mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-24 21:56:53 +01:00
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
import itertools
|
|
import re
|
|
|
|
from .common import SearchInfoExtractor
|
|
from ..utils import (
|
|
compat_urllib_parse,
|
|
)
|
|
|
|
|
|
class GoogleSearchIE(SearchInfoExtractor):
|
|
"""Information Extractor for Google Video search queries."""
|
|
_MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
|
|
_MAX_RESULTS = 1000
|
|
IE_NAME = u'video.google:search'
|
|
_SEARCH_KEY = 'gvsearch'
|
|
|
|
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(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'<h3 class="r"><a href="([^"]+)"', webpage):
|
|
e = {
|
|
'_type': 'url',
|
|
'url': mobj.group(1)
|
|
}
|
|
res['entries'].append(e)
|
|
|
|
if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
|
|
return res
|