Bump version to v0.5.27 for release

Pipfile

@@ -30,7 +30,7 @@ tqdm = "*"
 jinja2 = "*"
 cryptography = "*"
 dataclasses-json = "*"
-yt-dlp = ">=2023.2.17"
+yt-dlp = "*"
 vk-url-scraper = "*"
 uwsgi = "*"
 requests = {extras = ["socks"], version = "*"}

Pipfile.lock

@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "6e76638769e56f28c2cc56e548d3ac1752b36db2160e23a865089c80e584dcba"
+            "sha256": "84ebe4378c02b26d0663f6d7ede49064ec7428dddca668c8d8a5d64cf9191f09"
         },
         "pipfile-spec": 6,
         "requires": {

README.md

@@ -197,7 +197,8 @@ Outputs:
 * **Title**: Post title
 * **Text**: Post text
 * **Screenshot**: Link to screenshot of post
-* **Hash**: Hash of archived HTML file (which contains hashes of post media)
+* **Hash**: Hash of archived HTML file (which contains hashes of post media) - for checksums/verification
+* **Perceptual Hash**: Perceptual hashes of found images - these can be used for de-duplication of content
 * **WACZ**: Link to a WACZ web archive of post
 * **ReplayWebpage**: Link to a ReplayWebpage viewer of the WACZ archive
 

src/auto_archiver/archivers/telegram_archiver.py

@@ -48,7 +48,8 @@ class TelegramArchiver(Archiver):
         video = s.find("video")
         if video is None:
             logger.warning("could not find video")
-            image_tags = s.find_all(class_="js-message_photo")
+            image_tags = s.find_all(class_="tgme_widget_message_photo_wrap")
+            logger.info(image_tags)
 
             image_urls = []
             for im in image_tags:

src/auto_archiver/archivers/twitter_archiver.py

@@ -90,20 +90,36 @@ class TwitterArchiver(Archiver):
 
     def download_alternative(self, item: Metadata, url: str, tweet_id: str) -> Metadata:
         """
-        CURRENTLY STOPPED WORKING
+        Hack alternative working again.
+        https://stackoverflow.com/a/71867055/6196010 (OUTDATED URL)
+        https://github.com/JustAnotherArchivist/snscrape/issues/996#issuecomment-1615937362
+        next to test: https://cdn.embedly.com/widgets/media.html?&schema=twitter&url=https://twitter.com/bellingcat/status/1674700676612386816
         """
-        return False
-        # https://stackoverflow.com/a/71867055/6196010
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/114.0",
+            "Accept": "*/*",
+            "Accept-Language": "en-US,en;q=0.5",
+            "Accept-Encoding": "gzip, deflate, br",
+            "Origin": "https://platform.twitter.com",
+            "Connection": "keep-alive",
+            "Referer": "https://platform.twitter.com/",
+            "Sec-Fetch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "cross-site",
+            "Pragma": "no-cache",
+            "Cache-Control": "no-cache",
+            "TE": "trailers"
+        }
         logger.debug(f"Trying twitter hack for {url=}")
         result = Metadata()
 
-        hack_url = f"https://cdn.syndication.twimg.com/tweet?id={tweet_id}"
+        hack_url = f"https://cdn.syndication.twimg.com/tweet-result?id={tweet_id}"
         r = requests.get(hack_url)
         if r.status_code != 200: return False
         tweet = r.json()
 
         urls = []
-        for p in tweet["photos"]:
+        for p in tweet.get("photos", []):
             urls.append(p["url"])
 
         # 1 tweet has 1 video max
@@ -113,14 +129,18 @@ class TwitterArchiver(Archiver):
 
         logger.debug(f"Twitter hack got {urls=}")
 
-        for u in urls:
-            media = Media()
+        for i, u in enumerate(urls):
+            media = Media(filename="")
             media.set("src", u)
-            media.filename = self.download_from_url(u, f'{slugify(url)}_{i}', item)
+            ext = ""
+            if (mtype := mimetypes.guess_type(u)[0]):
+                ext = mimetypes.guess_extension(mtype)
+
+            media.filename = self.download_from_url(u, f'{slugify(url)}_{i}{ext}', item)
             result.add_media(media)
 
-        result.set_content(json.dumps(tweet, ensure_ascii=False)).set_timestamp(datetime.strptime(tweet["created_at"], "%Y-%m-%dT%H:%M:%S.%fZ"))
-        return result
+        result.set_title(tweet.get("text")).set_content(json.dumps(tweet, ensure_ascii=False)).set_timestamp(datetime.strptime(tweet["created_at"], "%Y-%m-%dT%H:%M:%S.%fZ"))
+        return result.success("twitter-hack")
 
     def get_username_tweet_id(self, url):
         # detect URLs that we definitely cannot handle

src/auto_archiver/databases/gsheet_db.py

@@ -67,7 +67,7 @@ class GsheetsDb(Database):
         batch_if_valid('title', item.get_title())
         batch_if_valid('text', item.get("content", ""))
         batch_if_valid('timestamp', item.get_timestamp())
-        batch_if_valid('hash', media.get("hash", "not-calculated"))
+        if media: batch_if_valid('hash', media.get("hash", "not-calculated"))
 
         # merge all pdq hashes into a single string, if present
         pdq_hashes = []

src/auto_archiver/version.py

@@ -3,7 +3,7 @@ _MAJOR = "0"
 _MINOR = "5"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "25"
+_PATCH = "27"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""