administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 11:20:41 +00:00
Code Issues Projects Releases Wiki Activity

Move GoogleSearchIE into its own file

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-06-23 20:32:49 +02:00
parent 9b122384e9
commit 3fc03845a1
2 changed files with 39 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/InfoExtractors.py
View File

@ -49,36 +49,6 @@ from .extractor.zdf import ZDFIE
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
class YahooSearchIE(SearchInfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""

39
youtube_dl/extractor/google.py Normal file
View File

@ -0,0 +1,39 @@
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