midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[yahoo] use unicode_literals

Browse source
This commit is contained in:
Arjun Sreedharan 2014-02-11 13:25:24 +05:30 committed by Jaime Marquínez Ferrándiz
parent cb38928974
commit 2317e6b2b3
1 changed files with 31 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
youtube_dl/extractor/yahoo.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import itertools import itertools
import json import json
import re import re
@ -12,25 +14,25 @@ from ..utils import (
class YahooIE(InfoExtractor): class YahooIE(InfoExtractor):
IE_DESC = u'Yahoo screen' IE_DESC = 'Yahoo screen'
_VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html' _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
_TESTS = [ _TESTS = [
{ {
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
u'file': u'214727115.mp4', 'file': '214727115.mp4',
u'md5': u'4962b075c08be8690a922ee026d05e69', 'md5': '4962b075c08be8690a922ee026d05e69',
u'info_dict': { 'info_dict': {
u'title': u'Julian Smith & Travis Legg Watch Julian Smith', 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
u'description': u'Julian and Travis watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith',
}, },
}, },
{ {
u'url': u'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',
u'file': u'103000935.mp4', 'file': '103000935.mp4',
u'md5': u'd6e6fc6e1313c608f316ddad7b82b306', 'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
u'info_dict': { 'info_dict': {
u'title': u'Codefellas - The Cougar Lies with Spanish Moss', 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
u'description': u'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?',
}, },
}, },
] ]
@ -41,7 +43,7 @@ class YahooIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
items_json = self._search_regex(r'mediaItems: ({.*?})$', items_json = self._search_regex(r'mediaItems: ({.*?})$',
webpage, u'items', flags=re.MULTILINE) webpage, 'items', flags=re.MULTILINE)
items = json.loads(items_json) items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0] info = items['mediaItems']['query']['results']['mediaObj'][0]
# The 'meta' field is not always in the video webpage, we request it # The 'meta' field is not always in the video webpage, we request it
@ -60,7 +62,7 @@ class YahooIE(InfoExtractor):
}) })
query_result_json = self._download_webpage( query_result_json = self._download_webpage(
'http://video.query.yahoo.com/v1/public/yql?' + data, 'http://video.query.yahoo.com/v1/public/yql?' + data,
video_id, u'Downloading video info') video_id, 'Downloading video info')
query_result = json.loads(query_result_json) 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']
@ -103,13 +105,13 @@ class YahooNewsIE(YahooIE):
_VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html' _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
_TEST = { _TEST = {
u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
u'md5': u'67010fdf3a08d290e060a4dd96baa07b', 'md5': '67010fdf3a08d290e060a4dd96baa07b',
u'info_dict': { 'info_dict': {
u'id': u'104538833', 'id': '104538833',
u'ext': u'mp4', 'ext': 'mp4',
u'title': u'China Moses Is Crazy About the Blues', 'title': 'China Moses Is Crazy About the Blues',
u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0', 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
}, },
} }
@ -120,14 +122,14 @@ class YahooNewsIE(YahooIE):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id') long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
return self._get_info(long_id, video_id) return self._get_info(long_id, video_id)
class YahooSearchIE(SearchInfoExtractor): class YahooSearchIE(SearchInfoExtractor):
IE_DESC = u'Yahoo screen search' IE_DESC = 'Yahoo screen search'
_MAX_RESULTS = 1000 _MAX_RESULTS = 1000
IE_NAME = u'screen.yahoo:search' IE_NAME = 'screen.yahoo:search'
_SEARCH_KEY = 'yvsearch' _SEARCH_KEY = 'yvsearch'
def _get_n_results(self, query, n): def _get_n_results(self, query, n):
@ -139,12 +141,12 @@ class YahooSearchIE(SearchInfoExtractor):
'entries': [] 'entries': []
} }
for pagenum in itertools.count(0): 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) 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, webpage = self._download_webpage(result_url, query,
note='Downloading results page '+str(pagenum+1)) note='Downloading results page '+str(pagenum+1))
info = json.loads(webpage) info = json.loads(webpage)
m = info[u'm'] m = info['m']
results = info[u'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:
@ -152,7 +154,7 @@ class YahooSearchIE(SearchInfoExtractor):
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) res['entries'].append(e)
if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)): if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)):
break break
return res return res