adds browsertrix to all archivers flows

archivers/telegram_archiver.py

@@ -86,4 +86,4 @@ class TelegramArchiver(Archiver):
 
         cdn_url = self.storage.get_cdn_url(key)
         return ArchiveResult(status=status, cdn_url=cdn_url, thumbnail=key_thumb, thumbnail_index=thumb_index,
-                             duration=duration, title=original_url, timestamp=s.find_all('time')[1].get('datetime'), hash=hash, screenshot=screenshot)
+                             duration=duration, title=original_url, timestamp=s.find_all('time')[1].get('datetime'), hash=hash, screenshot=screenshot, wacz=wacz)

archivers/telethon_archiver.py

@@ -74,6 +74,7 @@ class TelethonArchiver(Archiver):
             logger.debug(f'got {len(media_posts)=} for {url=}')
 
             screenshot = self.get_screenshot(url)
+            wacz = self.get_wacz(url)
 
             if len(media_posts) > 0:
                 key = self.get_html_key(url)
@@ -81,7 +82,7 @@ class TelethonArchiver(Archiver):
                 if check_if_exists and self.storage.exists(key):
                     # only s3 storage supports storage.exists as not implemented on gd
                     cdn_url = self.storage.get_cdn_url(key)
-                    return ArchiveResult(status='already archived', cdn_url=cdn_url, title=post.message, timestamp=post.date, screenshot=screenshot)
+                    return ArchiveResult(status='already archived', cdn_url=cdn_url, title=post.message, timestamp=post.date, screenshot=screenshot, wacz=wacz)
 
                 key_thumb, thumb_index = None, None
                 group_id = post.grouped_id if post.grouped_id is not None else post.id
@@ -120,7 +121,7 @@ class TelethonArchiver(Archiver):
 
                 page_cdn, page_hash, _ = self.generate_media_page_html(url, uploaded_media, html.escape(str(post)))
 
-                return ArchiveResult(status=status, cdn_url=page_cdn, title=message, timestamp=post.date, hash=page_hash, screenshot=screenshot, thumbnail=key_thumb, thumbnail_index=thumb_index)
+                return ArchiveResult(status=status, cdn_url=page_cdn, title=message, timestamp=post.date, hash=page_hash, screenshot=screenshot, thumbnail=key_thumb, thumbnail_index=thumb_index, wacz=wacz)
 
             page_cdn, page_hash, _ = self.generate_media_page_html(url, [], html.escape(str(post)))
-            return ArchiveResult(status=status, cdn_url=page_cdn, title=post.message, timestamp=getattr_or(post, "date"), hash=page_hash, screenshot=screenshot)
+            return ArchiveResult(status=status, cdn_url=page_cdn, title=post.message, timestamp=getattr_or(post, "date"), hash=page_hash, screenshot=screenshot, wacz=wacz)

archivers/twitter_api_archiver.py

@@ -70,5 +70,6 @@ class TwitterApiArchiver(TwitterArchiver):
         }, ensure_ascii=False, indent=4)
 
         screenshot = self.get_screenshot(url)
+        wacz = self.get_wacz(url)
         page_cdn, page_hash, thumbnail = self.generate_media_page(urls, url, output)
-        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, timestamp=timestamp, title=tweet.data.text)
+        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, timestamp=timestamp, title=tweet.data.text, wacz=wacz)

archivers/twitter_archiver.py

@@ -85,8 +85,9 @@ class TwitterArchiver(Archiver):
 
         timestamp = datetime.strptime(tweet["created_at"], "%Y-%m-%dT%H:%M:%S.%fZ")
         screenshot = self.get_screenshot(url)
+        wacz = self.get_wacz(url)
         page_cdn, page_hash, thumbnail = self.generate_media_page(urls, url, r.text)
-        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, timestamp=timestamp, title=tweet["text"])
+        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, timestamp=timestamp, title=tweet["text"], wacz=wacz)
 
     def choose_variant(self, variants):
         # choosing the highest quality possible

archivers/vk_archiver.py

@@ -70,4 +70,5 @@ class VkArchiver(Archiver):
         page_cdn, page_hash, thumbnail = self.generate_media_page_html(url, uploaded_media, textual_output, thumbnail=thumbnail)
         # # if multiple wall/photos/videos are present the screenshot will only grab the 1st
         screenshot = self.get_screenshot(url)
-        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, thumbnail_index=thumbnail_index, timestamp=datetime, title=title)
+        wacz = self.get_wacz(url)
+        return ArchiveResult(status="success", cdn_url=page_cdn, screenshot=screenshot, hash=page_hash, thumbnail=thumbnail, thumbnail_index=thumbnail_index, timestamp=datetime, title=title, wacz=wacz)

archivers/wayback_archiver.py

@@ -61,7 +61,7 @@ class WaybackArchiver(Archiver):
             retries += 1
 
         if status_r.status_code != 200:
-            return ArchiveResult(status=f"Internet archive failed: check https://web.archive.org/save/status/{job_id}", screenshot=screenshot)
+            return ArchiveResult(status=f"Internet archive failed: check https://web.archive.org/save/status/{job_id}", screenshot=screenshot, wacz=wacz)
 
         status_json = status_r.json()
         if status_json['status'] != 'success':