[njpwworld] Add new extractor (closes #11561)

diff --git a/ChangeLog b/ChangeLog
index add8a6758a4d46a916fe77a59599c14b5c873157..e0e1f52d01ce4df23af0c4890f47edf0d7feac1c 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+version <unreleased>
+
+Extractors
++ [njpwworld] Add new extractor (#11561)
+
+
 version 2017.02.24.1
 
 Extractors

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 83a170fa708aa1c745f5abe9f095fba25a4e71e4..703bc5d34d771f87a5e30613a9e2a97a57c2757f 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -637,6 +637,7 @@ from .ninecninemedia import (
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
 from .nintendo import NintendoIE
+from .njpwworld import NJPWWorldIE
 from .nobelprize import NobelPrizeIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE

diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py
new file mode 100644 (file)
index 0000000..f5e3f68
--- /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,
+        }