github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[smotri] Modernize, make more robust and fix tests

Browse source
This commit is contained in:
Sergey M․ 2016-07-24 18:38:18 +07:00
parent 8fdc538b46
commit e8be2943a7
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 50 additions and 49 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

99
youtube_dl/extractor/smotri.py
View file

@ -13,20 +13,21 @@
sanitized_Request, sanitized_Request,
unified_strdate, unified_strdate,
urlencode_postdata, urlencode_postdata,
xpath_text,
) )
class SmotriIE(InfoExtractor): class SmotriIE(InfoExtractor):
IE_DESC = 'Smotri.com' IE_DESC = 'Smotri.com'
IE_NAME = 'smotri' IE_NAME = 'smotri'
_VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' _VALID_URL = r'https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
_NETRC_MACHINE = 'smotri' _NETRC_MACHINE = 'smotri'
_TESTS = [ _TESTS = [
# real video id 2610366 # real video id 2610366
{ {
'url': 'http://smotri.com/video/view/?id=v261036632ab', 'url': 'http://smotri.com/video/view/?id=v261036632ab',
'md5': '2a7b08249e6f5636557579c368040eb9', 'md5': '02c0dfab2102984e9c5bb585cc7cc321',
'info_dict': { 'info_dict': {
'id': 'v261036632ab', 'id': 'v261036632ab',
'ext': 'mp4', 'ext': 'mp4',
@ -174,11 +175,11 @@ def _real_extract(self, url):
if video_password: if video_password:
video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest() video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
request = sanitized_Request( video = self._download_json(
'http://smotri.com/video/view/url/bot/', urlencode_postdata(video_form)) 'http://smotri.com/video/view/url/bot/',
request.add_header('Content-Type', 'application/x-www-form-urlencoded') video_id, 'Downloading video JSON',
data=urlencode_postdata(video_form),
video = self._download_json(request, video_id, 'Downloading video JSON') headers={'Content-Type': 'application/x-www-form-urlencoded'})
video_url = video.get('_vidURL') or video.get('_vidURL_mp4') video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
@ -196,11 +197,11 @@ def _real_extract(self, url):
raise ExtractorError(msg, expected=True) raise ExtractorError(msg, expected=True)
title = video['title'] title = video['title']
thumbnail = video['_imgURL'] thumbnail = video.get('_imgURL')
upload_date = unified_strdate(video['added']) upload_date = unified_strdate(video.get('added'))
uploader = video['userNick'] uploader = video.get('userNick')
uploader_id = video['userLogin'] uploader_id = video.get('userLogin')
duration = int_or_none(video['duration']) duration = int_or_none(video.get('duration'))
# 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
@ -209,7 +210,7 @@ def _real_extract(self, url):
# Warning if video is unavailable # Warning if video is unavailable
warning = self._html_search_regex( warning = self._html_search_regex(
r'<div class="videoUnModer">(.*?)</div>', webpage, r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,
'warning message', default=None) 'warning message', default=None)
if warning is not None: if warning is not None:
self._downloader.report_warning( self._downloader.report_warning(
@ -217,20 +218,22 @@ def _real_extract(self, url):
(video_id, warning)) (video_id, warning))
# Adult content # Adult content
if re.search('EroConfirmText">', webpage) is not None: if 'EroConfirmText">' in webpage:
self.report_age_confirmation() self.report_age_confirmation()
confirm_string = self._html_search_regex( confirm_string = self._html_search_regex(
r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id, r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,
webpage, 'confirm string') webpage, 'confirm string')
confirm_url = webpage_url + '&confirm=%s' % confirm_string confirm_url = webpage_url + '&confirm=%s' % confirm_string
webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') webpage = self._download_webpage(
confirm_url, video_id,
'Downloading video page (age confirmed)')
adult_content = True adult_content = True
else: else:
adult_content = False adult_content = False
view_count = self._html_search_regex( view_count = self._html_search_regex(
'Общее количество просмотров.*?<span class="Number">(\\d+)</span>', r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL) webpage, 'view count', fatal=False)
return { return {
'id': video_id, 'id': video_id,
@ -249,37 +252,33 @@ def _real_extract(self, url):
class SmotriCommunityIE(InfoExtractor): class SmotriCommunityIE(InfoExtractor):
IE_DESC = 'Smotri.com community videos' IE_DESC = 'Smotri.com community videos'
IE_NAME = 'smotri:community' IE_NAME = 'smotri:community'
_VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' _VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'
_TEST = { _TEST = {
'url': 'http://smotri.com/community/video/kommuna', 'url': 'http://smotri.com/community/video/kommuna',
'info_dict': { 'info_dict': {
'id': 'kommuna', 'id': 'kommuna',
