From ca3abff9eaa30aaf8c5be21396c508139402fee0 Mon Sep 17 00:00:00 2001
From: selfisekai <laura@selfisekai.rocks>
Date: Sat, 7 Nov 2020 04:13:19 +0100
Subject: [PATCH] aliexpress product video extractor

---
 haruhi_dl/extractor/aliexpress.py | 44 +++++++++++++++++++++++++++++++
 haruhi_dl/extractor/extractors.py |  5 +++-
 2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/haruhi_dl/extractor/aliexpress.py b/haruhi_dl/extractor/aliexpress.py
index 6f241e683..6b9afa80a 100644
--- a/haruhi_dl/extractor/aliexpress.py
+++ b/haruhi_dl/extractor/aliexpress.py
@@ -10,6 +10,7 @@ from ..utils import (
 
 
 class AliExpressLiveIE(InfoExtractor):
+    IE_NAME = 'aliexpress:live'
     _VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
     _TEST = {
         'url': 'https://live.aliexpress.com/live/2800002704436634',
@@ -51,3 +52,46 @@ class AliExpressLiveIE(InfoExtractor):
             'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
             'formats': formats,
         }
+
+
+class AliExpressProductIE(InfoExtractor):
+    IE_NAME = 'aliexpress:product'
+
+    _TESTS = [{
+        'url': 'https://pl.aliexpress.com/item/4000570726711.html',
+        'info_dict': {
+            'id': '249591332087',
+            'title': str,  # depends on IP location
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.aliexpress.com/item/4000813110155.html',
+        'info_dict': {
+            'id': '274294663774',
+            'title': str,  # depends on IP location
+            'ext': 'mp4',
+        },
+    }]
+
+    _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?aliexpress\.(?:com|ru)/item/(?P<id>\d+)\.html'
+
+    def _real_extract(self, url):
+        pid = self._match_id(url)
+        webpage = self._download_webpage(url, pid, 'Downloading product page')
+
+        vid = self._search_regex(
+            r'"videoId"\s*:\s*"?(\d+)"?',
+            webpage, 'video id')
+        uid = self._search_regex(
+            r'"videoUid"\s*:\s*"?(?P<uid>\d+)"?',
+            webpage, 'video uid')
+
+        og_title = self._og_search_title(webpage)
+        title = self._search_regex(r'^.*?\|(.+?)\|', og_title, 'product title', default=og_title)
+
+        return {
+            # I have no idea what these params mean but it at least seems to work
+            'url': 'https://cloud.video.taobao.com/play/u/%s/p/1/e/6/t/10301/%s.mp4' % (uid, vid),
+            'id': vid,
+            'title': title,
+        }
diff --git a/haruhi_dl/extractor/extractors.py b/haruhi_dl/extractor/extractors.py
index 624a430e8..217bff4d0 100644
--- a/haruhi_dl/extractor/extractors.py
+++ b/haruhi_dl/extractor/extractors.py
@@ -42,7 +42,10 @@ from .animeondemand import AnimeOnDemandIE
 from .anvato import AnvatoIE
 from .aol import AolIE
 from .allocine import AllocineIE
-from .aliexpress import AliExpressLiveIE
+from .aliexpress import (
+    AliExpressLiveIE,
+    AliExpressProductIE,
+)
 from .apa import APAIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE