From db182c63fb4a58974e425a56d235131fd9efc531 Mon Sep 17 00:00:00 2001
From: Yen Chi Hsuan <yan12125@gmail.com>
Date: Sat, 25 Feb 2017 18:44:39 +0800
Subject: [njpwworld] Add new extractor (closes #11561)

---
 youtube_dl/extractor/njpwworld.py | 83 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 youtube_dl/extractor/njpwworld.py

(limited to 'youtube_dl/extractor/njpwworld.py')

diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py
new file mode 100644
index 000000000..f5e3f6815
--- /dev/null
+++ b/youtube_dl/extractor/njpwworld.py
@@ -0,0 +1,83 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    get_element_by_class,
+    urlencode_postdata,
+)
+
+
+class NJPWWorldIE(InfoExtractor):
+    _VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
+    IE_DESC = '新日本プロレスワールド'
+    _NETRC_MACHINE = 'njpwworld'
+
+    _TEST = {
+        'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
+        'info_dict': {
+            'id': 's_series_00155_1_9',
+            'ext': 'mp4',
+            'title': '第9試合　ランディ・サベージ　vs　リック・スタイナー',
+            'tags': list,
+        },
+        'params': {
+            'skip_download': True,  # AES-encrypted m3u8
+        },
+        'skip': 'Requires login',
+    }
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        # No authentication to be performed
+        if not username:
+            return True
+
+        webpage, urlh = self._download_webpage_handle(
+            'https://njpwworld.com/auth/login', None,
+            note='Logging in', errnote='Unable to login',
+            data=urlencode_postdata({'login_id': username, 'pw': password}))
+        # /auth/login will return 302 for successful logins
+        if urlh.geturl() == 'https://njpwworld.com/auth/login':
+            self.report_warning('unable to login')
+            return False
+
+        return True
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = []
+        for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
+            player_url = compat_urlparse.urljoin(url, player_url)
+
+            player_page = self._download_webpage(
+                player_url, video_id, note='Downloading player page')
+
+            entries = self._parse_html5_media_entries(
+                player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
+                m3u8_entry_protocol='m3u8_native',
+                preference=2 if 'hq' in kind else 1)
+            formats.extend(entries[0]['formats'])
+
+        self._sort_formats(formats)
+
+        post_content = get_element_by_class('post-content', webpage)
+        tags = re.findall(
+            r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
+        ) if post_content else None
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'formats': formats,
+            'tags': tags,
+        }
-- 
cgit v1.2.3


From 8fffac6927b4144bfb3e473b58fa52313042ecbb Mon Sep 17 00:00:00 2001
From: Sergey M․ <dstftw@gmail.com>
Date: Fri, 19 May 2017 23:11:02 +0700
Subject: [njpwworld] Fix extraction (closes #13162)

---
 youtube_dl/extractor/njpwworld.py | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

(limited to 'youtube_dl/extractor/njpwworld.py')

diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py
index f5e3f6815..9b5ad5a9f 100644
--- a/youtube_dl/extractor/njpwworld.py
+++ b/youtube_dl/extractor/njpwworld.py
@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    extract_attributes,
     get_element_by_class,
     urlencode_postdata,
 )
@@ -56,17 +57,24 @@ class NJPWWorldIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         formats = []
-        for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
-            player_url = compat_urlparse.urljoin(url, player_url)
-
+        for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
+            player = extract_attributes(mobj.group(0))
+            player_path = player.get('href')
+            if not player_path:
+                continue
+            kind = self._search_regex(
+                r'(low|high)$', player.get('class') or '', 'kind',
+                default='low')
+            player_url = compat_urlparse.urljoin(url, player_path)
             player_page = self._download_webpage(
                 player_url, video_id, note='Downloading player page')
-
             entries = self._parse_html5_media_entries(
                 player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
-                m3u8_entry_protocol='m3u8_native',
-                preference=2 if 'hq' in kind else 1)
-            formats.extend(entries[0]['formats'])
+                m3u8_entry_protocol='m3u8_native')
+            kind_formats = entries[0]['formats']
+            for f in kind_formats:
+                f['quality'] = 2 if kind == 'high' else 1
+            formats.extend(kind_formats)
 
         self._sort_formats(formats)
 
-- 
cgit v1.2.3