Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-24 01:14:32 +01:00
Code Issues Releases Wiki Activity

added test data

Browse Source
This commit is contained in:
Thomas Tsiakalakis 2019-02-21 18:22:42 +01:00
parent a0dcbe9241
commit f278dad081
1 changed files with 22 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/intldropout.py
View File

@ -37,17 +37,15 @@ class IntlDropoutIE(VHXEmbedIE):
_VALID_URL = r'https://intl\.dropout\.tv/(?P<id>.+)' _VALID_URL = r'https://intl\.dropout\.tv/(?P<id>.+)'
_TEST = { _TEST = {
'url': 'https://intl.dropout.tv/um-actually/season:1/videos/c-3po-s-origins-hp-lovecraft-the-food-album-with-weird-al-yankovic', 'url': 'https://intl.dropout.tv/um-actually/season:1/videos/c-3po-s-origins-hp-lovecraft-the-food-album-with-weird-al-yankovic',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': 'e6cbf01c24ad9fb8281c23357416ec97',
'info_dict': { 'info_dict': {
'id': '42', 'id': '397785',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Video title goes here', 'title': "C-3PO's Origins, HP Lovecraft, the Food Album (with Weird Al Yankovic)",
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
# TODO more properties, either as: 'description': 'Caldwell Tanner, Siobhan Thompson, and Nate Dern inspect guns and review the Diagon Alley bar scene.',
# * A value 'upload_date': '20181206',
# * MD5 checksum; start the string with md5: 'timestamp': 1544117975,
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
} }
@ -64,7 +62,8 @@ class IntlDropoutIE(VHXEmbedIE):
login_page = self._download_webpage( login_page = self._download_webpage(
self._LOGIN_URL, None, self._LOGIN_URL, None,
note='Downloading login page', note='Downloading login page',
errnote='unable to fetch login page', fatal=False errnote='unable to fetch login page', fatal=False,
expected_status=200
) )
if login_page is False: if login_page is False:
@ -82,18 +81,27 @@ class IntlDropoutIE(VHXEmbedIE):
self._LOGIN_URL, urlencode_postdata(login_form)) self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.add_header('Content-Type', 'application/x-www-form-urlencoded')
try: try:
self._download_webpage(request, None, 'Logging in') self._download_webpage(request, None, 'Logging in', expected_status=302)
except Exception: except Exception:
print('error') raise ExtractorError(
'Unable to login',
expected=True)
def _real_extract(self, url): def _real_extract(self, url):
webpage = self._download_webpage(url, None)
try: try:
video = self._html_search_regex(r'<iframe[^>]+"(?P<embed>https://embed.vhx.tv/videos/[0-9]+[^"]*)"[^>]*>', webpage, 'embed') webpage = self._download_webpage(url, None, expected_status=200)
except Exception:
raise ExtractorError(
'Unable to fetch page',
expected=True)
try:
video = self._html_search_regex(r'<iframe[^>]*"(?P<embed>https://embed.vhx.tv/videos/[0-9]+[^"]*)"[^>]*>', webpage, 'embed')
except RegexNotFoundError: except RegexNotFoundError:
items = re.findall(r'<a href="(?P<url>https://intl.dropout.tv/videos/[^"]+)"', webpage) items = re.findall(r'<a href="(?P<url>https://intl.dropout.tv/videos/[^"]+)"', webpage)
playlist_id = self._search_regex(r'https://intl.dropout.tv/(?P<id>.+)', url, 'id') playlist_id = self._search_regex(r'https://intl.dropout.tv/(?P<id>.+)', url, 'id')
playlist_title = self._html_search_regex(r'<h1 class="[^"]*collection-title[^"]*"[^>]*>(?P<title>[^<]+)<', webpage, 'title') playlist_title = self._html_search_regex(r'<h1 class="[^"]*collection-title[^"]*"[^>]*>(?P<title>[^<]+)<', webpage, 'title')
return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=playlist_title) return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=playlist_title)
return self.url_result(video) video_id = self._search_regex(r'https://embed.vhx.tv/videos/(?P<id>[0-9]+)', video, 'id')
video_title = self._html_search_regex(r'<h1 class="[^"]*video-title[^"]*"[^>]*>(<strong>)?(?P<title>[^<]+)<', webpage, 'title')
return self.url_result(video, video_id=video_id, video_title=video_title)