X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..82abf0abb400fbf710e03be31cc8942c21a040be:/youtube_dl/extractor/googlesearch.py diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index 21c240e..498304c 100644 --- a/youtube_dl/extractor/googlesearch.py +++ b/youtube_dl/extractor/googlesearch.py @@ -1,39 +1,59 @@ +from __future__ import unicode_literals + import itertools import re from .common import SearchInfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, ) class GoogleSearchIE(SearchInfoExtractor): - """Information Extractor for Google Video search queries.""" - _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'