def search(self, results, media, lang):
if Prefs['strip_enable']:
title = media.name.split(Prefs['strip_symbol'], 1)[0]
else:
title = media.name
title = getSearchTitle(title)
Log('***MEDIA TITLE [from media.name]*** %s' % title)
searchSettings = PAsearchSites.getSearchSettings(title)
Log(searchSettings)
filepath = None
filename = None
if media.filename:
filepath = urllib.unquote(media.filename)
filename = str(os.path.splitext(os.path.basename(filepath))[0])
if searchSettings['siteNum'] is None and filepath:
directory = str(os.path.split(os.path.dirname(filepath))[1])
newTitle = getSearchTitle(directory)
Log('***MEDIA TITLE [from directory]*** %s' % newTitle)
searchSettings = PAsearchSites.getSearchSettings(newTitle)
if searchSettings['siteNum'] is not None and searchSettings[
'searchTitle'].lower() == PAsearchSites.getSearchSiteName(
searchSettings['siteNum']).lower():
newTitle = '%s %s' % (newTitle, title)
Log('***MEDIA TITLE [from directory + media.name]*** %s' %
newTitle)
searchSettings = PAsearchSites.getSearchSettings(newTitle)
siteNum = searchSettings['siteNum']
if siteNum is not None:
search = PAsearchData.SearchData(media,
searchSettings['searchTitle'],
searchSettings['searchDate'],
filepath, filename)
provider = PAsiteList.getProviderFromSiteNum(siteNum)
if provider is not None:
providerName = getattr(provider, '__name__')
Log('Provider: %s' % providerName)
provider.search(results, lang, siteNum, search)
if Prefs['metadataapi_enable']:
if providerName != 'networkMetadataAPI' and (
not results
or 100 != max([result.score
for result in results])):
siteNum = PAsearchSites.getSiteNumByFilter(
'MetadataAPI')
if siteNum is not None:
provider = PAsiteList.getProviderFromSiteNum(
siteNum)
if provider is not None:
providerName = getattr(provider, '__name__')
Log('Provider: %s' % providerName)
try:
provider.search(results, lang, siteNum,
search)
except Exception as e:
Log(e)
results.Sort('score', descending=True)
def update(metadata, siteID, movieGenres, movieActors):
Log('******UPDATE CALLED*******')
metadata_id = str(metadata.id).split('|')
url = PAutils.Decode(metadata_id[0])
sceneDate = metadata_id[2]
poster = metadata_id[3] if len(metadata_id) > 3 else None
detailsPageElements = HTML.ElementFromURL(url)
# Studio
metadata.studio = 'Full P**n Network'
# Title
metadata.title = detailsPageElements.xpath(
'//h4')[0].text_content().strip()
# Summary
metadata.summary = detailsPageElements.xpath(
'//p[@class="hide-for-small-only"]')[0].text_content().strip()
# Release Date
if sceneDate:
date_object = parse(sceneDate)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Tagline and Collection(s)
metadata.collections.clear()
for seriesName in [
metadata.studio,
PAsearchSites.getSearchSiteName(siteID)
]:
metadata.collections.add(seriesName)
# Genres
movieGenres.clearGenres()
genres = detailsPageElements.xpath(
'//div[@class="small-12"]//a[contains(@href, "/category/")]/text()')
for genreLink in genres:
genreName = genreLink.strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath(
'//div[@class="small-12"]//a[contains(@href, "/model/")]/@href')
for actorLink in actors:
actorPage = HTML.ElementFromURL(
PAsearchSites.getSearchBaseURL(siteID) + actorLink)
actorName = actorPage.xpath('//h1')[0].text_content().strip()
actorPhotoURL = actorPage.xpath('//img[@alt="%s"]/@src' % actorName)[0]
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = [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:
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:
# 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:
# 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):
Log('******UPDATE CALLED*******')
metadata_id = str(metadata.id).split('|')
sceneId = metadata_id[0]
token = getToken(PAsearchSites.getSearchBaseURL(siteID))
detailsPageElements = getDatafromAPI(
PAsearchSites.getSearchBaseURL(siteID), sceneId, token)
# Studio
producerLink = detailsPageElements['producer']
metadata.studio = '%s %s' % (producerLink['name'],
producerLink['last_name'])
# Title
metadata.title = detailsPageElements['title']
# Summary
metadata.summary = detailsPageElements['synopsis_clean']
# Tagline and Collection(s)
metadata.collections.clear()
tagline = PAsearchSites.getSearchSiteName(siteID).strip()
metadata.tagline = tagline
metadata.collections.add(tagline)
# Genres
movieGenres.clearGenres()
for genreLink in detailsPageElements['tags']:
genreName = genreLink['title']
movieGenres.addGenre(genreName)
# Release Date
date_object = parse(detailsPageElements['release_date'])
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
for actorLink in detailsPageElements['performers']:
actorName = '%s %s' % (actorLink['name'], actorLink['last_name'])
actorPhotoURL = actorLink['poster_image'].split('?', 1)[0]
movieActors.addActor(actorName, actorPhotoURL)
# Director
director = metadata.directors.new()
directorLink = detailsPageElements['director']
director.name = '%s %s' % (directorLink['name'], directorLink['last_name'])
# Poster
art = [detailsPageElements['poster_picture'].split('?', 1)[0]]
for photoLink in detailsPageElements['album']:
img = photoLink['path'].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:
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 and idx > 1:
# 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 search(results, encodedTitle, title, searchTitle, siteNum, lang,
searchDate):
searchResultsURLs = []
