def search(results, lang, siteNum, searchData):
searchResultsURLs = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
if searchData.title.count(' ') > 1:
directSearch = searchData.title.replace(' ', '-').lower()
else:
directSearch = searchData.title.replace(' ', '')
searchResultsURLs.append(
'%s/models/%s.html' %
(PAsearchSites.getSearchBaseURL(siteNum), directSearch))
for searchResultURL in googleResults:
if searchResultURL not in searchResultsURLs:
if '/models/' in searchResultURL:
searchResultsURLs.append(searchResultURL)
for modelURL in searchResultsURLs:
req = PAutils.HTTPRequest(modelURL)
pageElements = HTML.ElementFromString(req.text)
for sceneResult in pageElements.xpath(
'//div[contains(@class, "latest-updates")]//div[@data-setid]'):
sceneLink = sceneResult.xpath(
'.//div[contains(@class, "text-info")]//a[contains(@class, "text-sm")]'
)[0]
curID = PAutils.Encode(sceneLink.xpath('./@href')[0])
titleNoFormatting = sceneLink.text_content().strip()
poster = PAutils.Encode(
sceneResult.xpath('.//a[@class="updateimg"]//img/@src0_3x')[0])
releaseDate = sceneResult.xpath(
'.//div[contains(@class, "video-data")]/span[2]'
)[0].text_content()
score = 100 - Util.LevenshteinDistance(searchData.title.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 search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
sceneID = None
splited = searchTitle.split(' ')
searchResults = []
if unicode(splited[0], 'UTF-8').isdigit():
sceneID = splited[0]
searchTitle = searchTitle.replace(sceneID, '', 1).strip()
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + sceneID + '.html'
searchResults.append(directURL)
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
if ('/update/' in sceneURL) and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
curID = PAutils.Encode(sceneURL)
titleDate = detailsPageElements.xpath(
'//title')[0].text_content().split('Released')
titleNoFormatting = titleDate[0].strip()
date = titleDate[-1].replace('!', '').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 search(results, lang, siteNum, searchData):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + searchData.title.lower().replace(' ', '-').replace(
'\'', '-')
searchResults = [directURL]
if unicode(directURL[-1], 'UTF-8').isdigit() and directURL[-2] == '-':
directURL = '%s-%s' % (directURL[:-1], directURL[-1])
searchResults.append(directURL)
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/video/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
searchResults = list(
dict.fromkeys(
[sceneURL.replace('www.', '', 1) for sceneURL in searchResults]))
for sceneURL in searchResults:
if sceneURL == directURL.replace('www.', '', 1):
for original, new in plurals.items():
sceneURL = sceneURL.replace(original, new)
req = PAutils.HTTPRequest(sceneURL)
if 'signup.' not in req.url:
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
releaseDate = searchData.dateFormat() if searchData.date 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))
return results
def search(results, lang, siteNum, searchData):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/search/' not in sceneURL and '/page/' not in sceneURL
and '/tag/' not in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
if detailsPageElements.xpath('//meta[@property="og:type"]/@content'
)[0].strip() == 'video':
titleNoFormatting = detailsPageElements.xpath(
'//meta[@property="og:title"]/@content')[0].strip()
curID = PAutils.Encode(sceneURL)
date = detailsPageElements.xpath(
'//div[@class="post_date"]')[0].text_content().strip()
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat(
) if searchData.date else ''
displayDate = releaseDate if date else ''
if searchData.date and displayDate:
score = 100 - Util.LevenshteinDistance(
searchData.date, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
searchData.title.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum),
releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchData.encoded = searchData.title.replace(' ', '-')
searchResultsURLs = [
PAsearchSites.getSearchSearchURL(siteNum) + 'updates/' +
searchData.encoded + '.html',
PAsearchSites.getSearchSearchURL(siteNum) + 'updates/' +
searchData.encoded + '-.html',
PAsearchSites.getSearchSearchURL(siteNum) + 'updates/' +
searchData.encoded + '-4k.html',
PAsearchSites.getSearchSearchURL(siteNum) + 'dvds/' +
searchData.encoded + '.html'
]
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if sceneURL not in searchResultsURLs:
if (('/updates/' in sceneURL or '/dvds/' in sceneURL
or '/scenes/' in sceneURL) and '/tour_ns/'
in sceneURL) and sceneURL not in searchResultsURLs:
searchResultsURLs.append(sceneURL)
for sceneURL in searchResultsURLs:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
try:
searchResult = HTML.ElementFromString(req.text)
titleNoFormatting = searchResult.xpath(
'(//div[@class="indScene"] | //div[@class="indSceneDVD"])/h1'
)[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
score = 100 - Util.LevenshteinDistance(
searchData.title.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(id='%s|%d' % (curID, siteNum),
name='%s [New Sensations]' %
titleNoFormatting,
score=score,
lang=lang))
except:
pass
return results
def search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
sceneID = searchTitle.split(' ', 1)[0]
if unicode(sceneID, 'UTF-8').isdigit():
searchTitle = searchTitle.replace(sceneID, '', 1).strip()
else:
sceneID = None
directURL = PAsearchSites.getSearchSearchURL(siteNum) + sceneID
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
if ('/videos/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
searchResults = HTML.ElementFromString(req.text)
titleNoFormatting = searchResults.xpath(
'//h1[@class="customhcolor"]')[0].text_content()
curID = PAutils.Encode(
PAsearchSites.getSearchSearchURL(siteNum) + sceneID)
releaseDate = ''
date = searchResults.xpath(
'//div[@class="date"]')[0].text_content().strip()
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
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 %s' %
(PAsearchSites.getSearchSiteName(siteNum),
titleNoFormatting, releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
sceneURL = sceneURL.replace('/cn/', '/').replace('/de/', '/').replace('/jp/', '/').replace('/ja/', '/').replace('/en/', '/')
if '/nude_girl/' not in sceneURL and '/shoots/' not in sceneURL and '/fetish/' not in sceneURL and '/updates/' not in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
prevModelURL = ''
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = PAutils.parseTitle(detailsPageElements.xpath('//title')[0].text_content().split(':')[-1].split('|')[0].strip(), siteNum)
subSite = PAutils.parseTitle(detailsPageElements.xpath('//div[@id="shoot-featured-image"]//h4')[0].text_content().strip(), siteNum)
curID = PAutils.Encode(sceneURL)
modelURL = detailsPageElements.xpath('//tr[contains(.,"Scene")]//a/@href')[0]
if not modelURL == prevModelURL:
req = PAutils.HTTPRequest(modelURL)
actorPageElements = HTML.ElementFromString(req.text)
prevModelURL = modelURL
date = ''
for scene in actorPageElements.xpath('//article[@class="card card-shoot"]'):
if titleNoFormatting.lower() == scene.xpath('.//h2')[0].text_content().strip().lower() and subSite.lower() == scene.xpath('.//h3/text()')[0].strip().lower():
date = scene.xpath('.//span')[0].text_content().strip()
break
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat() if searchData.date else ''
displayDate = releaseDate if date else ''
if searchData.date and displayDate:
score = 100 - Util.LevenshteinDistance(searchData.date, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
results.Append(MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate), name='%s [Abby Winters/%s] %s' % (titleNoFormatting, subSite, displayDate), score=score, lang=lang))
return results
def search(results, encodedTitle, title, searchTitle, siteNum, lang,
searchDate):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + searchTitle.replace(' ', '-').lower() + '/'
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
if ('/video/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
detailsPageElements = None
try:
detailsPageElements = HTML.ElementFromURL(sceneURL)
except:
pass
if detailsPageElements:
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath(
'//div[@class="single-part-details"]//h2')[0].text_content(
).strip()
date = detailsPageElements.xpath(
'//div[@class="video-info-left-icon"]//span[3]/text()'
)[0].strip()
releaseDate = datetime.strptime(date, '%d%b,%Y')
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]' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum)),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchData.encoded = searchData.title.lower().replace(' ', '-')
directURL = PAsearchSites.getSearchSearchURL(siteNum).replace('/search.php?query=', '/trailers/') + searchData.encoded + '.html'
directResults = [directURL]
req = PAutils.HTTPRequest(PAsearchSites.getSearchSearchURL(siteNum) + searchData.encoded)
searchResults = HTML.ElementFromString(req.text)
for searchResult in searchResults.xpath('//div[contains(@class, "item-video")]'):
sceneURL = searchResult.xpath('./div[1]//a/@href')[0]
time = searchResult.xpath('.//div[contains(@class, "time")]/text()')[0].strip()
if time.replace(':', '').isdigit():
if not sceneURL.startswith('http'):
sceneURL = 'http:' + sceneURL
directResults.append(sceneURL)
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if '/trailers/' in sceneURL and sceneURL not in searchResults:
directResults.append(sceneURL)
for sceneURL in directResults:
try:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath('//h1 | //h3')[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
date = detailsPageElements.xpath('//div[contains(@class, "videoInfo")]/p/text()')
if date:
releaseDate = parse(date[0].strip()).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat() if searchData.date 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))
except:
pass
return results
def search(results, lang, siteNum, searchData):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if '/session/' in sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = PAutils.parseTitle(
detailsPageElements.xpath('//h3[@class="mas_title"]')
[0].text_content().strip(), siteNum)
subSite = detailsPageElements.xpath('//title')[0].text_content().split(
'|')[1].strip().replace('.com', '')
curID = PAutils.Encode(sceneURL)
date = ' '.join(
detailsPageElements.xpath('//div[@class="lch"]/span')
[0].text_content().rsplit(',', 2)[1:]).strip()
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat() if searchData.date else ''
displayDate = releaseDate if date else ''
if searchData.date and displayDate:
score = 100 - Util.LevenshteinDistance(searchData.date,
releaseDate)
else:
score = 100 - Util.LevenshteinDistance(searchData.title.lower(),
titleNoFormatting.lower())
results.Append(
MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting, subSite, displayDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchResults = []
sceneID = searchData.title.split(' ', 1)[0]
if unicode(sceneID, 'UTF-8').isdigit():
searchData.title = searchData.title.replace(sceneID, '', 1).strip()
else:
sceneID = None
if sceneID:
searchResults.append(
PAsearchSites.getSearchSearchURL(siteNum) + sceneID)
if searchData.title:
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if '/video/' in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
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)
releaseDate = searchData.dateFormat() if searchData.date else ''
if sceneID and sceneID in sceneURL:
score = 100
else:
score = 100 - Util.LevenshteinDistance(searchData.title.lower(),
titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s]' %
(titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum)),
score=score,
lang=lang))
return results
def search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
directURL = searchTitle.replace(' ', '-').lower()
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
sceneURL = sceneURL.split('?', 1)[0]
sceneName = None
if ('/movies/' in sceneURL):
sceneName = sceneURL.split('/')[-1]
elif unicode(sceneURL.split('/')[-3]).isdigit():
sceneName = sceneURL.split('/')[-1]
if sceneName and sceneName not in searchResults:
searchResults.append(sceneName)
dbURL = getDBURL(PAsearchSites.getSearchBaseURL(siteNum))
for sceneName in searchResults:
for sceneType in ['videoscontent', 'moviescontent']:
detailsPageElements = getDataFromAPI(dbURL, sceneType, sceneName, siteNum)
if detailsPageElements:
break
if detailsPageElements:
curID = detailsPageElements['id']
titleNoFormatting = PAutils.parseTitle(detailsPageElements['title'], siteNum)
siteName = detailsPageElements['site']['name'] if 'site' in detailsPageElements else PAsearchSites.getSearchSiteName(siteNum)
if 'publishedDate' in detailsPageElements:
releaseDate = parse(detailsPageElements['publishedDate']).strftime('%Y-%m-%d')
else:
releaseDate = parse(searchDate).strftime('%Y-%m-%d') if searchDate else ''
displayDate = releaseDate if 'publishedDate' in detailsPageElements else ''
if 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|%s' % (curID, siteNum, releaseDate, sceneType), name='%s [%s] %s' % (titleNoFormatting, siteName, displayDate), score=score, lang=lang))
return results
def search(results, lang, siteNum, search):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum, lang='enes')
for sceneURL in googleResults:
sceneURL = sceneURL.replace('index.php/', '')
sceneURL = sceneURL.replace('es/', '')
if '/tags/' not in sceneURL and '/actr' not in sceneURL and '?pag' not in sceneURL and '/xvideos' not in sceneURL and '/tag/' not in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
if '/en/' in sceneURL:
searchResults.append(sceneURL.replace('en/', ''))
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
try:
if '/en/' in sceneURL:
language = 'English'
titleNoFormatting = PAutils.parseTitle(detailsPageElements.xpath('//title')[0].text_content().split('|')[0].split('-')[0].strip(), siteNum)
else:
language = 'Español'
titleNoFormatting = detailsPageElements.xpath('//title')[0].text_content().split('|')[0].split('-')[0].strip()
curID = PAutils.Encode(sceneURL)
date = detailsPageElements.xpath('//div[@class="released-views"]/span')[0].text_content().strip()
if date:
releaseDate = datetime.strptime(date, '%d/%m/%Y').strftime('%Y-%m-%d')
else:
releaseDate = parse(search['date']).strftime('%Y-%m-%d') if search['date'] else ''
displayDate = releaseDate if date else ''
if search['date'] and displayDate:
score = 100 - Util.LevenshteinDistance(search['date'], releaseDate)
else:
score = 100 - Util.LevenshteinDistance(search['title'].lower(), titleNoFormatting.lower())
results.Append(MetadataSearchResult(id='%s|%d' % (curID, siteNum), name='%s {%s} [%s] %s' % (titleNoFormatting, language, PAsearchSites.getSearchSiteName(siteNum), displayDate), score=score, lang=lang))
except:
pass
return results
def search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
sceneURL = sceneURL.replace('www.', '')
if ('trailers' in sceneURL
) and 'as3' not in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
subSite = detailsPageElements.xpath(
'//div[@class="about"]//h3')[0].text_content().replace(
'About', '').strip()
curID = PAutils.Encode(sceneURL)
date = ''
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = parse(searchDate).strftime(
'%Y-%m-%d') if searchDate else ''
displayDate = releaseDate if date else ''
if searchDate and displayDate:
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 [PervCity/%s]' %
(titleNoFormatting, subSite),
score=score,
lang=lang))
return results
def search(results, encodedTitle, 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:
req = PAutils.HTTPRequest(url)
detailsPageElements = HTML.ElementFromString(req.text)
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))
encodedTitle = searchTitle.replace(' ', '_')
req = PAutils.HTTPRequest(PAsearchSites.getSearchSearchURL(siteNum) + encodedTitle)
searchResults = HTML.ElementFromString(req.text)
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 search(results, lang, siteNum, searchData):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + searchData.title.replace(' ', '-').lower()
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/virtualreality/' in sceneURL and sceneURL not in searchResults
and '/virtualreality/list' not in sceneURL):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
if detailsPageElements:
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath(
'//div[contains(@class, "video-details")]//h1[1]'
)[0].text_content().strip()
date = detailsPageElements.xpath(
'//div[@class="stats-container"]//li[3]//span[2]'
)[0].text_content().strip()
releaseDate = parse(date).strftime('%Y-%m-%d')
if searchData.date and releaseDate:
score = 100 - Util.LevenshteinDistance(
searchData.date, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(
searchData.title.lower(), titleNoFormatting.lower())
results.Append(
MetadataSearchResult(
id='%s|%d' % (curID, siteNum),
name='%s [%s]' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum)),
score=score,
lang=lang))
return results
def search(results, encodedTitle, searchTitle, siteNum, lang, searchDate):
encodedTitle = searchTitle.replace(' ', '-')
