github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[yahoo] Modernize

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-04-04 18:31:30 +02:00
parent 65a40ab82b
commit 88f1c6de7b
1 changed files with 17 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/extractor/yahoo.py
View file

@ -1,7 +1,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools import itertools
import json
import re import re
from .common import InfoExtractor, SearchInfoExtractor from .common import InfoExtractor, SearchInfoExtractor
@ -19,18 +18,20 @@ class YahooIE(InfoExtractor):
_TESTS = [ _TESTS = [
{ {
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
'file': '214727115.mp4',
'md5': '4962b075c08be8690a922ee026d05e69', 'md5': '4962b075c08be8690a922ee026d05e69',
'info_dict': { 'info_dict': {
'id': '214727115',
'ext': 'mp4',
'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
'description': 'Julian and Travis watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith',
}, },
}, },
{ {
'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
'file': '103000935.mp4',
'md5': 'd6e6fc6e1313c608f316ddad7b82b306', 'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
'info_dict': { 'info_dict': {
'id': '103000935',
'ext': 'mp4',
'title': 'Codefellas - The Cougar Lies with Spanish Moss', 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
}, },
@ -60,10 +61,9 @@ class YahooIE(InfoExtractor):
'env': 'prod', 'env': 'prod',
'format': 'json', 'format': 'json',
}) })
query_result_json = self._download_webpage( query_result = self._download_json(
'http://video.query.yahoo.com/v1/public/yql?' + data, 'http://video.query.yahoo.com/v1/public/yql?' + data,
video_id, 'Downloading video info') video_id, 'Downloading video info')
query_result = json.loads(query_result_json)
info = query_result['query']['results']['mediaObj'][0] info = query_result['query']['results']['mediaObj'][0]
meta = info['meta'] meta = info['meta']
@ -86,7 +86,6 @@ class YahooIE(InfoExtractor):
else: else:
format_url = compat_urlparse.urljoin(host, path) format_url = compat_urlparse.urljoin(host, path)
format_info['url'] = format_url format_info['url'] = format_url
formats.append(format_info) formats.append(format_info)
self._sort_formats(formats) self._sort_formats(formats)
@ -134,27 +133,25 @@ class YahooSearchIE(SearchInfoExtractor):
def _get_n_results(self, query, n): def _get_n_results(self, query, n):
"""Get a specified number of results for a query""" """Get a specified number of results for a query"""
entries = []
res = {
'_type': 'playlist',
'id': query,
'entries': []
}
for pagenum in itertools.count(0): for pagenum in itertools.count(0):
result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) result_url = '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, info = self._download_json(result_url, query,
note='Downloading results page '+str(pagenum+1)) note='Downloading results page '+str(pagenum+1))
info = json.loads(webpage)
m = info['m'] m = info['m']
results = info['results'] results = info['results']
for (i, r) in enumerate(results): for (i, r) in enumerate(results):
if (pagenum * 30) +i >= n: if (pagenum * 30) + i >= n:
break break
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r) mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo') e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
res['entries'].append(e) entries.append(e)
if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)): if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)):
break break
return res return {
'_type': 'playlist',
'id': query,
'entries': entries,
}