X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fwat.py;h=8ef3e0906436b3a13e1bc368173e7f7c81ba6c22;hb=HEAD;hp=9f1b8b4b5f1bbe6f5d34d5e31bcc5596c35543f7;hpb=e2e84aed7e75a4e073dca934b7ff85e29399b23a;p=youtube-dl diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 9f1b8b4b5..8ef3e0906 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -19,7 +19,6 @@ class WatIE(InfoExtractor): _TESTS = [ { 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', - 'md5': '83d882d9de5c9d97f0bb2c6273cde56a', 'info_dict': { 'id': '11713067', 'ext': 'mp4', @@ -28,10 +27,15 @@ class WatIE(InfoExtractor): 'upload_date': '20140819', 'duration': 120, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'expected_warnings': ['HTTP Error 404'], }, { 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', - 'md5': '34bdfa5ca9fd3c7eb88601b635b0424c', + 'md5': 'b16574df2c3cd1a36ca0098f2a791925', 'info_dict': { 'id': '11713075', 'ext': 'mp4', @@ -86,38 +90,37 @@ class WatIE(InfoExtractor): def extract_url(path_template, url_type): req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id) - head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type) - red_url = head.geturl() - if req_url == red_url: - raise ExtractorError( - '%s said: Sorry, this video is not available from your country.' % self.IE_NAME, - expected=True) - return red_url + head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False) + if head: + red_url = head.geturl() + if req_url != red_url: + return red_url + return None + + def remove_bitrate_limit(manifest_url): + return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url) formats = [] try: - http_url = extract_url('android5/%s.mp4', 'http') - m3u8_url = extract_url('ipad/%s.m3u8', 'm3u8') - m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') - formats.extend(m3u8_formats) - formats.extend(self._extract_f4m_formats( - m3u8_url.replace('ios.', 'web.').replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - for m3u8_format in m3u8_formats: - vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr') - if not vbr or not abr: - continue - format_id = m3u8_format['format_id'].replace('hls', 'http') - fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url) - if self._is_valid_url(fmt_url, video_id, format_id): - f = m3u8_format.copy() - f.update({ - 'url': fmt_url, - 'format_id': format_id, - 'protocol': 'http', - }) - formats.append(f) + alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')] + manifest_urls = self._download_json( + 'http://www.wat.tv/get/webhtml/' + video_id, video_id) + m3u8_url = manifest_urls.get('hls') + if m3u8_url: + m3u8_url = remove_bitrate_limit(m3u8_url) + for m3u8_alt_url in alt_urls(m3u8_url): + formats.extend(self._extract_m3u8_formats( + m3u8_alt_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'), + video_id, f4m_id='hds', fatal=False)) + mpd_url = manifest_urls.get('mpd') + if mpd_url: + mpd_url = remove_bitrate_limit(mpd_url) + for mpd_alt_url in alt_urls(mpd_url): + formats.extend(self._extract_mpd_formats( + mpd_alt_url, video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) except ExtractorError: abr = 64