searchResultsURLs = [
PAsearchSites.getSearchSearchURL(siteNum) + 'updates/' + encodedTitle +
'.html',
PAsearchSites.getSearchSearchURL(siteNum) + 'updates/' + encodedTitle +
'-.html',
PAsearchSites.getSearchSearchURL(siteNum) + 'dvds/' + encodedTitle +
'.html'
]
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
if sceneURL not in searchResultsURLs:
if (('/updates/' in sceneURL or '/dvds/' in sceneURL
or '/scenes/' in sceneURL) and '/tour_ns/'
in sceneURL) and sceneURL not in searchResultsURLs:
searchResultsURLs.append(sceneURL)
for sceneURL in searchResultsURLs:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
searchResult = HTML.ElementFromString(req.text)
titleNoFormatting = searchResult.xpath(
'(//div[@class="trailerVideos clear"] | //div[@class="dvdSections clear"])/div[1]'
)[0].text_content().replace('DVDS /', '').strip()
curID = PAutils.Encode(sceneURL)
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 [New Sensations]' % titleNoFormatting,
score=score,
lang=lang))
return results
def search(results, lang, siteNum, search):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum)
for sceneURL in googleResults:
if ('/tour1/' in sceneURL and sceneURL.endswith('.html') and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath('//h1')[0].text_content().strip()
releaseDate = search['date'] if search['date'] else ''
score = 100 - Util.LevenshteinDistance(search['title'].lower(), titleNoFormatting.lower())
results.Append(MetadataSearchResult(id='%s|%d|%s' % (curID, siteNum, releaseDate), name='%s [%s]' % (titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum)), score=score, lang=lang))
return results
def search(results, lang, siteNum, search):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + search['title'].replace(' ', '-').lower() + '.html'
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum)
for sceneURL in googleResults:
if ('/updates/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
if detailsPageElements:
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath(
'//title')[0].text_content().strip()
date = detailsPageElements.xpath(
'//span[(contains(@class, "update_date"))]')[0].text_content(
).strip()
releaseDate = datetime.strptime(date,
'%m/%d/%Y').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' % (curID, siteNum),
name='%s [%s]' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum)),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
sceneID = None
parts = searchData.title.split()
if unicode(parts[0], 'UTF-8').isdigit():
sceneID = parts[0]
searchData.title = searchData.title.replace(sceneID, '', 1).strip()
searchResults = []
if sceneID:
directURL = PAsearchSites.getSearchSearchURL(siteNum) + sceneID
searchResults.append(directURL)
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
sceneURL = re.sub(r'www\.', '', sceneURL)
sceneURL = re.sub(r'/(?<=\d/).*', '', sceneURL)
if '/videos/' in sceneURL and '/page/' not in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
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('//div[@class="date"]')[0].text_content().strip()
try:
releaseDate = parse(date).strftime('%Y-%m-%d')
except:
releaseDate = ''
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' % (curID, siteNum), name='%s [%s] %s' % (titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum), releaseDate), score=score, lang=lang))
return results
def search(results, lang, siteNum, searchData):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + searchData.title.replace(' ', '-').lower()
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/scene/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
if detailsPageElements:
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
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()
releaseDate = parse(date).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' % (curID, siteNum),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum), releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchData.encoded = searchData.title.replace(' ', '-')
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/updates/' in sceneURL and '/tour_hwxxx/'
in sceneURL) and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//div[@class="trailerInfo"]/h2')[0].text_content().strip()
date = detailsPageElements.xpath(
'//div[@class="trailerInfo"]/div[@class="released2 trailerStarr"]'
)[0].text_content().strip().split(',')[0]
releaseDate = parse(date).strftime('%Y-%m-%d')
curID = PAutils.Encode(sceneURL)
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' % (curID, siteNum),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum), releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchData.encoded = searchData.title.lower().replace(' ', '-')
directURL = PAsearchSites.getSearchSearchURL(siteNum) + searchData.encoded + '.html'
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if '/trailers/' in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
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)
score = 100 - Util.LevenshteinDistance(searchData.title, titleNoFormatting)
results.Append(MetadataSearchResult(id='%s|%d' % (curID, siteNum), name='%s [%s]' % (titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum)), score=score, lang=lang))
return results
def search(results, lang, siteNum, searchData):
directURL = PAsearchSites.getSearchSearchURL(siteNum) + searchData.title.replace(' ', '-').lower() + '.html'
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if ('/video/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath('//meta[@property="og:title"]/@content')[0].strip()
score = 100 - Util.LevenshteinDistance(searchData.title.lower(), titleNoFormatting.lower())
results.Append(MetadataSearchResult(id='%s|%d' % (curID, siteNum), name='%s [%s]' % (titleNoFormatting, PAsearchSites.getSearchSiteName(siteNum)), score=score, lang=lang))
return results
def search(results, lang, siteNum, search):
search['encoded'] = search['title'].lower().replace(' ', '-')
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + search['encoded'] + '.html'
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum)
for sceneURL in googleResults:
if '/trailers/' in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if not req.text == 'Page not found':
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//meta[@name="twitter:title"]/@content')[0].strip()
curID = PAutils.Encode(sceneURL)
date = detailsPageElements.xpath(
'//div[@class="trailer topSpace"]/div[2]/p')[0].text_content(
).split('\\')[1].strip()
releaseDate = parse(date).strftime('%Y-%m-%d')
if search['date']:
score = 100 - Util.LevenshteinDistance(search['date'],
releaseDate)
else:
score = 100 - Util.LevenshteinDistance(search['title'],
titleNoFormatting)
results.Append(
MetadataSearchResult(id='%s|%d' % (curID, siteNum),
name='%s [GirlsOutWest] %s' %
(titleNoFormatting, releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, search):
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + search['title'].replace(' ', '-').lower()
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum)
for sceneURL in googleResults:
if ('/scenes/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
curID = PAutils.Encode(sceneURL)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
releaseDate = parse(
detailsPageElements.xpath('//time/@datetime')[0]).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' % (curID, siteNum),
name='%s [%s] %s' %
(titleNoFormatting,
PAsearchSites.getSearchSiteName(siteNum), releaseDate),
score=score,
lang=lang))
return results
def search(results, lang, siteNum, search):
searchResults = []
directURL = PAsearchSites.getSearchSearchURL(
siteNum) + search['title'].lower().replace(' ', '-')
if unicode(directURL[-1], 'UTF-8').isdigit() and directURL[-2] == '-':
directURL = '%s-%s' % (directURL[:-1], directURL[-1])
searchResults.append(directURL)
googleResults = PAutils.getFromGoogleSearch(search['title'], siteNum)
for sceneURL in googleResults:
if ('/video/' in sceneURL and sceneURL not in searchResults):
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if 'signup.' not in req.url:
detailsPageElements = HTML.ElementFromString(req.text)
titleNoFormatting = detailsPageElements.xpath(
'//h1')[0].text_content().strip()
curID = PAutils.Encode(sceneURL)
releaseDate = parse(
search['date']).strftime('%Y-%m-%d') if search['date'] 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))
return results
def search(results, encodedTitle, title, searchTitle, siteNum, lang,
searchByDateActor, searchDate, searchSiteID):
if searchSiteID != 9999:
siteNum = searchSiteID
directURL = '%s%s.html' % (PAsearchSites.getSearchSearchURL(siteNum),
searchTitle.lower().replace(' ', '-'))
searchResults = [directURL]
googleResults = PAutils.getFromGoogleSearch(searchTitle, siteNum)
for sceneURL in googleResults:
sceneURL = sceneURL.lower()
if ('/trailers/' in sceneURL) and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
data = PAutils.HTTPRequest(sceneURL)
if data and data != 'Page not found':
searchResult = HTML.ElementFromString(data)
titleNoFormatting = searchResult.xpath(
'//h2[@class="title"]/text()')[0]
curID = String.Encode(sceneURL)
releaseDate = parse(searchDate) if searchDate else ''
score = 100 - Util.LevenshteinDistance(searchTitle,
titleNoFormatting)
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [Girls Rimming]' % titleNoFormatting,
score=score,
lang=lang))
return results
def search(results, lang, siteNum, searchData):
searchResults = []
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for sceneURL in googleResults:
if '/trailers/' in sceneURL and sceneURL not in searchResults:
searchResults.append(sceneURL)
for sceneURL in searchResults:
req = PAutils.HTTPRequest(sceneURL)
if req.ok:
detailsPageElements = HTML.ElementFromString(req.text)
curID = PAutils.Encode(sceneURL)
titleNoFormatting = PAutils.parseTitle(detailsPageElements.xpath('//div[@class="trailer_videoinfo"]//h3')[0].text_content().strip(), siteNum)
releaseDate = None
dateNode = detailsPageElements.xpath('//div[@class="trailer_videoinfo"]//p[contains(., "Added")]')
if dateNode:
date = None
try:
date = dateNode[0].text_content().split('-')[1].strip()
except:
pass
if date:
releaseDate = parse(date).strftime('%Y-%m-%d')
if searchData.date and releaseDate:
score = 100 - Util.LevenshteinDistance(searchData.date, releaseDate)
else:
score = 100 - Util.LevenshteinDistance(searchData.title.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 search(results, lang, siteNum, searchData):
searchResults = []
siteResults = []
temp = []
count = 0
sceneID = None
parts = searchData.title.split()
if unicode(parts[0], 'UTF-8').isdigit():
sceneID = parts[0]
if int(sceneID) > 100:
searchData.title = searchData.title.replace(sceneID, '', 1).strip()
movieURL = '%s/movies/%s' % (
PAsearchSites.getSearchBaseURL(siteNum), sceneID)
searchResults.append(movieURL)
searchData.encoded = searchData.title.replace(' ', '+')
searchURL = '%s%s' % (PAsearchSites.getSearchSearchURL(siteNum),
searchData.encoded)
req = PAutils.HTTPRequest(searchURL,
headers={'Referer': 'http://www.data18.com'})
searchPageElements = HTML.ElementFromString(req.text)
for searchResult in searchPageElements.xpath(
'//a[contains(@href, "movies")]//parent::div[contains(@style, "float: left; padding")]'
):
movieURL = searchResult.xpath('.//*[img]/@href')[0]
urlID = re.sub(r'.*/', '', movieURL)
if movieURL not in searchResults:
titleNoFormatting = PAutils.parseTitle(
searchResult.xpath('.//*[contains(@href, "movies")]')
[1].text_content(), siteNum)
curID = PAutils.Encode(movieURL)
siteResults.append(movieURL)
date = searchResult.text
if date and not date == 'unknown':
try:
releaseDate = datetime.strptime(
date, '%Y%m%d').strftime('%Y-%m-%d')
except:
releaseDate = ''
else:
releaseDate = searchData.dateFormat(
) if searchData.date else ''
displayDate = releaseDate if date else ''
if sceneID == urlID:
score = 100
elif searchData.date and displayDate:
score = 80 - Util.LevenshteinDistance(searchData.date,
releaseDate)
else:
score = 80 - Util.LevenshteinDistance(
searchData.title.lower(), titleNoFormatting.lower())
if score > 70:
sceneURL = PAutils.Decode(curID)
req = PAutils.HTTPRequest(sceneURL)
detailsPageElements = HTML.ElementFromString(req.text)
# Studio
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Network")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Studio")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Site")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
studio = ''
if score == 80:
count += 1
temp.append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting, studio, displayDate),
score=score,
lang=lang))
else:
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting, studio, displayDate),
score=score,
lang=lang))
#Split Scenes
sceneCount = detailsPageElements.xpath(
'//text()[contains(., "Related Scenes")]')[0][-2]
if sceneCount.isdigit():
