
JavTitle = JavTitle.replace('S********l', 'Schoolgirl')
JavTitle = JavTitle.replace('S***e', 'Slave')
JavTitle = JavTitle.replace('M****t', 'Molest')
JavTitle = JavTitle.replace('F***e', 'Force')
JavTitle = JavTitle.replace('G*******g', 'Gang Bang')
JavTitle = JavTitle.replace('G******g', 'G******g')
JavTitle = JavTitle.replace('K*d', 'Descendant')
JavTitle = JavTitle.replace('C***d', 'Descendant')
JavTitle = JavTitle.replace('T*****e', 'Torture')
JavTitle = JavTitle.replace('T******e', 'Tentacle')
JavTitle = JavTitle.replace('D**g', 'Drug')
JavTitle = JavTitle.replace('P****h', 'Punish')
JavTitle = JavTitle.replace('S*****t', 'Student')
JavTitle = JavTitle.replace('V*****e', 'Violate')
JavTitle = JavTitle.replace('V*****t', 'Violent')
JavTitle = JavTitle.replace('B***d', 'Blood')
JavTitle = JavTitle.replace('M************n', 'Mother and Son')
metadata.title = javID + ' ' + JavTitle
# Summary
try:
description = detailsPageElements.xpath('//div[@class="cmn-box-description01"]')[0].text_content()
metadata.summary = description.replace('Product Description', '', 1).strip()
except:
pass
# Studio
metadata.studio = detailsPageElements.xpath('//dd[@itemprop="productionCompany"]')[0].text_content().strip()
# Director
director = metadata.directors.new()
directorName = detailsPageElements.xpath('//dd[@itemprop="director"]')[0].text_content().strip()
if directorName != '----':
director.name = directorName
# Release Date
date = detailsPageElements.xpath('//dd[@itemprop="dateCreated"]')[0].text_content().strip().replace('.', '').replace(',', '').replace('Sept', 'Sep').replace('June', 'Jun').replace('July', 'Jul')
date_object = datetime.strptime(date, '%b %d %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actor in detailsPageElements.xpath('//div[@itemprop="actors"]//span[@itemprop="name"]'):
fullActorName = actor.text_content().strip()
if fullActorName != '----':
splitActorName = fullActorName.split('(')
mainName = splitActorName[0].strip()
actorPhotoURL = detailsPageElements.xpath('//div[@id="%s"]//img[contains(@alt, "%s")]/@src' % (mainName.replace(' ', ''), mainName))[0]
if actorPhotoURL.rsplit('/', 1)[1] == 'nowprinting.gif':
actorPhotoURL = ''
if len(splitActorName) > 1 and mainName == splitActorName[1][:-1]:
actorName = mainName
else:
actorName = fullActorName
movieActors.addActor(actorName, actorPhotoURL)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//a[@itemprop="genre"]'):
genreName = (genreLink.text_content().lower().strip()).lower()
if '**' in genreName:
genreName = genreName.replace('r**e', 'rape')
genreName = genreName.replace('s********l', 'schoolgirl')
genreName = genreName.replace('s***e', 'slave')
genreName = genreName.replace('m****ter', 'molester')
genreName = genreName.replace('g*******g', 'gang bang')
genreName = genreName.replace('g******g', 'g******g')
genreName = genreName.replace('k*d', 'descendant')
genreName = genreName.replace('c***d', 'descendant')
genreName = genreName.replace('f***e', 'force')
genreName = genreName.replace('t*****e', 'torture')
genreName = genreName.replace('t******e', 'tentacle')
genreName = genreName.replace('d**g', 'drug')
genreName = genreName.replace('p****h', 'punish')
genreName = genreName.replace('s*****t', 'student')
genreName = genreName.replace('v*****e', 'violate')
genreName = genreName.replace('v*****t', 'violent')
genreName = genreName.replace('b***d', 'blood')
movieGenres.addGenre(genreName)
metadata.collections.add('Japan Adult Video')
# Posters
art = []
xpaths = [
'//img[@itemprop="image"]/@src',
'//img[contains(@alt, "cover")]/@src',
'//section[@id="product-gallery"]//img/@data-src'
]
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
art.append(poster)
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, headers={'Referer': 'http://www.google.com'})
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 and idx > 1:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content, sort_order=idx)
except:
pass
return metadata
def update(metadata, siteID, movieGenres, movieActors):
metadata_id = metadata.id.split('|')
sceneURL = PAsearchSites.getSearchBaseURL(
siteID) + '/video/' + metadata_id[0]
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h2[@class="h2 m-0"]')[0].text_content().strip()
# Summary
try:
paragraphs = detailsPageElements.xpath('//div[@class="desc-text"]')
pNum = 0
summary = ""
for paragraph in paragraphs:
if pNum >= 0 and pNum < (len(paragraphs)):
summary = summary + '\n\n' + paragraph.text_content()
pNum += 1
except:
pass
if summary == '':
try:
summary = detailsPageElements.xpath(
'//div[@class="desc-text"]')[0].text_content().strip()
except:
pass
metadata.summary = summary.strip()
# Studio
metadata.studio = 'ManyVids'
# Collections / Tagline
metadata.collections.clear()
tagline = detailsPageElements.xpath(
'//a[contains(@class,"username ")]')[0].text_content().strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
genres = detailsPageElements.xpath('//div[@class="tags"]/a')
for genreLink in genres:
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actorName = detailsPageElements.xpath(
'//a[contains(@class,"username ")]')[0].text_content()
actorPhotoURL = ''
try:
actorPhotoURL = detailsPageElements.xpath(
'//div[@class="pr-2"]/a/img')[0].get('src')
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = ['//div[@id="rmpPlayer"]/@data-video-screenshot']
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
art.append(poster)
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, headers={'Referer': 'http://www.google.com'})
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 or height > width:
# Item is a poster
metadata.posters[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
if width > 100 and width > height:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def update(metadata, lang, siteNum, movieGenres, movieActors, art):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//title')[0].text_content().strip().split('•')[0]
# Summary
summary = ''
for paragraph in detailsPageElements.xpath('//li/div[@class="small"]/p'):
summary = summary + paragraph.text_content()
metadata.summary = summary
# Studio
metadata.studio = 'SinsVR'
# Tagline and Collection
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath('//span//time')[0].text_content().strip()
if date:
date_object = datetime.strptime(date, '%b %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for tag in detailsPageElements.xpath('//div[@class="tags-item"]'):
genreName = tag.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//div/strong[text()="Starring"]//following-sibling::span/a[@class="tiny-link"]'
):
actorName = actorLink.text_content().strip()
actorPageURL = PAsearchSites.getSearchBaseURL(siteNum) + actorLink.get(
'href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = actorPage.xpath(
'//div[@class="model-header__photo"]/img')[0].get('src')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
for poster in detailsPageElements.xpath(
'//div[contains(@class, "tn-photo__container")]/div/a/div/img/@src'
):
if poster.startswith('http'):
img = poster.replace('sceneGallerySmall', 'sceneGallery')
art.append(img)
poster = detailsPageElements.xpath('//dl8-video')[0]
img = poster.get('poster')
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