diff options
Diffstat (limited to 'youtube_dl')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 54 | ||||
| -rw-r--r-- | youtube_dl/extractor/myspass.py | 64 |
2 files changed, 65 insertions, 53 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 95d65b377..c3d0e6191 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -39,6 +39,7 @@ from .extractor.keek import KeekIE from .extractor.metacafe import MetacafeIE from .extractor.mixcloud import MixcloudIE from .extractor.mtv import MTVIE +from .extractor.myspass import MySpassIE from .extractor.myvideo import MyVideoIE from .extractor.nba import NBAIE from .extractor.statigram import StatigramIE @@ -88,59 +89,6 @@ from .extractor.zdf import ZDFIE -class MySpassIE(InfoExtractor): - _VALID_URL = r'http://www.myspass.de/.*' - - def _real_extract(self, url): - META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' - - # video id is the last path element of the URL - # usually there is a trailing slash, so also try the second but last - url_path = compat_urllib_parse_urlparse(url).path - url_parent_path, video_id = os.path.split(url_path) - if not video_id: - _, video_id = os.path.split(url_parent_path) - - # get metadata - metadata_url = META_DATA_URL_TEMPLATE % video_id - metadata_text = self._download_webpage(metadata_url, video_id) - metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) - - # extract values from metadata - url_flv_el = metadata.find('url_flv') - if url_flv_el is None: - raise ExtractorError(u'Unable to extract download url') - video_url = url_flv_el.text - extension = os.path.splitext(video_url)[1][1:] - title_el = metadata.find('title') - if title_el is None: - raise ExtractorError(u'Unable to extract title') - title = title_el.text - format_id_el = metadata.find('format_id') - if format_id_el is None: - format = ext - else: - format = format_id_el.text - description_el = metadata.find('description') - if description_el is not None: - description = description_el.text - else: - description = None - imagePreview_el = metadata.find('imagePreview') - if imagePreview_el is not None: - thumbnail = imagePreview_el.text - else: - thumbnail = None - info = { - 'id': video_id, - 'url': video_url, - 'title': title, - 'ext': extension, - 'format': format, - 'thumbnail': thumbnail, - 'description': description - } - return [info] class SpiegelIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py new file mode 100644 index 000000000..7b016bb86 --- /dev/null +++ b/youtube_dl/extractor/myspass.py @@ -0,0 +1,64 @@ +import os.path +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + + ExtractorError, +) + + +class MySpassIE(InfoExtractor): + _VALID_URL = r'http://www.myspass.de/.*' + + def _real_extract(self, url): + META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' + + # video id is the last path element of the URL + # usually there is a trailing slash, so also try the second but last + url_path = compat_urllib_parse_urlparse(url).path + url_parent_path, video_id = os.path.split(url_path) + if not video_id: + _, video_id = os.path.split(url_parent_path) + + # get metadata + metadata_url = META_DATA_URL_TEMPLATE % video_id + metadata_text = self._download_webpage(metadata_url, video_id) + metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) + + # extract values from metadata + url_flv_el = metadata.find('url_flv') + if url_flv_el is None: + raise ExtractorError(u'Unable to extract download url') + video_url = url_flv_el.text + extension = os.path.splitext(video_url)[1][1:] + title_el = metadata.find('title') + if title_el is None: + raise ExtractorError(u'Unable to extract title') + title = title_el.text + format_id_el = metadata.find('format_id') + if format_id_el is None: + format = 'mp4' + else: + format = format_id_el.text + description_el = metadata.find('description') + if description_el is not None: + description = description_el.text + else: + description = None + imagePreview_el = metadata.find('imagePreview') + if imagePreview_el is not None: + thumbnail = imagePreview_el.text + else: + thumbnail = None + info = { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': extension, + 'format': format, + 'thumbnail': thumbnail, + 'description': description + } + return [info] |