sceneCount = int(sceneCount)
else:
sceneCount = 0
for sceneNum in range(1, sceneCount + 1):
section = "Scene " + str(sceneNum)
scene = PAutils.Encode(
detailsPageElements.xpath(
'//a[contains(., "%s")]/@href' % (section))[0])
if score == 80:
count += 1
temp.append(
MetadataSearchResult(id='%s|%d|%s|%s|%d' %
(scene, siteNum, releaseDate,
titleNoFormatting, sceneNum),
name='%s [%s][%s] %s' %
(titleNoFormatting, section,
studio, displayDate),
score=score,
lang=lang))
else:
results.Append(
MetadataSearchResult(id='%s|%d|%s|%s|%d' %
(scene, siteNum, releaseDate,
titleNoFormatting, sceneNum),
name='%s [%s][%s] %s' %
(titleNoFormatting, section,
studio, displayDate),
score=score,
lang=lang))
else:
if score == 80:
count += 1
temp.append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s %s' % (titleNoFormatting, displayDate),
score=score,
lang=lang))
else:
results.Append(
MetadataSearchResult(
id='%s|%d|%s' % (curID, siteNum, releaseDate),
name='%s %s' % (titleNoFormatting, displayDate),
score=score,
lang=lang))
googleResults = PAutils.getFromGoogleSearch(searchData.title, siteNum)
for movieURL in googleResults:
if ('/movies/' in movieURL and '.html' not in movieURL
and movieURL not in searchResults
and movieURL not in siteResults):
searchResults.append(movieURL)
for movieURL in searchResults:
req = PAutils.HTTPRequest(movieURL)
detailsPageElements = HTML.ElementFromString(req.text)
urlID = re.sub(r'.*/', '', movieURL)
try:
siteName = detailsPageElements.xpath(
'//i[contains(., "Network")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
siteName = detailsPageElements.xpath(
'//i[contains(., "Studio")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
siteName = detailsPageElements.xpath(
'//i[contains(., "Site")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
siteName = ''
titleNoFormatting = PAutils.parseTitle(
detailsPageElements.xpath('//h1')[0].text_content(), siteNum)
curID = PAutils.Encode(movieURL)
try:
date = detailsPageElements.xpath('//p[contains(., "Release")]')[
0].text_content().text_content().split(':')[2].strip()
except:
date = ''
if date and not date == 'unknown':
releaseDate = parse(date).strftime('%Y-%m-%d')
else:
releaseDate = searchData.dateFormat() if searchData.date else ''
displayDate = releaseDate if date else ''
if sceneID == urlID:
score = 100
elif searchData.date and displayDate:
score = 80 - Util.LevenshteinDistance(searchData.date, releaseDate)
else:
score = 80 - Util.LevenshteinDistance(searchData.title.lower(),
titleNoFormatting.lower())
# Studio
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Network")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Studio")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
try:
studio = detailsPageElements.xpath(
'//i[contains(., "Site")]//preceding-sibling::a[1]'
)[0].text_content().strip()
except:
studio = ''
if score == 80:
count += 1
temp.append(
MetadataSearchResult(id='%s|%d|%s' %
(curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting, studio, displayDate),
score=score,
lang=lang))
else:
results.Append(
MetadataSearchResult(id='%s|%d|%s' %
(curID, siteNum, releaseDate),
name='%s [%s] %s' %
(titleNoFormatting, studio, displayDate),
score=score,
lang=lang))
#Split Scenes
sceneCount = detailsPageElements.xpath(
'//text()[contains(., "Related Scenes")]')[0][-2]
if sceneCount.isdigit():
sceneCount = int(sceneCount)
else:
sceneCount = 0
for sceneNum in range(1, sceneCount + 1):
section = "Scene " + str(sceneNum)
scene = PAutils.Encode(
detailsPageElements.xpath('//a[contains(., "%s")]/@href' %
(section))[0])
if score == 80:
count += 1
temp.append(
MetadataSearchResult(
id='%s|%d|%s|%s|%d' % (scene, siteNum, releaseDate,
titleNoFormatting, sceneNum),
name='%s [%s][%s] %s' %
(titleNoFormatting, section, studio, displayDate),
score=score,
lang=lang))
else:
results.Append(
MetadataSearchResult(
id='%s|%d|%s|%s|%d' % (scene, siteNum, releaseDate,
titleNoFormatting, sceneNum),
name='%s [%s][%s] %s' %
(titleNoFormatting, section, studio, displayDate),
score=score,
lang=lang))
for result in temp:
if count > 1 and result.score == 80:
results.Append(
MetadataSearchResult(id=result.id,
name=result.name,
score=79,
lang=lang))
else:
results.Append(
MetadataSearchResult(id=result.id,
name=result.name,
score=result.score,
lang=lang))
return results
