From 934858ad86f5b628978d3bcdd7edd765d4590840 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:41:54 +0200 Subject: [PATCH] Move YahooSearchIE to youtube_dl.extractor.yahoo --- youtube_dl/InfoExtractors.py | 35 +------------------------------ youtube_dl/extractor/yahoo.py | 39 ++++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 35 deletions(-) diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 26fc65690..fb10c2ec4 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -27,7 +27,7 @@ from .extractor.metacafe import MetacafeIE from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE from .extractor.vimeo import VimeoIE -from .extractor.yahoo import YahooIE +from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.zdf import ZDFIE @@ -45,39 +45,6 @@ from .extractor.zdf import ZDFIE -class YahooSearchIE(SearchInfoExtractor): - """Information Extractor for Yahoo! Video search queries.""" - - _MAX_RESULTS = 1000 - IE_NAME = u'screen.yahoo:search' - _SEARCH_KEY = 'yvsearch' - - def _get_n_results(self, query, n): - """Get a specified number of results for a query""" - - res = { - '_type': 'playlist', - 'id': query, - 'entries': [] - } - for pagenum in itertools.count(0): - result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) - webpage = self._download_webpage(result_url, query, - note='Downloading results page '+str(pagenum+1)) - info = json.loads(webpage) - m = info[u'm'] - results = info[u'results'] - - for (i, r) in enumerate(results): - if (pagenum * 30) +i >= n: - break - mobj = re.search(r'(?Pscreen\.yahoo\.com/.*?-\d*?\.html)"', r) - e = self.url_result('http://' + mobj.group('url'), 'Yahoo') - res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )): - break - - return res class BlipTVUserIE(InfoExtractor): diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 4f3af17d7..4b3aec9d1 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,9 +1,12 @@ import datetime +import itertools import json import re -from .common import InfoExtractor +from .common import InfoExtractor, SearchInfoExtractor from ..utils import ( + compat_urllib_parse, + ExtractorError, ) @@ -74,3 +77,37 @@ class YahooIE(InfoExtractor): 'ext': 'flv', } return info_dict + +class YahooSearchIE(SearchInfoExtractor): + """Information Extractor for Yahoo! Video search queries.""" + + _MAX_RESULTS = 1000 + IE_NAME = u'screen.yahoo:search' + _SEARCH_KEY = 'yvsearch' + + def _get_n_results(self, query, n): + """Get a specified number of results for a query""" + + res = { + '_type': 'playlist', + 'id': query, + 'entries': [] + } + for pagenum in itertools.count(0): + result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) + webpage = self._download_webpage(result_url, query, + note='Downloading results page '+str(pagenum+1)) + info = json.loads(webpage) + m = info[u'm'] + results = info[u'results'] + + for (i, r) in enumerate(results): + if (pagenum * 30) +i >= n: + break + mobj = re.search(r'(?Pscreen\.yahoo\.com/.*?-\d*?\.html)"', r) + e = self.url_result('http://' + mobj.group('url'), 'Yahoo') + res['entries'].append(e) + if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )): + break + + return res -- 2.22.2