From 45abe2051dafed38f4c8319a7bfe9bdbf3e372b4 Mon Sep 17 00:00:00 2001
From: Nehal Patel <nehalvpatels+github@gmail.com>
Date: Wed, 6 Jul 2016 23:36:29 -0500
Subject: [PATCH] [BrainPOP] Add new extractor

---
 youtube_dl/extractor/brainpop.py   | 47 ++++++++++++++++++++++++++++++
 youtube_dl/extractor/extractors.py |  1 +
 2 files changed, 48 insertions(+)
 create mode 100644 youtube_dl/extractor/brainpop.py

diff --git a/youtube_dl/extractor/brainpop.py b/youtube_dl/extractor/brainpop.py
new file mode 100644
index 000000000..6b3dd6a92
--- /dev/null
+++ b/youtube_dl/extractor/brainpop.py
@@ -0,0 +1,47 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class BrainPOPIE(InfoExtractor):
+    _VALID_URL = r'https?:\/\/(?:(.+)\.)?brainpop\.com\/(?P<id>[^\r\n]+)'
+    _TEST = {
+        'url': 'https://www.brainpop.com/english/freemovies/williamshakespeare/',
+        'md5': '676d936271b628dc05e4cec377751919',
+        'info_dict': {
+            'id': 'english/freemovies/williamshakespeare/',
+            'ext': 'mp4',
+            'title': 'William Shakespeare - BrainPOP',
+            'thumbnail': 're:^https?://.*\.png$',
+            'description': 'He could do comedies, tragedies, histories and poetry.  Learn about the greatest playwright in the history of the English language!',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        self.report_extraction(video_id)
+
+        ec_token = self._html_search_regex(r'ec_token : \'(.+)\'', webpage, "token")
+        movie_cdn_path = self._html_search_regex(r'movie_cdn_path : \'(.+)\'', webpage, "cdn path")
+        mp4 = self._html_search_regex(r'mp4":"([^"]*)', webpage, "mp4")
+
+        url = movie_cdn_path + mp4.replace("\\", "") + "?" + ec_token
+
+        title = self._html_search_regex(r'type":"Movie","name":"([^"]*)"', webpage, "title")
+
+        thumbnail_cdn = self._html_search_regex(r"'cdn_path' : '([^']*)'", webpage, "thumbnail cdn")
+        thumbnail_image = self._html_search_regex(r'type":"Movie","name":"[^"]*","image":"([^"]*)"', webpage, "thumbnail")
+        thumbnail = thumbnail_cdn + thumbnail_image.replace("\\", "")
+
+        description = self._html_search_regex(r'type":"Movie","name":"[^"]*","image":"[^"]*","description":"([^"]*)"', webpage, "description")
+
+        return {
+            'id': video_id,
+            'url': url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'description': description,
+        }
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 4e2a2f2e9..cc45f5c23 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -93,6 +93,7 @@ from .bokecc import BokeCCIE
 from .bpb import BpbIE
 from .br import BRIE
 from .bravotv import BravoTVIE
+from .brainpop import BrainPOPIE
 from .breakcom import BreakIE
 from .brightcove import (
     BrightcoveLegacyIE,