mirror of
https://github.com/l1ving/youtube-dl
synced 2024-12-23 02:55:37 +08:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import itertools
|
|
import re
|
|
|
|
from .common import SearchInfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
)
|
|
|
|
|
|
class GoogleSearchIE(SearchInfoExtractor):
|
|
IE_DESC = 'Google Video search'
|
|
_MAX_RESULTS = 1000
|
|
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,
|
|
'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
|