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
if sceneURL not in searchResultsURLs:
url = None
if '/scene/' in sceneURL:
url = sceneURL
else:
for item in ['/trailers/', '/updates/']:
if item in sceneURL:
url = sceneURL.replace(item, '/1/scene/').replace(
'.html', '/')
break
if url and url not in searchResultsURLs:
searchResultsURLs.append(url)
for url in searchResultsURLs:
detailsPageElements = HTML.ElementFromURL(url)
curID = PAutils.Encode(url)
titleNoFormatting = detailsPageElements.xpath(
'//h4')[0].text_content().strip()
releaseDate = parse(searchDate).strftime(
'%Y-%m-%d') if searchDate else ''
score = 100 - Util.LevenshteinDistance(searchTitle.lower(),
titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [FPN/%s] %s' %
(titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
searchResults = HTML.ElementFromURL(
PAsearchSites.getSearchSearchURL(siteNum) +
searchTitle.replace(' ', '_'))
for searchResult in searchResults.xpath(
'//div[contains(@class, "section-updates")]'):
curID = PAutils.Encode(searchResult.xpath('.//a/@href')[0])
titleNoFormatting = searchResult.xpath(
'.//div[contains(@class, "scene-info")]//a')[0].text_content(
).strip()
poster = searchResult.xpath('.//img/@src')[0]
releaseDate = parse(searchDate).strftime(
'%Y-%m-%d') if searchDate else ''
score = 100 - Util.LevenshteinDistance(searchTitle.lower(),
titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d|%s|%s' % (curID, siteNum, releaseDate, poster),
name='%s [FPN/%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])
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[@id="content-more-less"]/p')[0].text_content().strip()
# Studio
metadata.studio = 'CumLouder'
# 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 - no actual date aviable, guessing (better than nothing)
date = detailsPageElements.xpath('//div[@class="added"]')[0].text_content().strip()
timeframe = date.split(' ')[2]
timenumber = int(date.split(' ')[1])
today = datetime.now()
if timeframe:
if timeframe == 'minutes':
date_object = today
elif timeframe == 'hour' or timeframe == 'hours':
date_object = today - relativedelta(hours=timenumber)
elif timeframe == 'day' or timeframe == 'days':
date_object = today - relativedelta(days=timenumber)
elif timeframe == 'week' or timeframe == 'weeks':
date_object = today - relativedelta(weeks=timenumber)
elif timeframe == 'month' or timeframe == 'months':
date_object = today - relativedelta(months=timenumber)
elif timeframe == 'year' or timeframe == 'years':
date_object = today - relativedelta(years=timenumber)
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Actors
movieActors.clearActors()
actors = detailsPageElements.xpath('//a[@class="pornstar-link"]')
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 = [
'//div[@class="box-video box-video-html5"]/video/@lazy'
]
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:
# 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.getSearchSearchURL(siteNum) + sceneURL
req = PAutils.HTTPRequest(sceneURL, headers={'Cookie': 'cLegalAge=true'})
detailsPageElements = HTML.ElementFromString(req.text)
# Title
Title = detailsPageElements.xpath(
'//span[@class="contentFilmName"]')[0].text_content().strip().title()
metadata.title = Title.title()
# Studio
metadata.studio = PAsearchSites.getSearchSiteName(siteNum)
# 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="contentFileDate"]')[
0].text_content().strip().split(' • ')[0]
date_object = datetime.strptime(date, '%Y %B %d')
metadata.originally_available_at = date_object
metadata.year = metadata.originally_available_at.year
# Summary
# Basic Summary
try:
description = detailsPageElements.xpath(
'//div[@class="contentPreviewDescription"]')[0].text_content()
metadata.summary = description.strip()
except:
pass
# Genres
movieGenres.clearGenres()
# Default Genres
genres = ['BDSM', 'S&M']
for genreName in genres:
movieGenres.addGenre(genreName)
# Dynamic Genres
for genreLink in detailsPageElements.xpath(
'//div[@class="contentPreviewTags"]/a'):
genreName = genreLink.text_content().strip()
movieGenres.addGenre(genreName)
# Actors
movieActors.clearActors()
siteActors = [
'abby', 'briana', 'david', 'diamond', 'greta', 'hellia', 'hilda',
'holly', 'jade', 'jeby', 'jessica', 'keya', 'lilith', 'luna', 'marc',
'micha', 'misty', 'nastee', 'nazryana', 'pearl', 'qs', 'queensnake',
'rachel', 'ruby', 'sharon', 'suzy', 'tanita', 'tracy', 'zara'
]
for actorLink in detailsPageElements.xpath(
'//div[@class="contentPreviewTags"]/a'):
if actorLink.text_content().strip().lower() in siteActors:
actorName = actorLink.text_content().strip()
actorPhotoURL = ''
movieActors.addActor(actorName, actorPhotoURL)
# Posters
art = []
for poster in detailsPageElements.xpath(
'//div[@class="contentBlock"]//img[contains(@src, "preview")]/@src'
):
posterUrl = PAsearchSites.getSearchBaseURL(siteNum) + poster.split(
'?')[0]
art.append(posterUrl)
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, 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 search(results, lang, siteNum, search):
req = PAutils.HTTPRequest(
PAsearchSites.getSearchSearchURL(siteNum) + search['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 search['date']:
score = 100 - Util.LevenshteinDistance(search['date'],
releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
search['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 = search['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
