]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/googlesearch.py
Fix description of the modularization.
[youtubedl] / youtube_dl / extractor / googlesearch.py
1 import itertools
2 import re
3
4 from .common import SearchInfoExtractor
5 from ..utils import (
6 compat_urllib_parse,
7 )
8
9
10 class GoogleSearchIE(SearchInfoExtractor):
11 """Information Extractor for Google Video search queries."""
12 _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
13 _MAX_RESULTS = 1000
14 IE_NAME = u'video.google:search'
15 _SEARCH_KEY = 'gvsearch'
16
17 def _get_n_results(self, query, n):
18 """Get a specified number of results for a query"""
19
20 res = {
21 '_type': 'playlist',
22 'id': query,
23 'entries': []
24 }
25
26 for pagenum in itertools.count(1):
27 result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
28 webpage = self._download_webpage(result_url, u'gvsearch:' + query,
29 note='Downloading result page ' + str(pagenum))
30
31 for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
32 e = {
33 '_type': 'url',
34 'url': mobj.group(1)
35 }
36 res['entries'].append(e)
37
38 if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
39 return res