[smotri] Simplify

This commit is contained in:
Philipp Hagemeister 2013-12-02 17:08:17 +01:00
parent 25939ffe56
commit aaebed13a8
2 changed files with 54 additions and 40 deletions

View File

@ -364,7 +364,8 @@ class InfoExtractor(object):
if display_name is None: if display_name is None:
display_name = name display_name = name
return self._html_search_regex( return self._html_search_regex(
r'''(?ix)<meta(?=[^>]+(?:name|property)=["\']%s["\']) r'''(?ix)<meta
(?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
[^>]+content=["\']([^"\']+)["\']''' % re.escape(name), [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
html, display_name, fatal=False) html, display_name, fatal=False)

View File

@ -14,46 +14,49 @@ from ..utils import (
class SmotriIE(InfoExtractor): class SmotriIE(InfoExtractor):
IE_DESC = u'Smotri.com' IE_DESC = u'Smotri.com'
IE_NAME = u'smotri' IE_NAME = u'smotri'
_VALID_URL = r'^(?:http://)?(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))' _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
_TESTS = [ _TESTS = [
# real video id 2610366 # real video id 2610366
{ {
u'url': u'http://smotri.com/video/view/?id=v261036632ab', u'url': u'http://smotri.com/video/view/?id=v261036632ab',
u'file': u'v261036632ab.mp4', u'file': u'v261036632ab.mp4',
u'md5': u'46a72e83a6ad8862b64fa6953fa93f8a', u'md5': u'2a7b08249e6f5636557579c368040eb9',
u'info_dict': { u'info_dict': {
u'title': u'катастрофа с камер видеонаблюдения', u'title': u'катастрофа с камер видеонаблюдения',
u'uploader': u'rbc2008', u'uploader': u'rbc2008',
u'uploader_id': u'rbc08', u'uploader_id': u'rbc08',
u'upload_date': u'20131118', u'upload_date': u'20131118',
u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg' u'description': u'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
}, },
}, },
# real video id 57591 # real video id 57591
{ {
u'url': u'http://smotri.com/video/view/?id=v57591cb20', u'url': u'http://smotri.com/video/view/?id=v57591cb20',
u'file': u'v57591cb20.flv', u'file': u'v57591cb20.flv',
u'md5': u'9eae59f6dda7087bf39a140e2fff5757', u'md5': u'830266dfc21f077eac5afd1883091bcd',
u'info_dict': { u'info_dict': {
u'title': u'test', u'title': u'test',
u'uploader': u'Support Photofile@photofile', u'uploader': u'Support Photofile@photofile',
u'uploader_id': u'support-photofile', u'uploader_id': u'support-photofile',
u'upload_date': u'20070704', u'upload_date': u'20070704',
u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg' u'description': u'test, видео test',
u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
}, },
}, },
# video-password # video-password
{ {
u'url': u'http://smotri.com/video/view/?id=v1390466a13c', u'url': u'http://smotri.com/video/view/?id=v1390466a13c',
u'file': u'v1390466a13c.mp4', u'file': u'v1390466a13c.mp4',
u'md5': u'fe4dd9357558d5ee3c8fc0ef0d39de66', u'md5': u'f6331cef33cad65a0815ee482a54440b',
u'info_dict': { u'info_dict': {
u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
u'uploader': u'timoxa40', u'uploader': u'timoxa40',
u'uploader_id': u'timoxa40', u'uploader_id': u'timoxa40',
u'upload_date': u'20100404', u'upload_date': u'20100404',
u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg' u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
u'description': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
}, },
u'params': { u'params': {
u'videopassword': u'qwerty', u'videopassword': u'qwerty',
@ -63,14 +66,15 @@ class SmotriIE(InfoExtractor):
{ {
u'url': u'http://smotri.com/video/view/?id=v15408898bcf', u'url': u'http://smotri.com/video/view/?id=v15408898bcf',
u'file': u'v15408898bcf.flv', u'file': u'v15408898bcf.flv',
u'md5': u'c66a5d61379ac6fde06f07eebe436316', u'md5': u'91e909c9f0521adf5ee86fbe073aad70',
u'info_dict': { u'info_dict': {
u'title': u'этот ролик не покажут по ТВ', u'title': u'этот ролик не покажут по ТВ',
u'uploader': u'zzxxx', u'uploader': u'zzxxx',
u'uploader_id': u'ueggb', u'uploader_id': u'ueggb',
u'upload_date': u'20101001', u'upload_date': u'20101001',
u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg', u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
u'age_limit': 18 u'age_limit': 18,
u'description': u'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
}, },
u'params': { u'params': {
u'videopassword': u'333' u'videopassword': u'333'
@ -89,6 +93,7 @@ class SmotriIE(InfoExtractor):
return self._html_search_regex( return self._html_search_regex(
r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name), r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
html, display_name, fatal=False) html, display_name, fatal=False)
return self._html_search_meta(name, html, display_name)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -108,7 +113,7 @@ class SmotriIE(InfoExtractor):
video_password = self._downloader.params.get('videopassword', None) video_password = self._downloader.params.get('videopassword', None)
if not video_password: if not video_password:
raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True) raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True)
video_json_url += '&md5pass=%s' % hashlib.md5(video_password).hexdigest() video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)') video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)')
