def search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
if siteNum == 978:
url = PAsearchSites.getSearchSearchURL(
siteNum) # All models are on one page
else:
url = PAsearchSites.getSearchSearchURL(siteNum) + searchTitle[
0:1] # First letter of model's name
req = PAutils.HTTPRequest(url)
searchResults = HTML.ElementFromString(req.text)
searchResultElements = searchResults.xpath(
'//a[starts-with(@href, "/free/girl/")][strong]')
for searchResult in searchResultElements:
titleNoFormatting = searchResult.text_content().strip()
curID = PAutils.Encode(searchResult.xpath('@href')[0].split('/')[3])
score = 100 - Util.LevenshteinDistance(searchTitle.lower(),
titleNoFormatting.lower())
if titleNoFormatting in searchTitle:
modelLink = PAsearchSites.getSearchBaseURL(
siteNum) + searchResult.xpath('@href')[0]
modelReq = PAutils.HTTPRequest(modelLink)
modelResults = HTML.ElementFromString(modelReq.text)
sceneResults = modelResults.xpath(
'.//a[starts-with(@href, "/free/scene/")][strong]')
if sceneResults:
for modelResult in modelResults.xpath(
'//div[contains(@class, "videos")]'):
titleLine = modelResult.xpath(
'.//h5')[0].text_content().strip()
href = modelResult.xpath(
'.//a[starts-with(@href, "/free/scene/")][strong]/@href'
)[0]
titleNoFormatting = titleLine.split('-')[1].strip()
curID = PAutils.Encode(
href.split('/')[3] + '/' + href.split('/')[4])
releaseDate = parse(
titleLine.split('ADDED:')[1].split('-')
[0].strip()).strftime('%Y-%m-%d')
score = 100 - Util.LevenshteinDistance(
searchDate, releaseDate)
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
else:
modelThumbnail = PAsearchSites.getSearchBaseURL(
siteNum) + searchResult.xpath('./img/@src')[0]
image = PAutils.HTTPRequest(
modelThumbnail,
headers={'Referer': 'http://www.google.com'})
releaseDate = parse(
image.headers['Last-Modified']).strftime('%Y-%m-%d')
if releaseDate == '2016-01-01': # Oldest image date, so could be anything pre 2016
releaseDate = ''
score = 100 - Util.LevenshteinDistance(titleNoFormatting,
searchTitle)
if releaseDate and parse(
searchDate
).year >= 2016: # Very good chance we can match on the date
delta = parse(searchDate) - parse(releaseDate)
if abs(delta.days) < 7:
score = 100 # High level of confidence right here
else:
score = score - 5
elif releaseDate == '' and parse(
searchDate).year < 2016: # Older video
score = score - 10
else:
score = score - 50
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, searchDate),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
return results
def update(metadata, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = '%s/membersarea/%s' % (PAsearchSites.getSearchBaseURL(siteNum), 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(siteNum).strip()
metadata.tagline = tagline
if Prefs['collections_addsitename']:
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(siteNum) + 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(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 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 search(results, lang, siteNum, searchData):
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + searchData.encoded)
searchResults = HTML.ElementFromString(req.text)
for searchResult in searchResults.xpath('//div[@class="scene"]'):
url = searchResult.xpath('.//a[@data-track="TITLE_LINK"]/@href')[0]
if '/scenes/' in url:
curID = PAutils.Encode(url)
titleNoFormatting = searchResult.xpath(
'.//a[@data-track="TITLE_LINK"]')[0].text_content()
releaseDate = parse(
searchResult.xpath('./span[@class="scene-date"]')
[0].text_content().strip()).strftime('%Y-%m-%d')
if searchData.date:
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' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum), releaseDate),
score=score,
lang=lang))
# search for exact scene name
urlTitle = searchData.encoded.replace('%20', '-')
urls = [
PAsearchSites.getSearchBaseURL(siteNum) + '/scenes/video---' +
urlTitle + '_vids.html',
PAsearchSites.getSearchBaseURL(siteNum) + '/scenes/movie---' +
urlTitle + '_vids.html'
]
for url in urls:
try:
sceneReq = PAutils.HTTPRequest(url)
scenePage = HTML.ElementFromString(sceneReq.text)
curID = PAutils.Encode(url)
titleNoFormatting = scenePage.xpath(
'//div[@class="content-desc content-new-scene"]//h1'
)[0].text_content().strip()
releaseDate = parse(
scenePage.xpath('//meta[@itemprop="uploadDate"]')[0].get(
'content'))
score = 100
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum), releaseDate),
score=score,
lang=lang))
except:
pass
return results
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 = PAutils.Decode(metadata_id[2])
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="container text-center"]//h2')[0].text_content().strip()
# Studio
metadata.studio = 'Cumbizz'
# 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(
'//span[@class="label label-primary"]/a'):
