New possible extract method (V2 Anon)

twExtract/__init__.py

@@ -16,6 +16,9 @@ userIDregex = r"\/i\/user\/(\d+)"
 v2Features='{"longform_notetweets_inline_media_enabled":true,"super_follow_badge_privacy_enabled":true,"longform_notetweets_rich_text_read_enabled":true,"super_follow_user_api_enabled":true,"super_follow_tweet_api_enabled":true,"android_graphql_skip_api_media_color_palette":true,"creator_subscriptions_tweet_preview_api_enabled":true,"freedom_of_speech_not_reach_fetch_enabled":true,"creator_subscriptions_subscription_count_enabled":true,"tweetypie_unmention_optimization_enabled":true,"longform_notetweets_consumption_enabled":true,"subscriptions_verification_info_enabled":true,"blue_business_profile_image_shape_enabled":true,"tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled":true,"super_follow_exclusive_tweet_notifications_enabled":true}'
 v2graphql_api="2OOZWmw8nAtUHVnXXQhgaA"
 
+v2AnonFeatures='{"creator_subscriptions_tweet_preview_api_enabled":true,"c9s_tweet_anatomy_moderator_badge_enabled":true,"tweetypie_unmention_optimization_enabled":true,"responsive_web_edit_tweet_api_enabled":true,"graphql_is_translatable_rweb_tweet_is_translatable_enabled":true,"view_counts_everywhere_api_enabled":true,"longform_notetweets_consumption_enabled":true,"responsive_web_twitter_article_tweet_consumption_enabled":false,"tweet_awards_web_tipping_enabled":false,"responsive_web_home_pinned_timelines_enabled":true,"freedom_of_speech_not_reach_fetch_enabled":true,"standardized_nudges_misinfo":true,"tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled":true,"longform_notetweets_rich_text_read_enabled":true,"longform_notetweets_inline_media_enabled":true,"responsive_web_graphql_exclude_directive_enabled":true,"verified_phone_label_enabled":false,"responsive_web_media_download_video_enabled":false,"responsive_web_graphql_skip_user_profile_image_extensions_enabled":false,"responsive_web_graphql_timeline_navigation_enabled":true,"responsive_web_enhance_cards_enabled":false}'
+v2AnonGraphql_api="5GOHgZe-8U2j5sVHQzEm9A"
+
 class TwExtractError(Exception):
     def __init__(self, code, message):
         self.code = code
@@ -27,7 +30,7 @@ class TwExtractError(Exception):
 def getGuestToken():
     global guestToken
     if guestToken is None:
-        r = requests.post("https://api.twitter.com/1.1/guest/activate.json", headers={"Authorization":bearer})
+        r = requests.post("https://api.twitter.com/1.1/guest/activate.json", headers={"Authorization":v2Bearer})
         guestToken = json.loads(r.text)["guest_token"]
     return guestToken
 
@@ -197,6 +200,43 @@ def extractStatusV2(url,workaroundTokens):
         return tweet
     raise TwExtractError(400, "Extract error")
 
+def extractStatusV2Anon(url):
+    # get tweet ID
+    m = re.search(pathregex, url)
+    if m is None:
+        raise TwExtractError(400, "Extract error")
+    twid = m.group(2)
+
+    guestToken = getGuestToken()
+
+    # get tweet
+    try:
+        vars = json.loads('{"tweetId":"0","withCommunity":false,"includePromotedContent":false,"withVoice":false}')
+        vars['tweetId'] = str(twid)
+        tweet = requests.get(f"https://api.twitter.com/graphql/{v2AnonGraphql_api}/TweetResultByRestId?variables={urllib.parse.quote(json.dumps(vars))}&features={urllib.parse.quote(v2AnonFeatures)}", headers={"Authorization":v2Bearer,"x-twitter-active-user":"yes","x-guest-token":guestToken,"x-twitter-client-language":"en","User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/116.0"})
+        try:
+            rateLimitRemaining = tweet.headers.get("x-rate-limit-remaining")
+            print(f"Twitter Anon Token Rate limit remaining: {rateLimitRemaining}")
+        except: # for some reason the header is not always present
+            pass
+        if tweet.status_code == 429:
+            raise TwExtractError(400, "Extract error")
+        output = tweet.json()
+        
+        if "errors" in output:
+            raise TwExtractError(400, "Extract error")
+        entry=output['data']['tweetResult']
+        tweetEntry=None
+        result = entry['result']
+        if '__typename' in result and result['__typename'] == 'TweetWithVisibilityResults':
+            result=result['tweet']
+        if 'rest_id' in result and result['rest_id'] == twid:
+            tweetEntry=result
+        tweet=tweetEntry
+    except Exception as e:
+        raise TwExtractError(400, "Extract error")
+    return tweet
+
 def extractStatusV2Legacy(url,workaroundTokens):
     tweet = extractStatusV2(url,workaroundTokens)
     if 'errors' in tweet or 'legacy' not in tweet:
@@ -216,6 +256,25 @@ def extractStatusV2Legacy(url,workaroundTokens):
         tweet['legacy']['card'] = tweet['tweet_card']['legacy']
     return tweet['legacy']
 
+def extractStatusV2AnonLegacy(url,workaroundTokens):
+    tweet = extractStatusV2Anon(url)
+    if 'errors' in tweet or 'legacy' not in tweet:
+        if 'errors' in tweet:
+            raise TwExtractError(400, "Extract error: "+json.dumps(tweet['errors']))
+        else:
+            raise TwExtractError(400, "Extract error (no legacy data)")
+    tweet['legacy']['user'] = tweet["core"]["user_results"]["result"]["legacy"]
+    tweet['legacy']['user']['profile_image_url'] = tweet['legacy']['user']['profile_image_url_https']
+    if 'card' in tweet:
+        tweet['legacy']['card'] = tweet['card']['legacy']
+    if 'extended_entities' in tweet['legacy']:
+        tweet['legacy']['extended_entities'] = {'media':tweet['legacy']['extended_entities']['media']}
+        for media in tweet['legacy']['extended_entities']['media']:
+            media['media_url'] = media['media_url_https']
+    if 'tweet_card' in tweet:
+        tweet['legacy']['card'] = tweet['tweet_card']['legacy']
+    return tweet['legacy']
+
 def extractStatus(url,workaroundTokens=None):
     methods=[extractStatus_syndication,extractStatusV2Legacy,extractStatus_twExtractProxy]
     for method in methods: