Simplify formats accumulation for f4m/m3u8/smil formats

[youtube-dl] / youtube_dl / extractor / funimation.py

diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py
index 0b427961251320f199c9e73cc7433dfd847d654b..0f37ed7863c93da4813a6ac6be2d6402fc7bbd0a 100644 (file)
--- a/youtube_dl/extractor/funimation.py
+++ b/youtube_dl/extractor/funimation.py
@@ -1,13 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
     determine_ext,
     encode_dict,
+    int_or_none,
     sanitized_Request,
     ExtractorError,
     urlencode_postdata
@@ -17,6 +16,8 @@ from ..utils import (
 class FunimationIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
 
+    _NETRC_MACHINE = 'funimation'
+
     _TESTS = [{
         'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
         'info_dict': {
@@ -39,7 +40,14 @@ class FunimationIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
-        'only_matching': True,
+        'info_dict': {
+            'id': '9635',
+            'display_id': 'broadcast-dub-preview',
+            'ext': 'mp4',
+            'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
+            'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
+            'thumbnail': 're:https?://.*\.(?:jpg|png)',
+        },
     }]
 
     def _login(self):
@@ -54,10 +62,16 @@ class FunimationIE(InfoExtractor):
             'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
             'Content-Type': 'application/x-www-form-urlencoded'
         })
-        login = self._download_webpage(
+        login_page = self._download_webpage(
             login_request, None, 'Logging in as %s' % username)
-        if re.search(r'<meta property="og:url" content="http://www.funimation.com/login"/>', login) is not None:
-            raise ExtractorError('Unable to login, wrong username or password.', expected=True)
+        if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
+            return
+        error = self._html_search_regex(
+            r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
+            login_page, 'error messages', default=None)
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+        raise ExtractorError('Unable to log in')
 
     def _real_initialize(self):
         self._login()
@@ -96,12 +110,13 @@ class FunimationIE(InfoExtractor):
             webpage = self._download_webpage(
                 request, display_id, 'Downloading %s webpage' % kind)
 
-            items = self._parse_json(
+            playlist = self._parse_json(
                 self._search_regex(
                     r'var\s+playersData\s*=\s*(\[.+?\]);\n',
                     webpage, 'players data'),
-                display_id)[0]['playlist'][0]['items']
+                display_id)[0]['playlist']
 
+            items = next(item['items'] for item in playlist if item.get('items'))
             item = next(item for item in items if item.get('itemAK') == display_id)
 
             error_messages = {}
@@ -128,7 +143,7 @@ class FunimationIE(InfoExtractor):
                 preference = 1 if video.get('languageMode') == 'dub' else 0
                 if not auth_token.startswith('?'):
                     auth_token = '?%s' % auth_token
-                for quality in ('sd', 'hd', 'hd1080'):
+                for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
                     format_url = video.get('%sUrl' % quality)
                     if not format_url:
                         continue
@@ -136,24 +151,19 @@ class FunimationIE(InfoExtractor):
                         errors.append(format_url)
                         continue
                     if determine_ext(format_url) == 'm3u8':
-                        m3u8_formats = self._extract_m3u8_formats(
+                        formats.extend(self._extract_m3u8_formats(
                             format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
-                            preference=preference, m3u8_id=funimation_id or 'hls', fatal=False)
-                        if m3u8_formats:
-                            formats.extend(m3u8_formats)
+                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
                     else:
-                        f = {
+                        tbr = int_or_none(self._search_regex(
+                            r'-(\d+)[Kk]', format_url, 'tbr', default=None))
+                        formats.append({
                             'url': format_url + auth_token,
-                            'format_id': funimation_id,
+                            'format_id': '%s-http-%dp' % (funimation_id, height),
+                            'height': height,
+                            'tbr': tbr,
                             'preference': preference,
-                        }
-                        mobj = re.search(r'(?P<height>\d+)-(?P<tbr>\d+)[Kk]', format_url)
-                        if mobj:
-                            f.update({
-                                'height': int(mobj.group('height')),
-                                'tbr': int(mobj.group('tbr')),
-                            })
-                        formats.append(f)
+                        })
 
         if not formats and errors:
             raise ExtractorError(