1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-24 09:52:58 +08:00
youtube-dl/youtube_dl/extractor/googlesearch.py
2014-03-13 16:52:13 +01:00

52 lines
1.5 KiB
Python

from __future__ import unicode_literals
import itertools
import re
from .common import SearchInfoExtractor
from ..utils import (
compat_urllib_parse,
)
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search'
_SEARCH_KEY = 'gvsearch'
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
entries = []
res = {
'_type': 'playlist',
'id': query,
'title': query,
}
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'<h3 class="r"><a href="([^"]+)"', webpage)):
# Skip playlists
if not re.search(r'id="vidthumb%d"' % (hit_idx + 1), webpage):
continue
entries.append({
'_type': 'url',
'url': mobj.group(1)
})
if (len(entries) >= n) or not re.search(r'id="pnnext"', webpage):
res['entries'] = entries[:n]
return res