Move YahooSearchIE to youtube_dl.extractor.yahoo

This commit is contained in:
Philipp Hagemeister 2013-06-23 20:41:54 +02:00
parent 3c25b9abae
commit 934858ad86
2 changed files with 39 additions and 35 deletions

View File

@ -27,7 +27,7 @@
from .extractor.statigram import StatigramIE from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE from .extractor.photobucket import PhotobucketIE
from .extractor.vimeo import VimeoIE from .extractor.vimeo import VimeoIE
from .extractor.yahoo import YahooIE from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE from .extractor.zdf import ZDFIE
@ -45,39 +45,6 @@
class YahooSearchIE(SearchInfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
_MAX_RESULTS = 1000
IE_NAME = u'screen.yahoo:search'
_SEARCH_KEY = 'yvsearch'
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(0):
result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
webpage = self._download_webpage(result_url, query,
note='Downloading results page '+str(pagenum+1))
info = json.loads(webpage)
m = info[u'm']
results = info[u'results']
for (i, r) in enumerate(results):
if (pagenum * 30) +i >= n:
break
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
res['entries'].append(e)
if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
break
return res
class BlipTVUserIE(InfoExtractor): class BlipTVUserIE(InfoExtractor):

View File

@ -1,9 +1,12 @@
import datetime import datetime
import itertools
import json import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor, SearchInfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse,
ExtractorError, ExtractorError,
) )
@ -74,3 +77,37 @@ def _real_extract(self, url):
'ext': 'flv', 'ext': 'flv',
} }
return info_dict return info_dict
class YahooSearchIE(SearchInfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
_MAX_RESULTS = 1000
IE_NAME = u'screen.yahoo:search'
_SEARCH_KEY = 'yvsearch'
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(0):
result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
webpage = self._download_webpage(result_url, query,
note='Downloading results page '+str(pagenum+1))
info = json.loads(webpage)
m = info[u'm']
results = info[u'results']
for (i, r) in enumerate(results):
if (pagenum * 30) +i >= n:
break
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
res['entries'].append(e)
if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
break
return res