def _get_title(self, html):
found_title = re.search(r'video_title":"(.*?)"', html)
if not found_title:
raise VideoParserError(
'Cannot find video title in pornhub.com video')
return found_title.group(1)
def get_video_stats(self, html, **kwargs):
document = self.etree.fromstring(html, self.parser)
title = document.xpath('//p[@class="title_substrate"]')[0].text
author = document.xpath(
'//span[@class="autor text_t"]/a[@href]')[0].text
uploaded_date = document.xpath(
'//span[@class="autor text_t"]//text()')[2].strip()
website = document.xpath('//span[@class="autor_web"]/a[@href]')[0]. \
attrib['href'].replace('/user_site_out.php?link=','')
website = urllib.unquote(website)
c_list = document.xpath('//div[@class="categories_list"]')[0]
categories = self._get_categories(html=self.tostring(c_list))
thumbnail = document.xpath('//video[@controls="controls"]/@poster')[0]
found_video_id = re.search(r'var video_id = "(.*?)"', html)
if not found_video_id:
raise VideoParserError('Could not find video id for drtuber video')
embed_code = '<iframe src=http://www.drtuber.com/embed/{video_id}' \
' width=608 height=454 frameborder=0 ' \
' scrolling=no></iframe>'.format(video_id=found_video_id.group(1))
return {
'author': author,
'categories': categories,
'embed_code': embed_code,
'thumbnail': thumbnail,
'uploaded_date': uploaded_date,
'title': title
}
def get_download_options(self, html, **kwargs):
regex = '"quality_720p":"(.*?)","quality_240p":"(.*?)","quality_180p":"(.*?)","quality_480p":"(.*?)",'
find_video_options = re.search(regex, html)
if find_video_options:
video_urls = []
password = self._get_title(html=html)
for i in xrange(1, 5):
encrypted_url = find_video_options.group(i)
if encrypted_url:
video_urls.append(
aes_decrypt_text(encrypted_url, password,
32).decode('utf-8'))
else:
video_urls.append(None)
return {
'720': video_urls[0],
'240': video_urls[1],
'180': video_urls[2],
'480': video_urls[3]
}
raise VideoParserError(
'Could not parse video download options for pornhub.com video')
def get_download_url(self, html, **kwargs):
found_flv_url = re.search(r'flv_url=(.*?)\&', html)
if not found_flv_url:
raise VideoParserError(
'Missing video download url for xvideos video')
return urllib.unquote_plus(found_flv_url.group(1))
def get_download_url(self, html, **kwargs):
found_download_url = re.search(r"__fileurl = '(.*?)';", html)
if not found_download_url:
raise VideoParserError('Could not find video download url for motherless' \
' video')
return found_download_url.group(1)
def get_download_url(self,html,**kwargs):
download_quality = kwargs.get('download_quality','default')
download_options = self._get_download_options(html=html)
if download_quality == 'default':
for quality in ['720','480','240','180']:
if download_options[quality]:
return download_options[quality]
raise VideoParserError('Could not find video download url for youporn.com video')
else:
if download_quality in download_options:
return download_options[download_quality]
raise VideoParserError('Invalid download quality, only available options are 720,480,240,180 or default')
def get_download_options(self,html):
find_video_options = re.search(r'{"hd":"(.*?)","480p":"(.*?)","mobile":"(.*?)"}\]}',html)
if find_video_options:
return {'720':None if not find_video_options.group(1) else find_video_options.group(1),
'480':None if not find_video_options.group(2) else find_video_options.group(2),
'240':None if not find_video_options.group(3) else find_video_options.group(3)}
raise VideoParserError('Could not parse video download options for redtube.com video')
def get_download_url(self, html, **kwargs):
document = self.etree.fromstring(html, self.parser)
