X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9a117f94b4bfe84cfe1d904d5132aefcf41511c9..acbcfdb2cbb57cd2ab6a5d73341cd077fa71f6c9:/youtube_dl/extractor/googlesearch.py diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py index f9c88e9..5279fa8 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 ( - compat_urllib_parse, -) 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 mobj in re.finditer(r'

n) or not re.search(self._MORE_PAGES_INDICATOR, webpage): + if (len(entries) >= n) or not re.search(r'id="pnnext"', webpage): + res['entries'] = entries[:n] return res