genreName = genreLink.text_content().strip().lower()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//div[@class="breadcrumbs"]/a'):
actorName = str(actorLink.text_content().strip())
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//section[@class="har_section har_image_bck har_wht_txt har_fixed"]/@data-image',
'//img[@class="vidgal unos"]/@src',
'//img[@class="vidgal dos"]/@src',
'//img[@class="vidgal tres"]/@src',
'//img[@class="vidgal quatros"]/@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, lang, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
searchURL = PAutils.Decode(metadata_id[0])
sceneID = int(metadata_id[2])
req = PAutils.HTTPRequest(searchURL)
detailsPageElements = None
searchResults = req.json()
if 'results' not in searchResults:
return metadata
for searchResult in searchResults['results']:
if searchResult['id'] == sceneID:
detailsPageElements = searchResult
break
if not detailsPageElements:
return metadata
# Title
metadata.title = detailsPageElements['title']
# Summary
metadata.summary = re.sub(r'<.*?>', '',
detailsPageElements['long_description']).strip(
) # must strip HTML tags
# Tagline and Collection(s)
metadata.collections.clear()
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = metadata.studio
metadata.collections.add(metadata.studio)
# Release date
date_object = parse(detailsPageElements['release_date'])
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
genres = []
for genreLink in genres:
genreName = genreLink
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
if 'actors' in detailsPageElements:
actors = detailsPageElements['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['name']
actorPhotoURL = actorLink['thumb']['image']
if actorPhotoURL.endswith('noimageavailable.gif'):
actorSearchURL = PAsearchSites.getSearchBaseURL(
siteNum
) + '/api/v2/search/actors?thumb_size=355x475&query=' + actorName.split(
)[0]
req = PAutils.HTTPRequest(actorSearchURL)
searchResults = req.json()
if 'results' in searchResults:
for searchResult in searchResults['results']:
if searchResult['id'] == actorLink['id']:
actorPhotoURL = searchResult['thumb']['image']
break
movieActors.addActor(actorName, actorPhotoURL)
# Director
metadata.directors.clear()
if 'directors' in detailsPageElements:
for directorLink in detailsPageElements['directors']:
director = metadata.directors.new()
director.name = directorLink['name']
# Posters
art = [detailsPageElements['thumb']['image']]
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])
cookies = {'nats': 'MC4wLjMuNTguMC4wLjAuMC4w'}
req = PAutils.HTTPRequest(sceneURL, cookies=cookies)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//title')[0].text_content().split('|')[0]
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[contains(@class, "video-summary")]//p[@class=""]'
)[0].text_content()
# Studio
metadata.studio = '5Kporn'
# Tagline and Collection(s)
metadata.collections.clear()
metadata.tagline = PAsearchSites.getSearchSiteName(siteID)
metadata.collections.add(metadata.tagline)
# Date
date = detailsPageElements.xpath('//h5[contains(., "Published")]')
if date:
date = date[0].text_content().replace('Published:', '').strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//h5[contains(., "Starring")]/a')
for actorLink in actors:
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
modelURL = actorLink.xpath('.//@href')[0]
req = PAutils.HTTPRequest(modelURL, cookies=cookies)
actorsPageElements = HTML.ElementFromString(req.text)
img = actorsPageElements.xpath('//img[@class="model-image"]/@src')
if img:
actorPhotoURL = img[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//div[contains(@class, "gal")]//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': sceneURL},
cookies=cookies)
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])
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
# Summary
description = ''
for desc in detailsPageElements.xpath('//div[@class="description"]//p'):
description += desc.text_content().strip() + '\n\n'
metadata.summary = description
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Tagline and Collection(s)
metadata.collections.clear()
tagline = detailsPageElements.xpath(
'//p[@class="series"]')[0].text_content().strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//span[@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()
for genreLink in detailsPageElements.xpath(
'//meta[@name="keywords"]/@content')[0].split(','):
genreName = genreLink.strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//div[@class="model-wrap"]//li')
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.xpath('.//h5')[0].text_content()
actorPhotoURL = actorLink.xpath('.//img/@src')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//div[@class="photo-wrap"]//@href',
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
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, 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:
# 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)
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(siteNum)
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)
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 = metadata.id.split('|')
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + '/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)
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, 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(
'//h1')[0].text_content().strip()
except:
try:
metadata.title = detailsPageElements.xpath(
'//meta[@property="og:title"]')[0].text_content().strip()
except:
try:
metadata.title = detailsPageElements.xpath(
'//meta[@name="twitter:title"]')[0].text_content().strip()
except:
pass
# Summary
summary = detailsPageElements.xpath(
'//div[@class="record-description-content record-box-content"]'
)[0].text_content().strip()
metadata.summary = summary[:summary.find('Runtime')].strip()
# Studio
metadata.studio = 'Hegre'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//span[@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[@class="tag"]'):
genreName = genreLink.text_content().strip().lower()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//a[@class="record-model"]')
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.get('title').strip()
actorPhotoURL = actorLink.xpath('.//img/@src')[0].replace(
'240x', '480x')
movieActors.addActor(actorName, actorPhotoURL)
# Director
director = metadata.directors.new()
director.name = 'Petter Hegre'
director.photo = 'https://img.discogs.com/TafxhnwJE2nhLodoB6UktY6m0xM=/fit-in/180x264/filters:strip_icc():format(jpeg):mode_rgb():quality(90)/discogs-images/A-2236724-1305622884.jpeg.jpg'
# Posters
art = [
detailsPageElements.xpath('//meta[@name="twitter:image"]/@content')
[0].replace('board-image', 'poster-image').replace('1600x', '640x'),
detailsPageElements.xpath('//meta[@name="twitter:image"]/@content')
[0].replace('1600x', '1920x')
]
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:
# 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('|')
sceneID = metadata_id[0]
title = metadata_id[2].strip()
apiurl = getAPIURL(
PAsearchSites.getSearchBaseURL(siteNum) + '/scene/' + sceneID + '/' +
urllib.quote(title))
apiurl = PAsearchSites.getSearchSearchURL(siteNum) + apiurl
detailsPageElements = getJSONfromAPI(apiurl +
updatequery.format(sceneID))[0]
# Title
metadata.title = PAutils.parseTitle(detailsPageElements['title'].title(),
siteNum)
# Summary
metadata.summary = detailsPageElements['description']
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Tagline and Collection(s)
metadata.collections.clear()
metadata.collections.add(metadata.studio)
# Release Date
date = detailsPageElements['sites']['collection'][sceneID]['publishDate']
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
movieActors.clearActors()
if 'tags' in detailsPageElements:
genres = detailsPageElements['tags']['collection']
if not isinstance(genres, list):
for (key, value) in genres.items():
genre = value['alias']
if genre:
if siteNum == 1027:
genre = genre.replace('-', ' ')
movieActors.addActor(genre, '')
else:
movieGenres.addGenre(genre)
# Actors
actors = getJSONfromAPI(apiurl + modelquery + sceneID)
if not isinstance(actors, list):
for key, value in actors.items():
collect = value['modelId']['collection']
for k, val in collect.items():
actorName = val['stageName']
if actorName:
movieActors.addActor(actorName, '')
if siteNum == 1024:
baseactor = 'Aletta Ocean'
elif siteNum == 1025:
baseactor = 'Eva Lovia'
elif siteNum == 1026:
baseactor = 'Romi Rain'
elif siteNum == 1030:
baseactor = 'Dani Daniels'
elif siteNum == 1031:
baseactor = 'Chloe Toy'
elif siteNum == 1033:
baseactor = 'Katya Clover'
elif siteNum == 1035:
baseactor = 'Lisey Sweet'
elif siteNum == 1037:
baseactor = 'Gina Gerson'
elif siteNum == 1038:
baseactor = 'Valentina Nappi'
elif siteNum == 1039:
baseactor = 'Vina Sky'
elif siteNum == 1058:
baseactor = 'Vicki Valkyrie'
elif siteNum == 1075:
baseactor = 'Dillion Harper'
elif siteNum == 1191:
baseactor = 'Lilu Moon'
else:
baseactor = ''
movieActors.addActor(baseactor, '')
# Posters
art = []
artobj = json.loads(PAutils.Decode(metadata_id[3]))
if artobj:
for detailsPageElements in artobj:
art.append(detailsPageElements['url'])
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 and idx > 1:
# Item is an art item
metadata.art[posterUrl] = Proxy.Media(image.content,
sort_order=idx)
except:
pass
return metadata
def getJSONfromAPI(url):
req = PAutils.HTTPRequest(url)
return req.json()['response']['collection']
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
try:
metadata.title = detailsPageElements.xpath(
'//h1[@class="entry-title"]')[-1].text_content().strip()
except:
pass
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Collections / Tagline
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
for genreLink in detailsPageElements.xpath(
'//div[@class="tags-list"]/a//i[@class="fa fa-folder-open"]/..'):
genreName = genreLink.text_content().replace('Movies',
'').strip().lower()
movieGenres.addGenre(genreName)
# Release Date
date = detailsPageElements.xpath(
'//div[@id="video-date"]')[0].text_content().strip()
if date:
date = date.replace('Date:', '').strip()
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//div[@id="video-actors"]//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()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
image = PAutils.Decode(metadata_id[2])
if image:
art.append(image)
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 search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
sceneID = None
splited = searchTitle.split(' ')
if unicode(splited[0], 'utf8').isdigit():
sceneID = splited[0]
searchTitle = searchTitle.replace(sceneID, '', 1).strip()
req = PAutils.HTTPRequest(
PAsearchSites.getSearchBaseURL(siteNum) + '/vrpornvideo/' +
sceneID)
searchResults = HTML.ElementFromString(req.text)
titleNoFormatting = searchResults.xpath(
'//h1[contains(@class, "video-title")]')[0].text_content()
curID = PAutils.Encode(
PAsearchSites.getSearchBaseURL(siteNum) + '/vrpornvideo/' +
sceneID)
girlName = ''
releaseDate = ''
date = searchResults.xpath('//p[@itemprop="uploadDate"]/@content')
if date:
releaseDate = parse(date[0]).strftime('%Y-%m-%d')
score = 100
results.Append(
MetadataSearchResult(id='%s|%d' % (curID, siteNum),
name='[%s] %s in %s %s' %
(PAsearchSites.getSearchSiteName(siteNum),
girlName, titleNoFormatting, releaseDate),
score=score,
lang=lang))
else:
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + encodedTitle)
searchResults = HTML.ElementFromString(req.text)
for searchResult in searchResults.xpath(
'//div[@class="tile-grid-item"]'):
data = searchResult.xpath(
'.//a[contains(@class, "video-card-title")]')[0]
titleNoFormatting = searchResult.xpath(
'.//a[contains(@class, "video-card-title")]/@title')[0]
curID = PAutils.Encode(
searchResult.xpath(
'.//a[contains(@class, "video-card-title")]/@href')[0])
releaseDate = ''
date = searchResult.xpath(
'.//span[@class="video-card-upload-date"]/@content')
if date:
releaseDate = parse(date[0]).strftime('%Y-%m-%d')
girlName = searchResult.xpath(
'.//a[@class="video-card-link"]')[0].text_content()
if searchDate and releaseDate:
score = 100 - Util.LevenshteinDistance(searchDate, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
searchTitle.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d' % (curID, siteNum),
name='[%s] %s in %s %s' %
(PAsearchSites.getSearchSiteName(siteNum), girlName,
titleNoFormatting, releaseDate),
score=score,
lang=lang))
return results
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
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
movieActors.clearActors()
# Title
metadata.title = detailsPageElements.xpath(
'//div[contains(@class, "title")]/h2')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="description"]/div[@class="desc-text"]')[0].text_content(
).strip()
# Studio/Tagline/Collection
metadata.collections.clear()
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = metadata.studio
metadata.collections.add(metadata.studio)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath(
'//ul[contains(@class, "tags")]//a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Posters/Background
art = []
xpaths = [
'//meta[@property="og:image"]/@content',
'//div[contains(@class, "thumbnails")]//img/@src',
]
for xpath in xpaths:
for poster in detailsPageElements.xpath(xpath):
poster = poster.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, 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)
# Title
metadata.title = detailsPageElements.xpath(
'//h1[contains(@class, "video-title")]')[0].text_content()
# Summary
metadata.summary = detailsPageElements.xpath(
'//p[@class="video-description"]')[0].text_content().strip()
# Studio
metadata.studio = 'BadoinkVR'
# Tagline and Collection
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
sceneDate = detailsPageElements.xpath(
'//p[@itemprop="uploadDate"]/@content')
if sceneDate:
date_object = parse(sceneDate[0])
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements.xpath('//a[@class="video-tag"]'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements.xpath(
'//a[contains(@class,"video-actor-link")]'):
actorName = actorLink.text_content().strip()
actorPageURL = PAsearchSites.getSearchBaseURL(siteID) + actorLink.get(
'href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = actorPage.xpath(
'//img[@class="girl-details-photo"]/@src')[0].split('?')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//div[contains(@class,"gallery-item")]/@data-big-image',
'//img[@class="video-image"]/@src'
]
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
img = img.split('?')[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, 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 idx > 1 and 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, art):
metadata_id = metadata.id.split('|')
sceneURL = PAutils.Decode(metadata_id[0])
if not sceneURL.startswith('http'):
sceneURL = PAsearchSites.getSearchBaseURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = 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
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 search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
sceneURL = sceneURL.split('?')[0].replace('dev.', '', 1)
if ('/view/' in sceneURL) and (
'photoset' not in sceneURL) and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in googleResults:
if ('/model/' in sceneURL):
req = PAutils.HTTPRequest(sceneURL)
actorPageElements = HTML.ElementFromString(req.text)
for searchResult in actorPageElements.xpath(
'//div[contains(@class, "content-item")]'):
sceneURL = searchResult.xpath('.//h3//@href')[0].split(
'?')[0].replace('dev.', '', 1)
if sceneURL not in searchResults:
titleNoFormatting = searchResult.xpath(
'.//h3')[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
date = searchResult.xpath('.//span[@class="pub-date"]'
)[0].text_content().strip()
releaseDate = parse(date).strftime('%Y-%m-%d')
if searchDate:
score = 100 - Util.LevenshteinDistance(
searchDate, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
searchTitle.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d' % (curID, siteNum),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
date = detailsPageElements.xpath(
'//span[@class="date"]')[0].text_content().strip()
releaseDate = parse(date).strftime('%Y-%m-%d')
if searchDate:
score = 100 - Util.LevenshteinDistance(searchDate, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(searchTitle.lower(),
titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d' % (curID, siteNum),
name='%s [%s] %s' %
(titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
return results
def update(metadata, siteNum, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
sceneURL = PAutils.Decode(metadata_id[0])
try:
sceneDate = metadata_id[2]
except:
pass
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
movieGenres.clearGenres()
movieActors.clearActors()
# Title
if 'webmasters' in sceneURL:
resultTitleID = detailsPageElements.xpath('//h1/text()')[0].title()
metadata.title = re.sub(r'^\d+', '', resultTitleID)
else:
resultTitleID = detailsPageElements.xpath(
'//h4/span')[0].text_content().title()
metadata.title = re.sub(r'^\d+', '', resultTitleID)
sceneID = re.sub(r'\D.*', '', resultTitleID)
# Summary
try:
if 'webmasters' in sceneURL:
metadata.summary = detailsPageElements.xpath(
'//div[@class="row gallery-description"]//div'
)[1].text_content().strip()
else:
metadata.summary = detailsPageElements.xpath(
'//div[@class="row"]//a/@title')[0].strip()
except:
pass
# Tagline and Collection(s)
metadata.collections.clear()
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = metadata.studio
metadata.collections.add(metadata.studio)
# Actors
if 'webmasters' in sceneURL:
actors = detailsPageElements.xpath('//spam[@class="key-words"]//a')
else:
actors = detailsPageElements.xpath('//h5//a')
actorPhotoURL = ''
# Remove Actor Names from Genre List
genres = detailsPageElements.xpath(
'//meta[@name="keywords"]/@content')[0].replace('Aussie Ass', '')
genres = re.sub(r'id.\d*', '', genres, flags=re.IGNORECASE)
if actors:
for actorLink in actors:
actorName = actorLink.text_content().title()
genres = genres.replace(actorName, '')
modelURL = actorLink.xpath('./@href')[0]
req = PAutils.HTTPRequest(modelURL)
actorsPageElements = HTML.ElementFromString(req.text)
img = actorsPageElements.xpath(
'//img[contains(@id,"set-target")]/@src')[0]
if img:
actorPhotoURL = img
if 'http' not in actorPhotoURL:
actorPhotoURL = PAsearchSites.getSearchBaseURL(
siteNum) + actorPhotoURL
movieActors.addActor(actorName, actorPhotoURL)
# Date
date = ""
try:
if 'webmasters' in sceneURL:
pageResults = (int)(actorsPageElements.xpath(
'//span[@class="number_item "]')[0].text_content().strip())
if not pageResults:
pageResults = 1
for x in range(pageResults):
if x == 1:
actorsPageElements.xpath(
'//a[contains(@class,"in_stditem")]/@href')[1]
req = PAutils.HTTPRequest(
PAsearchSites.getSearchBaseURL(siteNum) +
actorsPageElements.xpath(
'//a[contains(@class,"in_stditem")]/@href')[1])
actorsPageElements = HTML.ElementFromString(req.text)
for sceneElements in actorsPageElements.xpath(
'//div[@class="box"]'):
if sceneID in sceneElements.xpath('.//a/text()')[1]:
date = actorsPageElements.xpath(
'.//span[@class="video-date"]')[0].text_content(
).strip()
break
else:
date = sceneDate
except:
date = sceneDate
if date:
date = parse(date).strftime('%d-%m-%Y')
date_object = datetime.strptime(date, '%d-%m-%Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
for genre in genres.split(','):
movieGenres.addGenre(genre.strip())
# Posters
art = []
xpaths = [
'//img[contains(@alt,"content")]/@src',
'//div[@class="box"]//img/@src',
]
altURL = ""
for xpath in xpaths:
for img in detailsPageElements.xpath(xpath):
if 'http' not in img:
if 'join' in img:
break
elif 'webmasters' in sceneURL:
img = sceneURL + "/" + img
else:
img = PAsearchSites.getSearchBaseURL(siteNum) + img
art.append(img)
if 'webmasters' not in sceneURL:
altURL = PAsearchSites.getSearchBaseURL(
siteNum) + "/webmasters/" + sceneID
req = PAutils.HTTPRequest(altURL)
detailsPageElements = HTML.ElementFromString(req.text)
sceneURL = altURL
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('|')
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(
'//meta[@property="og:title"]/@content')[0].replace(
' - Mormon Girlz', '').strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//*[contains(@id, "post-")]/aside[2]/div/div[1]')[0].text_content(
).strip()
# Studio
metadata.studio = 'MormonGirlz'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'//meta[@property="article:published_time"]/@content')[0].strip()
if date:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Genres
movieGenres.clearGenres()
xpaths = [
'//h1[contains(text(), "more of") and not(contains(text(), "Mormon Girls"))]'
]
for xpath in xpaths:
for genreLink in detailsPageElements.xpath(xpath):
genreName = genreLink.text.replace('more of', '').strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
# Posters
art = []
xpaths = ['//*[@class="ngg-gallery-thumbnail"]/a/@href']
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 search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
sceneID = re.sub(r'\D.*', '', searchTitle)
if sceneID:
sceneURL = PAsearchSites.getSearchBaseURL(
siteNum) + "/webmasters/" + sceneID
req = PAutils.HTTPRequest(sceneURL)
searchResults = HTML.ElementFromString(req.text)
titleNoFormatting = re.sub(
r'^\d+', '',
searchResults.xpath('//h1/text()')[0].title())
curID = PAutils.Encode(sceneURL)
score = 100
results.Append(
MetadataSearchResult(
id='%s|%d' % (curID, siteNum),
name='%s [%s]' %
(titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum)),
score=score,
lang=lang))
else:
# Handle 3 Types of Links: First, Last; First Only; First-Last
try:
encodedTitle = re.search(r'^\S*.\S*',
searchTitle).group(0).replace(' ',
'').lower()
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + encodedTitle +
".html")
searchResults = HTML.ElementFromString(req.text)
if searchResults.xpath(
'//html')[0].text_content() == 'Page not found':
raise Exception
except:
try:
encodedTitle = re.search(r'^\S*.\S*',
searchTitle).group(0).replace(
' ', '-').lower()
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + encodedTitle +
".html")
searchResults = HTML.ElementFromString(req.text)
if searchResults.xpath(
'//html')[0].text_content() == 'Page not found':
raise Exception
except:
encodedTitle = re.search(r'^\S*', searchTitle).group(0).lower()
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + encodedTitle +
".html")
searchResults = HTML.ElementFromString(req.text)
try:
pageResults = (int)(searchResults.xpath(
'//span[@class="number_item "]')[0].text_content().strip())
except:
pageResults = 1
for x in range(pageResults):
if x == 1:
searchResults.xpath(
'//a[contains(@class,"in_stditem")]/@href')[1]
req = PAutils.HTTPRequest(
PAsearchSites.getSearchBaseURL(siteNum) +
searchResults.xpath(
'//a[contains(@class,"in_stditem")]/@href')[1])
searchResults = HTML.ElementFromString(req.text)
for searchResult in searchResults.xpath('//div[@class="infos"]'):
resultTitleID = searchResult.xpath(
'.//span[@class="video-title"]')[0].text_content().strip(
).title()
titleNoFormatting = re.sub(r'^\d+', '', resultTitleID)
resultID = re.sub(r'\D.*', '', resultTitleID)
sceneURL = searchResult.xpath('.//a/@href')[0]
curID = PAutils.Encode(sceneURL)
date = searchResult.xpath(
'.//span[@class="video-date"]')[0].text_content().strip()
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = parse(searchDate).strftime(
'%Y-%m-%d') if searchDate else ''
releaseDate = parse(date).strftime('%Y-%m-%d')
displayDate = releaseDate if date else ''
if sceneID == resultID:
score = 100
elif searchDate and displayDate:
score = 100 - Util.LevenshteinDistance(
searchDate, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
searchTitle.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchURL = PAsearchSites.getSearchSearchURL(siteNum) + searchData.encoded
req = PAutils.HTTPRequest(searchURL)
searchResults = req.json()
if 'results' not in searchResults or not searchResults[
'results'] and searchData.filename:
# femjoy.17.03.12.maria.rya.girl.in.the.mirror.mp4
# try to extract as much of the title as possible without including the model
m = re.search(r'femjoy\.(\d{2}\.\d{2}\.\d{2})\.(.+)',
searchData.filename, re.IGNORECASE)
if m:
searchData.date = parse('20' + m.group(1)).strftime('%Y-%m-%d')
searchWords = m.group(2).split('.')
wordCount = len(searchWords)
if wordCount > 2:
searchData.title = ' '.join(searchWords[2:])
else:
searchData.title = searchWords[-1]
else:
# Belinda & Fiva - Give me your hand 29-Mar-2010.mp4
# take everything from after the dash and before the date
m = re.search(r'.+ - (.+) (\d{2}-[a-z]{3}-\d{4})',
searchData.filename, re.IGNORECASE)
if m:
searchData.date = parse(m.group(2)).strftime('%Y-%m-%d')
searchData.title = m.group(1)
searchData.encoded = urllib.quote(searchData.title)
searchURL = PAsearchSites.getSearchSearchURL(
siteNum) + searchData.encoded
req = PAutils.HTTPRequest(searchURL)
searchResults = req.json()
if 'results' in searchResults:
curID = PAutils.Encode(searchURL)
for searchResult in searchResults['results']:
titleNoFormatting = searchResult['title']
sceneID = searchResult['id']
date = searchResult['release_date']
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat(
) if searchData.date else ''
displayDate = releaseDate if date else ''
actorsName = [
actorLink['name'] for actorLink in searchResult['actors']
]
actorsString = getActorsString(actorsName)
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|%d' % (curID, siteNum, sceneID),
name='%s - %s [%s] %s' %
(titleNoFormatting, actorsString,
PAsearchSites.getSearchSiteName(siteNum), displayDate),
score=score,
lang=lang))
return results
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)
movieGenres.clearGenres()
# Title
metadata.title = detailsPageElements.xpath(
'//title')[0].text_content().split('|')[-1].strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//meta[@name="description"]')[0].get('content').strip()
# Studio
metadata.studio = 'ReidMyLips'
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Release Date
date = detailsPageElements.xpath(
'/html/body/div/div[4]/div[4]/div/main/div[2]/div[2]/div/div/div[2]/div/div/div[4]/p/span'
)[0].text_content().strip()
if len(date) > 0:
date_object = datetime.strptime(date, '%B %d, %Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
actorName = 'Riley Reid'
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
photos = detailsPageElements.xpath(
'//div[@id="pro-gallery-margin-container"]//a[@class="block-fullscreen gallery-item-social-download pull-right gallery-item-social-button"]//@href'
)
for photoLink in photos:
photo = photoLink.split('?')[0]
art.append(photo)
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('|')
sceneTitle = PAutils.Decode(metadata_id[0])
sceneDescription = PAutils.Decode(metadata_id[2])
sceneDate = metadata_id[3]
scenePoster = PAutils.Decode(metadata_id[4])
art = []
metadata.collections.clear()
movieGenres.clearGenres()
movieActors.clearActors()
# Title
metadata.title = sceneTitle
# Summary
metadata.summary = sceneDescription
# Studio
metadata.studio = 'Thick Cash'
# Tagline and Collection(s)
subSite = PAsearchSites.getSearchSiteName(siteNum)
metadata.tagline = subSite
if Prefs['collections_addsitename']:
metadata.collections.add(subSite)
# Genres
if subSite.lower() == 'Family Lust'.lower():
for genreName in ['Family Roleplay']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'Over 40 Handjobs'.lower():
for genreName in ['MILF', 'Handjob']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'Ebony Tugs'.lower():
for genreName in ['Ebony', 'Handjob']:
movieGenres.addGenre(genreName)
elif subSite.lower() == 'Teen Tugs'.lower():
for genreName in ['Teen', 'Handjob']:
movieGenres.addGenre(genreName)
# Release Date
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# 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 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 = 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 = []
movieGenres.clearGenres()
movieActors.clearActors()
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="main-info-left"]/h1')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//p[@class="description"]')[0].text_content().strip()
# Studio
metadata.studio = 'Love Her Feet'
# 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="date"]')[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 genreLink in detailsPageElements.xpath('//div[@class="video-tags"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
movieGenres.addGenre('Foot Sex')
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//div[@class="featured"]/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 = ''
try:
actorPageURL = actorLink.get('href')
req = PAutils.HTTPRequest(actorPageURL)
actorPage = HTML.ElementFromString(req.text)
actorPhotoURL = actorPage.xpath(
'//div[@class="picture"]/img')[0].get("src0_3x")
if 'http' not in actorPhotoURL:
actorPhotoURL = PAsearchSites.getSearchBaseURL(
siteNum) + actorPhotoURL
except:
pass
movieActors.addActor(actorName, actorPhotoURL)
# Photos
art = []
xpaths = [
'//meta[@property="og:image"]/@content',
'//div[@class="photos"]/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, 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)
# Studio
metadata.studio = 'Angela White'
# Title
metadata.title = PAutils.Decode(metadata_id[2]).strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//div[@class="desc"]/p')[0].text_content().strip()
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteNum).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
genres = detailsPageElements.xpath(
'//meta[@name="keywords"]/@content')[0].replace('.', '').split(',')
for genreLink in genres:
genreName = genreLink.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()
actorstr = metadata.title.replace('BTS', '')
actorstr = (''.join(i for i in list(actorstr) if not i.isdigit())).strip()
actors = actorstr.split(' X ')
for actorLink in actors:
actorName = actorLink.strip().lower()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//img[contains(@class, "tour-area-thumb")]/@data-src',
]
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, 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
if '/en/' in sceneURL:
metadata.title = PAutils.parseTitle(detailsPageElements.xpath('//title')[0].text_content().split('|')[0].split('-')[0].strip(), siteNum)
else:
metadata.title = detailsPageElements.xpath('//title')[0].text_content().split('|')[0].split('-')[0].strip()
# Summary
metadata.summary = detailsPageElements.xpath('//div[@class="description clearfix"]')[0].text_content().split(':')[-1].strip().replace('\n', ' ')
# 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="categories"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
if '/en/' in sceneURL:
if '&' in metadata.title:
actors = metadata.title.split('&')
else:
actors = detailsPageElements.xpath('//span[@class="site-name"]')[0].text_content().split(' and ')
else:
if '&' in metadata.title:
actors = metadata.title.split('&')
else:
actors = detailsPageElements.xpath('//span[@class="site-name"]')[0].text_content().split(' y ')
for actorLink in actors:
actorName = actorLink.strip()
modelURL = '%s/actrices/%s' % (PAsearchSites.getSearchBaseURL(siteNum), metadata.title[0].lower())
req = PAutils.HTTPRequest(modelURL)
modelPageElements = HTML.ElementFromString(req.text)
for model in modelPageElements.xpath('//div[@class="c-boxlist__box--image"]//parent::a'):
if model.text_content().strip().lower() == metadata.title.lower():
actorName = metadata.title
break
if 'africa' in actorName.lower():
actorName = 'Africat'
elif metadata.title == 'MAMADA ARGENTINA':
actorName = 'Alejandra Argentina'
elif actorName == 'Alika':
actorName = 'Alyka'
modelURL = '%s/actrices/%s' % (PAsearchSites.getSearchBaseURL(siteNum), actorName[0].lower())
req = PAutils.HTTPRequest(modelURL)
modelPageElements = HTML.ElementFromString(req.text)
actorPhotoURL = ''
for model in modelPageElements.xpath('//div[@class="c-boxlist__box--image"]//parent::a'):
if model.text_content().strip().lower() == actorName.lower():
actorPhotoURL = model.xpath('.//img/@src')[0].strip()
break
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
img = detailsPageElements.xpath('//div[@class="top-area-content"]/script')[0].text_content().strip()
posterImage = re.search(r'(?<=posterImage:\s").*(?=")', img)
if posterImage:
img = posterImage.group(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 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, 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
sceneDate = metadata_id[2]
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath(
'//div[@class="content-desc content-new-scene"]//h1')[0].text_content(
).replace('Video -', '').replace('Movie -', '').strip()
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# Summary
try:
metadata.summary = detailsPageElements.xpath(
'//div[@class="content-desc content-new-scene"]//p'
)[0].text_content().strip()
except:
pass
# Genres
movieGenres.clearGenres()
for genre in detailsPageElements.xpath(
'//ul[contains(@class, "scene-tags")]/li'):
genreName = genre.xpath('.//a')[0].text_content().lower()
movieGenres.addGenre(genreName)
# Release Date
date = detailsPageElements.xpath('//meta[@itemprop="uploadDate"]')[0].get(
'content')
if date:
date_object = datetime.strptime(date, '%m/%d/%Y')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
elif sceneDate:
date_object = parse(date)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actorPage in detailsPageElements.xpath(
'//ul[@id="featured_pornstars"]//div[@class="model"]'):
actorName = actorPage.xpath('.//h3')[0].text_content().strip()
actorPhotoURL = actorPage.xpath('.//img/@src')[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = [
detailsPageElements.xpath(
'//div[@id="trailer_player_finished"]//img/@src')[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, siteID, movieGenres, movieActors):
metadata_id = str(metadata.id).split('|')
curID = PAutils.Decode(metadata_id[0])
if len(metadata_id) > 2:
sceneDate = metadata_id[2]
if '/' in curID: # Viewing a Scene
sceneURL = PAsearchSites.getSearchBaseURL(
siteID) + '/free/scene/' + curID + '/ec'
else: # Viewing a Model
sceneURL = PAsearchSites.getSearchBaseURL(
siteID) + '/free/girl/' + curID + '/ec'
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Title
metadata.title = detailsPageElements.xpath('//h3/text()[1]')[0].strip()
# Summary
description = detailsPageElements.xpath(
'//meta[@name="description"]/@content')[0].strip()
metadata.summary = description.strip()
# Studio
metadata.studio = 'ExploitedX'
# Collections / Tagline
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID)
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(
'//a[starts-with(@href, "/free/keywords")]'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
if '/' in curID: # Viewing a Scene
unique_list = []
for modelLink in detailsPageElements.xpath(
'//a[starts-with(@href, "/free/girl/")]'):
modelLinkUrl = PAsearchSites.getSearchBaseURL(
siteID) + modelLink.xpath('./@href')[0]
if modelLinkUrl not in unique_list:
unique_list.append(modelLinkUrl)
req = PAutils.HTTPRequest(modelLinkUrl)
modelPageElements = HTML.ElementFromString(req.text)
actorName = modelPageElements.xpath(
'//meta[@name="twitter:description"]/@content')[0].strip()
actorPhotoURL = modelPageElements.xpath(
'//meta[@name="twitter:image"]/@content')[0].strip()
movieActors.addActor(actorName, actorPhotoURL)
else: # Viewing a Model
actorName = detailsPageElements.xpath(
'//meta[@name="twitter:description"]/@content')[0].strip()
actorPhotoURL = detailsPageElements.xpath(
'//meta[@name="twitter:image"]/@content')[0].strip()
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
xpaths = [
'//meta[@name="twitter:image"]/@content',
]
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:
# 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