download_url = document.xpath('//source[@src]/@src')
if not download_url:
raise VideoParserError(
'Could not find video download url for drtuber video')
return download_url[0]
def get_video_stats(self,html):
document = self.etree.fromstring(html,self.parser)
details = document.xpath('//div[@class="video-details"]')
details_doc = self.etree.fromstring(self.tostring(details[0]),self.parser)
has_user_link = details_doc.xpath('//span[@class="linkImitation"]')
if has_user_link:
author = has_user_link[0].text
else:
author = details_doc.xpath('//a[@rel="nofollow"]')[0].text
trs = details_doc.xpath('//table//tr')
title = document.xpath('//h1[@class="videoTitle"]')[0].text
categories = self._get_categories(html=self.tostring(trs[0]))
uploaded_date = self._get_uploaded_date(html=self.tostring(trs[1]))
views = self._get_views(html=self.tostring(trs[1]))
tags = self._get_tags(html=self.tostring(trs[2]))
ratings_percentage = document.xpath('//span[@class="percent-likes"]')[0].text
thumbnail = document.xpath('//meta[@property="og:image"]/@content')[0]
title = document.xpath('//h1[@class="videoTitle"]')[0].text
found_video_id = re.search(r'var iVideoID = (.*?);',html)
if not found_video_id:
raise VideoParserError('Could not find video id for redtube.com video')
embed_code = '<iframe src=http://www.embed.redtube.com?id={video_id}' \
'&bgcolor=000000 width=640 height=360 frameborder=0 ' \
'scrolling=no></iframe>'.format(video_id=found_video_id.group(1))
return {'author':author,
'tags':tags,
'categories':categories,
'embed_code':embed_code,
'thumbnail':thumbnail,
'uploaded_date':uploaded_date,
'ratings_percentage':ratings_percentage,
'title':title,
'views':views}
def get_download_options(self,html,**kwargs):
options = {'720':None,
'480':None,
'240':None,
'180':None}
doc = self.etree.fromstring(html,self.parser)
download_options = doc.xpath('//ul[@class="downloadList"]/li')
if not download_options:
raise VideoParserError('Could not find all the video download '\
'options for youporn.com video')
for li in download_options:
li_doc = self.etree.fromstring(self.tostring(li),self.parser)
link = li_doc.xpath('//a')[0]
for quality in ['/720p','/480p','/240p','/180p']:
if quality in link.attrib['href']:
options[quality.replace('/','').replace('p','')] = link.attrib['href']
break
return options
def get_video_stats(self, html):
document = self.etree.fromstring(html, self.parser)
thumbnail = document.xpath('//meta[@property="og:image"]/@content')[0]
author = document.xpath(
'//div[@class="usernameWrap clearfix"]//a[@class="bolded"]'
)[0].text
vid_row = document.xpath('//div[@class="video-info-row"]')
pornstars = self._get_porn_stars(self.tostring(vid_row[0]))
vid_show_less = document.xpath(
'//div[@class="video-info-row showLess"]')
categories = self._get_categories(html=self.tostring(vid_show_less[0]))
production = self._get_production_type(
html=self.tostring(vid_show_less[1]))
tags = self._get_tags(html=self.tostring(vid_show_less[2]))
uploaded_date = self._get_uploaded_date(
html=self.tostring(vid_show_less[3]))
stats_count = document.xpath('//div[@class="rating-info-container"]')
views, \
ratings_percentage, \
thumbs_up, \
thumbs_down = self._get_stats_count(html=self.tostring(stats_count[0]))
found_embed_code = re.search(r'"embedCode":"(.*?)\<\\/iframe>', html)
if not found_embed_code:
raise VideoParserError(
'Cannot get embed code for pornhub.com video')
embed_code = found_embed_code.group(1).replace('\\',
'').replace('"', '')
embed_code = '{e}</iframe>'.format(e=embed_code)
found_duration = re.search(r'"video_duration":"(.*?)",', html)
if not found_duration:
raise VideoParserError(
'Cannot find video duration in pornhub.com video')
duration_seconds = found_duration.group(1)
title = self._get_title(html=html)
download_options = self._get_download_options(html=html)
options = [download_options[download] for download in download_options]
return {
'author': author,
'tags': tags,
'categories': categories,
'embed_code': embed_code,
'thumbnail': thumbnail,
'uploaded_date': uploaded_date,
'production': production,
'pornstars': pornstars,
'ratings_percentage': ratings_percentage,
'thumbs_up': thumbs_up,
'thumbs_down': thumbs_down,
'title': title,
'views': views,
'duration_seconds': duration_seconds
}
def get_video_stats(self,html,**kwargs):
categories = []
tags = []
porn_stars = []
document = self.etree.fromstring(html,self.parser)
ratings = document.xpath('//div[@class="rating-count"]')[0].text.replace(' ratings)','').replace('(','')
ratings_percentage = document.xpath('//div[@class="rating-percentage"]')[0]
views = document.xpath('//div[@id="stats-views"]/text()')[0].replace(',','')
uploaded_date = document.xpath('//div[@id="stats-date"]/text()')[0]
title = document.xpath('//div[@class="container_15"]/h1[@class="grid_9"]')[0].text
get_video_details = document.xpath('//ul[@class="info-list-content"]//a')
for a in get_video_details:
get_type = re.match(r'/(.*?)/(.*?)/',a.attrib['href'],re.I|re.M)
if get_type:
#figure out the type of data, either tag, category or p**n star name
item_type = get_type.group(1)
if item_type == 'category':
#create a new YouPornCategory
categories.append(YouPornCategory(name=a.text,href=a.attrib['href']))
elif item_type == 'porntags':
#create a new YouPornTag
tags.append(YouPornTag(name=a.text,href=a.attrib['href']))
elif item_type == 'pornstar':
porn_stars.append((a.text,a.attrib['href']))
video_url = document.xpath('//link[@href]/@href')[0]
embed_code = "<iframe src={url}" \
" frameborder=0 height=481 width=608" \
" scrolling=no name=yp_embed_video>" \
"</iframe>".format(url=video_url)
author_name = document.xpath('//button[@data-name]//@data-name')[0]
author_href = document.xpath('//div[@class="author-block--line"]//a')[0].attrib['href']
author = YouPornAuthor(name=author_name,href=author_href)
has_zero_comments = document.xpath('//div[@id="tab-comments"]//h2[@class="psi"]')
if has_zero_comments:
if has_zero_comments[0].text == 'All Comments (0)':
total_comments = 0
else:
total_comments = document.xpath('//div[@id="tab-comments"]/ul/h2')[0] \
.text.replace('All Comments (','').replace(')','')
has_description = document.xpath('//div[@id="videoDescription"]')
if has_description:
description = document.xpath('//div[@id="videoDescription"]//p')[0].text
else:
description = ''
found_default_thumbnail = re.search(r'"default_thumbnail_url":"(.*?)"',html)
if not found_default_thumbnail:
raise VideoParserError('Cannot get thumbnail image for youporn video')
thumbnail = found_default_thumbnail.group(1)
found_duration_seconds = re.search(r'"duration_in_seconds":(.*?)',html)
if not found_duration_seconds:
raise VideoParserError('Cannot get duration in seconds for youporn video')
duration_seconds = found_duration_seconds.group(1)
found_duration_text = re.search(r'"duration_f":"(.*?)"',html)
if not found_duration_text:
raise VideoParserError('Cannot get duration text for youporn video')
duration_text = found_duration_text.group(1)
return {'total_comments':int(total_comments),
'author':author,
'porn_stars':porn_stars,
'categories':categories,
'tags':tags,
'uploaded_date':uploaded_date,
'views':views,
'ratings':ratings,
'ratings_percentage':ratings_percentage,
'title':title,
'thumbnail':thumbnail,
'duration_seconds':duration_seconds,
'duration_text':duration_text,
'description':description,
'embed_code':embed_code}