archive
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[bliptv] Simplify

Browse Source
pull/8/head
Philipp Hagemeister 11 years ago
parent 67c20aebb7
commit bca4e93076
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File

43
youtube_dl/extractor/bliptv.py
Unescape Escape View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import datetime import datetime
import json import json
import re import re
@ -14,7 +16,6 @@ from ..utils import (
ExtractorError, ExtractorError,
unescapeHTML, unescapeHTML,
determine_ext,
) )
@ -22,27 +23,27 @@ class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv""" """Information extractor for blip.tv"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' _VALID_URL = r'^(?:https?://)?(?:www\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
IE_NAME = u'blip.tv' IE_NAME = 'blip.tv'
_TEST = { _TEST = {
u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
u'file': u'5779306.m4v', 'file': '5779306.m4v',
u'md5': u'80baf1ec5c3d2019037c1c707d676b9f', 'md5': '80baf1ec5c3d2019037c1c707d676b9f',
u'info_dict': { 'info_dict': {
u"upload_date": u"20111205", 'upload_date': '20111205',
u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596", 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
u"uploader": u"Comic Book Resources - CBR TV", 'uploader': 'Comic Book Resources - CBR TV',
u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3" 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
} }
} }
def report_direct_download(self, title): def report_direct_download(self, title):
"""Report information extraction.""" """Report information extraction."""
self.to_screen(u'%s: Direct download detected' % title) self.to_screen('%s: Direct download detected' % title)
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: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError('Invalid URL: %s' % url)
# See https://github.com/rg3/youtube-dl/issues/857 # See https://github.com/rg3/youtube-dl/issues/857
api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url) api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url)
@ -66,13 +67,13 @@ class BlipTVIE(InfoExtractor):
request.add_header('User-Agent', 'iTunes/10.6.1') request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1)) self.report_extraction(mobj.group(1))
urlh = self._request_webpage(request, None, False, urlh = self._request_webpage(request, None, False,
u'unable to download video info webpage') 'unable to download video info webpage')
try: try:
json_code_bytes = urlh.read() json_code_bytes = urlh.read()
json_code = json_code_bytes.decode('utf-8') json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err)) raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err))
try: try:
json_data = json.loads(json_code) json_data = json.loads(json_code)
@ -89,7 +90,6 @@ class BlipTVIE(InfoExtractor):
continue continue
formats.append({ formats.append({
'url': f['url'], 'url': f['url'],
'ext': determine_ext(f['url']),
'format_id': f['role'], 'format_id': f['role'],
'width': int(f['media_width']), 'width': int(f['media_width']),
'height': int(f['media_height']), 'height': int(f['media_height']),
@ -97,7 +97,6 @@ class BlipTVIE(InfoExtractor):
else: else:
formats.append({ formats.append({
'url': data['media']['url'], 'url': data['media']['url'],
'ext': determine_ext(data['media']['url']),
'width': int(data['media']['width']), 'width': int(data['media']['width']),
'height': int(data['media']['height']), 'height': int(data['media']['height']),
}) })
@ -113,7 +112,7 @@ class BlipTVIE(InfoExtractor):
'formats': formats, 'formats': formats,
} }
except (ValueError, KeyError) as err: except (ValueError, KeyError) as err:
raise ExtractorError(u'Unable to parse video information: %s' % repr(err)) raise ExtractorError('Unable to parse video information: %s' % repr(err))
class BlipTVUserIE(InfoExtractor): class BlipTVUserIE(InfoExtractor):
@ -121,19 +120,19 @@ class BlipTVUserIE(InfoExtractor):
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
_PAGE_SIZE = 12 _PAGE_SIZE = 12
IE_NAME = u'blip.tv:user' IE_NAME = 'blip.tv:user'
def _real_extract(self, url): def _real_extract(self, url):
# Extract username # Extract username
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError('Invalid URL: %s' % url)
username = mobj.group(1) username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
page = self._download_webpage(url, username, u'Downloading user page') page = self._download_webpage(url, username, 'Downloading user page')
mobj = re.search(r'data-users-id="([^"]+)"', page) mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1) page_base = page_base % mobj.group(1)
@ -149,7 +148,7 @@ class BlipTVUserIE(InfoExtractor):
while True: while True:
url = page_base + "&page=" + str(pagenum) url = page_base + "&page=" + str(pagenum)
page = self._download_webpage(url, username, page = self._download_webpage(url, username,
u'Downloading video ids from page %d' % pagenum) 'Downloading video ids from page %d' % pagenum)
# Extract video identifiers # Extract video identifiers
ids_in_page = [] ids_in_page = []
@ -171,6 +170,6 @@ class BlipTVUserIE(InfoExtractor):
pagenum += 1 pagenum += 1
urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
return [self.playlist_result(url_entries, playlist_title = username)] return [self.playlist_result(url_entries, playlist_title = username)]

Write Preview
Loading…
Cancel
Save