X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fgooglesearch.py;h=469e1f9357eaf66ef48b3bed6c3d464c48f2b5dc;hb=a80c96eab0b7c47ddae331ece37faa458be7bb2e;hp=f9c88e9b5328a035cda2abe1014a015fceff2ed7;hpb=0f818663291752b2084d81aff76d945a43c66a06;p=youtube-dl diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index f9c88e9b5..469e1f935 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import itertools import re @@ -8,32 +10,50 @@ from ..utils import ( class GoogleSearchIE(SearchInfoExtractor): - IE_DESC = u'Google Video search' - _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"' + IE_DESC = 'Google Video search' _MAX_RESULTS = 1000 - IE_NAME = u'video.google:search' + IE_NAME = 'video.google:search' _SEARCH_KEY = 'gvsearch' + _TEST = { + 'url': 'gvsearch15:python language', + 'info_dict': { + 'id': 'python language', + 'title': 'python language', + }, + 'playlist_count': 15, + } def _get_n_results(self, query, n): """Get a specified number of results for a query""" + entries = [] res = { '_type': 'playlist', 'id': query, - 'entries': [] + 'title': query, } - for pagenum in itertools.count(1): - result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10) - webpage = self._download_webpage(result_url, u'gvsearch:' + query, - note='Downloading result page ' + str(pagenum)) + for pagenum in itertools.count(): + result_url = ( + 'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' + % (compat_urllib_parse.quote_plus(query), pagenum * 10)) + + webpage = self._download_webpage( + result_url, 'gvsearch:' + query, + note='Downloading result page ' + str(pagenum + 1)) + + for hit_idx, mobj in enumerate(re.finditer( + r'