'title': 'КПРФ',
}, },
'playlist_mincount': 4, 'playlist_mincount': 4,
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) community_id = self._match_id(url)
community_id = mobj.group('communityid')
url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id rss = self._download_xml(
rss = self._download_xml(url, community_id, 'Downloading community RSS') 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
community_id, 'Downloading community RSS')
entries = [self.url_result(video_url.text, 'Smotri') entries = [
for video_url in rss.findall('./channel/item/link')] self.url_result(video_url.text, SmotriIE.ie_key())
for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text return self.playlist_result(entries, community_id)
community_title = self._html_search_regex(
'^Видео сообщества "([^"]+)"$', description_text, 'community title')
return self.playlist_result(entries, community_id, community_title)
class SmotriUserIE(InfoExtractor): class SmotriUserIE(InfoExtractor):
IE_DESC = 'Smotri.com user videos' IE_DESC = 'Smotri.com user videos'
IE_NAME = 'smotri:user' IE_NAME = 'smotri:user'
_VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' _VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://smotri.com/user/inspector', 'url': 'http://smotri.com/user/inspector',
'info_dict': { 'info_dict': {
@ -290,19 +289,19 @@ class SmotriUserIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) user_id = self._match_id(url)
user_id = mobj.group('userid')
url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id rss = self._download_xml(
rss = self._download_xml(url, user_id, 'Downloading user RSS') 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
user_id, 'Downloading user RSS')
entries = [self.url_result(video_url.text, 'Smotri') entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')] for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text description_text = xpath_text(rss, './channel/description') or ''
user_nickname = self._html_search_regex( user_nickname = self._search_regex(
'^Видео режиссера (.*)$', description_text, '^Видео режиссера (.+)$', description_text,
'user nickname') 'user nickname', fatal=False)
return self.playlist_result(entries, user_id, user_nickname) return self.playlist_result(entries, user_id, user_nickname)
@ -310,11 +309,11 @@ def _real_extract(self, url):
class SmotriBroadcastIE(InfoExtractor): class SmotriBroadcastIE(InfoExtractor):
IE_DESC = 'Smotri.com broadcasts' IE_DESC = 'Smotri.com broadcasts'
IE_NAME = 'smotri:broadcast' IE_NAME = 'smotri:broadcast'
_VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*' _VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
broadcast_id = mobj.group('broadcastid') broadcast_id = mobj.group('id')
broadcast_url = 'http://' + mobj.group('url') broadcast_url = 'http://' + mobj.group('url')
broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page') broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
@ -328,7 +327,8 @@ def _real_extract(self, url):
(username, password) = self._get_login_info() (username, password) = self._get_login_info()
if username is None: if username is None:
self.raise_login_required('Erotic broadcasts allowed only for registered users') self.raise_login_required(
'Erotic broadcasts allowed only for registered users')
login_form = { login_form = {
'login-hint53': '1', 'login-hint53': '1',
@ -343,8 +343,9 @@ def _real_extract(self, url):
broadcast_page = self._download_webpage( broadcast_page = self._download_webpage(
request, broadcast_id, 'Logging in and confirming age') request, broadcast_id, 'Logging in and confirming age')
if re.search('>Неверный логин или пароль<', broadcast_page) is not None: if '>Неверный логин или пароль<' in broadcast_page:
raise ExtractorError('Unable to log in: bad username or password', expected=True) raise ExtractorError(
'Unable to log in: bad username or password', expected=True)
adult_content = True adult_content = True
else: else:
@ -383,11 +384,11 @@ def _real_extract(self, url):
broadcast_playpath = broadcast_json['_streamName'] broadcast_playpath = broadcast_json['_streamName']
broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL']) broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
broadcast_thumbnail = broadcast_json['_imgURL'] broadcast_thumbnail = broadcast_json.get('_imgURL')
broadcast_title = self._live_title(broadcast_json['title']) broadcast_title = self._live_title(broadcast_json['title'])
broadcast_description = broadcast_json['description'] broadcast_description = broadcast_json.get('description')
broadcaster_nick = broadcast_json['nick'] broadcaster_nick = broadcast_json.get('nick')
broadcaster_login = broadcast_json['login'] broadcaster_login = broadcast_json.get('login')
rtmp_conn = 'S:%s' % uuid.uuid4().hex rtmp_conn = 'S:%s' % uuid.uuid4().hex
except KeyError: except KeyError:
if protected_broadcast: if protected_broadcast: