From caefb1de877e163fa3ece44757cb2fae6adf47e4 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 9 Dec 2013 19:39:41 +0100 Subject: [ndtv] Add extractor (Fixes #1924) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ndtv.py | 66 ++++++++++++++++++++++++++++++++++++++++ youtube_dl/utils.py | 12 ++++++++ 3 files changed, 79 insertions(+) create mode 100644 youtube_dl/extractor/ndtv.py (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3f740baa1..1149dc1ec 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -100,6 +100,7 @@ from .myvideo import MyVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import NBCNewsIE +from .ndtv import NDTVIE from .newgrounds import NewgroundsIE from .nhl import NHLIE, NHLVideocenterIE from .niconico import NiconicoIE diff --git a/youtube_dl/extractor/ndtv.py b/youtube_dl/extractor/ndtv.py new file mode 100644 index 000000000..2e8501f99 --- /dev/null +++ b/youtube_dl/extractor/ndtv.py @@ -0,0 +1,66 @@ +import json +import re +import time + +from .common import InfoExtractor +from ..utils import month_by_name + + +class NDTVIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P[a-z0-9]+)' + + _TEST = { + u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710", + u"file": u"300710.mp4", + u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88", + u"info_dict": { + u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal", + u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.", + u"upload_date": u"20131208", + u"duration": 1327, + u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg", + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + filename = self._search_regex( + r"__filename='([^']+)'", webpage, u'video filename') + video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' % + filename) + + duration_str = filename = self._search_regex( + r"__duration='([^']+)'", webpage, u'duration', fatal=False) + duration = None if duration_str is None else int(duration_str) + + date_m = re.search(r'''(?x) + \s* + Published\s+On:\s* + (?P[A-Za-z]+)\s+(?P[0-9]+),\s*(?P[0-9]+) + ''', webpage) + upload_date = None + assert date_m + if date_m is not None: + month = month_by_name(date_m.group('monthname')) + if month is not None: + upload_date = '%s%02d%02d' % ( + date_m.group('year'), month, int(date_m.group('day'))) + + description = self._og_search_description(webpage) + READ_MORE = u' (Read more)' + if description.endswith(READ_MORE): + description = description[:-len(READ_MORE)] + + return { + 'id': video_id, + 'url': video_url, + 'title': self._og_search_title(webpage), + 'description': description, + 'thumbnail': self._og_search_thumbnail(webpage), + 'duration': duration, + 'upload_date': upload_date, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 64300d8e0..0dab9fcc5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1045,3 +1045,15 @@ def get_term_width(): except: pass return None + + +def month_by_name(name): + """ Return the number of a month by (locale-independently) English name """ + + ENGLISH_NAMES = [ + u'Januar', u'February', u'March', u'April', u'May', u'June', + u'July', u'August', u'September', u'October', u'November', u'December'] + try: + return ENGLISH_NAMES.index(name) + 1 + except ValueError: + return None -- cgit v1.2.3