Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

[common] remove duplicate reference to namespace

Browse Source
This commit is contained in:
remitamine 2016-02-02 22:02:08 +01:00
parent 9c74423510
commit f14be22816
1 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/common.py
View File

@ -1350,25 +1350,30 @@ def _parse_mpd(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
if mpd_doc.get('type') == 'dynamic': if mpd_doc.get('type') == 'dynamic':
return [] return []
namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace')
def _add_ns(path):
return self._xpath_ns(path, namespace)
def extract_multisegment_info(element, ms_parent_info): def extract_multisegment_info(element, ms_parent_info):
ms_info = ms_parent_info.copy() ms_info = ms_parent_info.copy()
segment_list = element.find(self._xpath_ns('SegmentList', namespace)) segment_list = element.find(_add_ns('SegmentList'))
if segment_list is not None: if segment_list is not None:
segment_urls_e = segment_list.findall(self._xpath_ns('SegmentURL', namespace)) segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
if segment_urls_e: if segment_urls_e:
ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e] ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
initialization = segment_list.find(self._xpath_ns('Initialization', namespace)) initialization = segment_list.find(_add_ns('Initialization'))
if initialization is not None: if initialization is not None:
ms_info['initialization_url'] = initialization.attrib['sourceURL'] ms_info['initialization_url'] = initialization.attrib['sourceURL']
else: else:
segment_template = element.find(self._xpath_ns('SegmentTemplate', namespace)) segment_template = element.find(_add_ns('SegmentTemplate'))
if segment_template is not None: if segment_template is not None:
start_number = segment_template.get('startNumber') start_number = segment_template.get('startNumber')
if start_number: if start_number:
ms_info['start_number'] = int(start_number) ms_info['start_number'] = int(start_number)
segment_timeline = segment_template.find(self._xpath_ns('SegmentTimeline', namespace)) segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
if segment_timeline is not None: if segment_timeline is not None:
s_e = segment_timeline.findall(self._xpath_ns('S', namespace)) s_e = segment_timeline.findall(_add_ns('S'))
if s_e: if s_e:
ms_info['total_number'] = 0 ms_info['total_number'] = 0
for s in s_e: for s in s_e:
@ -1387,23 +1392,22 @@ def extract_multisegment_info(element, ms_parent_info):
if initialization: if initialization:
ms_info['initialization_url'] = initialization ms_info['initialization_url'] = initialization
else: else:
initialization = segment_template.find(self._xpath_ns('Initialization', namespace)) initialization = segment_template.find(_add_ns('Initialization'))
if initialization is not None: if initialization is not None:
ms_info['initialization_url'] = initialization.attrib['sourceURL'] ms_info['initialization_url'] = initialization.attrib['sourceURL']
return ms_info return ms_info
namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace')
mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration')) mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
formats = [] formats = []
for period in mpd_doc.findall(self._xpath_ns('Period', namespace)): for period in mpd_doc.findall(_add_ns('Period')):
period_duration = parse_duration(period.get('duration')) or mpd_duration period_duration = parse_duration(period.get('duration')) or mpd_duration
period_ms_info = extract_multisegment_info(period, { period_ms_info = extract_multisegment_info(period, {
'start_number': 1, 'start_number': 1,
'timescale': 1, 'timescale': 1,
}) })
for adaptation_set in period.findall(self._xpath_ns('AdaptationSet', namespace)): for adaptation_set in period.findall(_add_ns('AdaptationSet')):
adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info) adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
for representation in adaptation_set.findall(self._xpath_ns('Representation', namespace)): for representation in adaptation_set.findall(_add_ns('Representation')):
representation_attrib = adaptation_set.attrib.copy() representation_attrib = adaptation_set.attrib.copy()
representation_attrib.update(representation.attrib) representation_attrib.update(representation.attrib)
mime_type = representation_attrib.get('mimeType') mime_type = representation_attrib.get('mimeType')
@ -1414,7 +1418,7 @@ def extract_multisegment_info(element, ms_parent_info):
elif content_type == 'video' or content_type == 'audio': elif content_type == 'video' or content_type == 'audio':
base_url = '' base_url = ''
for element in (representation, adaptation_set, period, mpd_doc): for element in (representation, adaptation_set, period, mpd_doc):
base_url_e = element.find(self._xpath_ns('BaseURL', namespace)) base_url_e = element.find(_add_ns('BaseURL'))
if base_url_e is not None: if base_url_e is not None:
base_url = base_url_e.text + base_url base_url = base_url_e.text + base_url
if re.match(r'^https?://', base_url): if re.match(r'^https?://', base_url):