video_json = json.loads(video_json_page) video_json = json.loads(video_json_page)
status = video_json['status'] status = video_json['status']
@ -120,7 +125,6 @@ class SmotriIE(InfoExtractor):
# Extract the URL of the video # Extract the URL of the video
video_url = video_json['file_data'] video_url = video_json['file_data']
video_ext = determine_ext(video_url)
# Video JSON does not provide enough meta data # Video JSON does not provide enough meta data
# We will extract some from the video web page instead # We will extract some from the video web page instead
@ -131,7 +135,7 @@ class SmotriIE(InfoExtractor):
if re.search(u'EroConfirmText">', video_page) is not None: if re.search(u'EroConfirmText">', video_page) is not None:
self.report_age_confirmation() self.report_age_confirmation()
confirm_string = self._html_search_regex( confirm_string = self._html_search_regex(
ur'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id, r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
video_page, u'confirm string') video_page, u'confirm string')
confirm_url = video_page_url + '&confirm=%s' % confirm_string confirm_url = video_page_url + '&confirm=%s' % confirm_string
video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)') video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)')
@ -145,6 +149,12 @@ class SmotriIE(InfoExtractor):
video_title = video_url.rsplit('/', 1)[-1] video_title = video_url.rsplit('/', 1)[-1]
video_description = self._search_meta(u'description', video_page) video_description = self._search_meta(u'description', video_page)
END_TEXT = u' на сайте Smotri.com'
if video_description.endswith(END_TEXT):
video_description = video_description[:-len(END_TEXT)]
START_TEXT = u'Смотреть онлайн ролик '
if video_description.startswith(START_TEXT):
video_description = video_description[len(START_TEXT):]
video_thumbnail = self._search_meta(u'thumbnail', video_page) video_thumbnail = self._search_meta(u'thumbnail', video_page)
upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date') upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date')
@ -170,22 +180,21 @@ class SmotriIE(InfoExtractor):
) )
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
ur'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>', u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL) video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
video_uploader_id = self._html_search_regex( video_uploader_id = self._html_search_regex(
ur'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\(.*?\'([^\']+)\'\);">', u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL) video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
video_view_count = self._html_search_regex( video_view_count = self._html_search_regex(
ur'Общее количество просмотров.*?<span class="Number">(\d+)</span>', u'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': video_title, 'title': video_title,
'ext': video_ext,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'description': video_description, 'description': video_description,
'uploader': video_uploader, 'uploader': video_uploader,
@ -197,10 +206,11 @@ class SmotriIE(InfoExtractor):
'video_page_url': video_page_url 'video_page_url': video_page_url
} }
class SmotriCommunityIE(InfoExtractor): class SmotriCommunityIE(InfoExtractor):
IE_DESC = u'Smotri.com community videos' IE_DESC = u'Smotri.com community videos'
IE_NAME = u'smotri:community' IE_NAME = u'smotri:community'
_VALID_URL = r'^(?:http://)?(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -212,18 +222,20 @@ class SmotriCommunityIE(InfoExtractor):
entries = [self.url_result(video_url.text, 'Smotri') entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')] for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text
community_title = self._html_search_regex( community_title = self._html_search_regex(
ur'^Видео сообщества "([^"]+)"$', rss.find('./channel/description').text, u'community title') u'^Видео сообщества "([^"]+)"$', description_text, u'community title')
return self.playlist_result(entries, community_id, community_title) return self.playlist_result(entries, community_id, community_title)
class SmotriUserIE(InfoExtractor): class SmotriUserIE(InfoExtractor):
IE_DESC = u'Smotri.com user videos' IE_DESC = u'Smotri.com user videos'
IE_NAME = u'smotri:user' IE_NAME = u'smotri:user'
_VALID_URL = r'^(?:http://)?(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url); mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('userid') user_id = mobj.group('userid')
url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
@ -232,8 +244,9 @@ class SmotriUserIE(InfoExtractor):
entries = [self.url_result(video_url.text, 'Smotri') entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')] for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text
user_nickname = self._html_search_regex( user_nickname = self._html_search_regex(
ur'^Видео режиссера (.*)$', rss.find('./channel/description').text, u'user nickname') u'^Видео режиссера (.*)$', description_text,
u'user nickname')
return self.playlist_result(entries, user_id, user_nickname) return self.playlist_result(entries, user_id, user_nickname)