diff options
Diffstat (limited to 'youtube_dl/extractor/veehd.py')
| -rw-r--r-- | youtube_dl/extractor/veehd.py | 54 |
1 files changed, 39 insertions, 15 deletions
diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index b1c854a64..96353f525 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -4,10 +4,13 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, - get_element_by_id, +) +from ..utils import ( + ExtractorError, clean_html, + get_element_by_id, ) @@ -15,23 +18,27 @@ class VeeHDIE(InfoExtractor): _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)' _TEST = { - 'url': 'http://veehd.com/video/4686958', - 'file': '4686958.mp4', + 'url': 'http://veehd.com/video/4639434_Solar-Sinter', 'info_dict': { - 'title': 'Time Lapse View from Space ( ISS)', - 'uploader_id': 'spotted', - 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', + 'id': '4639434', + 'ext': 'mp4', + 'title': 'Solar Sinter', + 'uploader_id': 'VideoEyes', + 'description': 'md5:46a840e8692ddbaffb5f81d9885cb457', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) # VeeHD seems to send garbage on the first request. # See https://github.com/rg3/youtube-dl/issues/2102 self._download_webpage(url, video_id, 'Requesting webpage') webpage = self._download_webpage(url, video_id) + + if 'This video has been removed<' in webpage: + raise ExtractorError('Video %s has been removed' % video_id, expected=True) + player_path = self._search_regex( r'\$\("#playeriframe"\).attr\({src : "(.+?)"', webpage, 'player path') @@ -40,17 +47,34 @@ class VeeHDIE(InfoExtractor): self._download_webpage(player_url, video_id, 'Requesting player page') player_page = self._download_webpage( player_url, video_id, 'Downloading player page') + config_json = self._search_regex( - r'value=\'config=({.+?})\'', player_page, 'config json') - config = json.loads(config_json) + r'value=\'config=({.+?})\'', player_page, 'config json', default=None) + + if config_json: + config = json.loads(config_json) + video_url = compat_urlparse.unquote(config['clip']['url']) + else: + iframe_src = self._search_regex( + r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url') + iframe_url = 'http://veehd.com/%s' % iframe_src + + self._download_webpage(iframe_url, video_id, 'Requesting iframe page') + iframe_page = self._download_webpage( + iframe_url, video_id, 'Downloading iframe page') + + video_url = self._search_regex( + r"file\s*:\s*'([^']+)'", iframe_page, 'video url') - video_url = compat_urlparse.unquote(config['clip']['url']) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) - uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', + uploader_id = self._html_search_regex( + r'<a href="/profile/\d+">(.+?)</a>', webpage, 'uploader') - thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', + thumbnail = self._search_regex( + r'<img id="veehdpreview" src="(.+?)"', webpage, 'thumbnail') - description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', + description = self._html_search_regex( + r'<td class="infodropdown".*?<div>(.*?)<ul', webpage, 'description', flags=re.DOTALL) return { |