w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[justin.tv] Modernize (Fixes #2705)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-05 17:56:36 +02:00
parent e4d41bfca5
commit ee1e199685
1 changed files with 42 additions and 41 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

79
youtube_dl/extractor/justintv.py
View file

@ -1,9 +1,12 @@
from __future__ import unicode_literals
import json import json
import os import os
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_str,
ExtractorError, ExtractorError,
formatSeconds, formatSeconds,
) )
@ -24,34 +27,31 @@ class JustinTVIE(InfoExtractor):
/?(?:\#.*)?$ /?(?:\#.*)?$
""" """
_JUSTIN_PAGE_LIMIT = 100 _JUSTIN_PAGE_LIMIT = 100
IE_NAME = u'justin.tv' IE_NAME = 'justin.tv'
IE_DESC = 'justin.tv and twitch.tv'
_TEST = { _TEST = {
u'url': u'http://www.twitch.tv/thegamedevhub/b/296128360', 'url': 'http://www.twitch.tv/thegamedevhub/b/296128360',
u'file': u'296128360.flv', 'md5': 'ecaa8a790c22a40770901460af191c9a',
u'md5': u'ecaa8a790c22a40770901460af191c9a', 'info_dict': {
u'info_dict': { 'id': '296128360',
u"upload_date": u"20110927", 'ext': 'flv',
u"uploader_id": 25114803, 'upload_date': '20110927',
u"uploader": u"thegamedevhub", 'uploader_id': 25114803,
u"title": u"Beginner Series - Scripting With Python Pt.1" 'uploader': 'thegamedevhub',
'title': 'Beginner Series - Scripting With Python Pt.1'
} }
} }
def report_download_page(self, channel, offset):
"""Report attempt to download a single page of videos."""
self.to_screen(u'%s: Downloading video information from %d to %d' %
(channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
# Return count of items, list of *valid* items # Return count of items, list of *valid* items
def _parse_page(self, url, video_id): def _parse_page(self, url, video_id):
info_json = self._download_webpage(url, video_id, info_json = self._download_webpage(url, video_id,
u'Downloading video info JSON', 'Downloading video info JSON',
u'unable to download video info JSON') 'unable to download video info JSON')
response = json.loads(info_json) response = json.loads(info_json)
if type(response) != list: if type(response) != list:
error_text = response.get('error', 'unknown error') error_text = response.get('error', 'unknown error')
raise ExtractorError(u'Justin.tv API: %s' % error_text) raise ExtractorError('Justin.tv API: %s' % error_text)
info = [] info = []
for clip in response: for clip in response:
video_url = clip['video_file_url'] video_url = clip['video_file_url']
@ -62,7 +62,7 @@ class JustinTVIE(InfoExtractor):
video_id = clip['id'] video_id = clip['id']
video_title = clip.get('title', video_id) video_title = clip.get('title', video_id)
info.append({ info.append({
'id': video_id, 'id': compat_str(video_id),
'url': video_url, 'url': video_url,
'title': video_title, 'title': video_title,
'uploader': clip.get('channel_name', video_uploader_id), 'uploader': clip.get('channel_name', video_uploader_id),
@ -74,8 +74,6 @@ class JustinTVIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'invalid URL: %s' % url)
api_base = 'http://api.justin.tv' api_base = 'http://api.justin.tv'
paged = False paged = False
@ -89,40 +87,41 @@ class JustinTVIE(InfoExtractor):
webpage = self._download_webpage(url, chapter_id) webpage = self._download_webpage(url, chapter_id)
m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
if not m: if not m:
raise ExtractorError(u'Cannot find archive of a chapter') raise ExtractorError('Cannot find archive of a chapter')
archive_id = m.group(1) archive_id = m.group(1)
api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
doc = self._download_xml(api, chapter_id, doc = self._download_xml(
note=u'Downloading chapter information', api, chapter_id,
errnote=u'Chapter information download failed') note='Downloading chapter information',
errnote='Chapter information download failed')
for a in doc.findall('.//archive'): for a in doc.findall('.//archive'):
if archive_id == a.find('./id').text: if archive_id == a.find('./id').text:
break break
else: else:
raise ExtractorError(u'Could not find chapter in chapter information') raise ExtractorError('Could not find chapter in chapter information')
video_url = a.find('./video_file_url').text video_url = a.find('./video_file_url').text
video_ext = video_url.rpartition('.')[2] or u'flv' video_ext = video_url.rpartition('.')[2] or 'flv'
chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id
chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id, chapter_info = self._download_json(
chapter_api_url, 'c' + chapter_id,
note='Downloading chapter metadata', note='Downloading chapter metadata',
errnote='Download of chapter metadata failed') errnote='Download of chapter metadata failed')
chapter_info = json.loads(chapter_info_json)
bracket_start = int(doc.find('.//bracket_start').text) bracket_start = int(doc.find('.//bracket_start').text)
bracket_end = int(doc.find('.//bracket_end').text) bracket_end = int(doc.find('.//bracket_end').text)
# TODO determine start (and probably fix up file) # TODO determine start (and probably fix up file)
# youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
#video_url += u'?start=' + TODO:start_timestamp #video_url += '?start=' + TODO:start_timestamp
# bracket_start is 13290, but we want 51670615 # bracket_start is 13290, but we want 51670615
self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. ' self._downloader.report_warning('Chapter detected, but we can just download the whole file. '
u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
info = { info = {
'id': u'c' + chapter_id, 'id': 'c' + chapter_id,
'url': video_url, 'url': video_url,
'ext': video_ext, 'ext': video_ext,
'title': chapter_info['title'], 'title': chapter_info['title'],
@ -131,14 +130,12 @@ class JustinTVIE(InfoExtractor):
'uploader': chapter_info['channel']['display_name'], 'uploader': chapter_info['channel']['display_name'],
'uploader_id': chapter_info['channel']['name'], 'uploader_id': chapter_info['channel']['name'],
} }
return [info] return info
else: else:
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
api = api_base + '/broadcast/by_archive/%s.json' % video_id api = api_base + '/broadcast/by_archive/%s.json' % video_id
self.report_extraction(video_id) entries = []
info = []
offset = 0 offset = 0
limit = self._JUSTIN_PAGE_LIMIT limit = self._JUSTIN_PAGE_LIMIT
while True: while True:
@ -146,8 +143,12 @@ class JustinTVIE(InfoExtractor):
self.report_download_page(video_id, offset) self.report_download_page(video_id, offset)
page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
page_count, page_info = self._parse_page(page_url, video_id) page_count, page_info = self._parse_page(page_url, video_id)
info.extend(page_info) entries.extend(page_info)
if not paged or page_count != limit: if not paged or page_count != limit:
break break
offset += limit offset += limit
return info return {
'_type': 'playlist',
'id': video_id,
'entries': entries,
}