renamed 'archive_media' and 'media' to avoid name collision, changed scope of test fixture controller to 'function' so that db is fresh for each executed test

cisticola/scraper/base.py

@@ -69,7 +69,7 @@ class Scraper:
 
         return blob, content_type, key
 
-    def archive_media(self, blob: bytes, content_type: str, key: str) -> str:
+    def archive_blob(self, blob: bytes, content_type: str, key: str) -> str:
 
         filename = self.__version__.replace(' ', '_') + '/' + key
 
@@ -83,7 +83,7 @@ class Scraper:
     def can_handle(self, channel: Channel) -> bool:
         raise NotImplementedError
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
         raise NotImplementedError
 
 
@@ -103,7 +103,7 @@ class ScraperController:
         self.scrapers.extend(scraper)
     
     @logger.catch
-    def scrape_channels(self, channels: List[Channel], media: bool = True):
+    def scrape_channels(self, channels: List[Channel], archive_media: bool = True):
         if self.session is None:
             logger.error("No DB session")
             return
@@ -128,7 +128,7 @@ class ScraperController:
                     else:
                         since = None
 
-                    posts = scraper.get_posts(channel, since=since, media=media)
+                    posts = scraper.get_posts(channel, since=since, archive_media=archive_media)
 
                     for post in posts:
                         session.add(post)

cisticola/scraper/bitchute.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 import time
 import re 
 from html.parser import HTMLParser
@@ -22,7 +22,7 @@ class BitchuteScraper(Scraper):
 
         return username
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
 
         session = requests.Session()
         session.headers.update(self.headers)
@@ -43,11 +43,11 @@ class BitchuteScraper(Scraper):
 
             archived_urls = {}
 
-            if media:
+            if archive_media:
                 if 'video_url' in post:
                     url = post['video_url']
                     media_blob, content_type, key = self.url_to_blob(url)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[url] = archived_url
 
             yield ScraperResult(
@@ -56,7 +56,7 @@ class BitchuteScraper(Scraper):
                 channel=channel.id,
                 platform_id=post['id'],
                 date=datetime.fromtimestamp(post['timestamp']),
-                date_archived=datetime.now(),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=json.dumps(post),
                 archived_urls=archived_urls)
 

cisticola/scraper/gab.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 import json
 from typing import Generator
 
@@ -16,7 +16,7 @@ class GabScraper(Scraper):
 
         return username
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
         client = Garc(profile = 'main')
         username = GabScraper.get_username_from_url(channel.url)
 
@@ -29,7 +29,7 @@ class GabScraper(Scraper):
             media_urls = []
             archived_urls = {}
 
-            if media:
+            if archive_media:
 
                 media_urls.extend([p['url'] for p in post['media_attachments']])
 
@@ -38,7 +38,7 @@ class GabScraper(Scraper):
 
                 for url in media_urls:
                     media_blob, content_type, key = self.url_to_blob(url)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[url] = archived_url
 
             yield ScraperResult(
@@ -46,8 +46,8 @@ class GabScraper(Scraper):
                 platform="Gab",
                 channel=channel.id,
                 platform_id=post['id'],
-                date=datetime.fromisoformat(post['created_at'].replace("Z", "+00:00")).replace(tzinfo = None),
-                date_archived=datetime.now(),
+                date=datetime.fromisoformat(post['created_at'].replace("Z", "+00:00")).replace(tzinfo=timezone.utc),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=json.dumps(post),
                 archived_urls=archived_urls)
 

cisticola/scraper/gettr.py

@@ -1,6 +1,6 @@
-from datetime import datetime
+from datetime import datetime, timezone
 import json
-from typing import Generator, Tuple
+from typing import Generator
 from urllib.parse import urlparse
 
 from gogettr import PublicClient
@@ -19,7 +19,7 @@ class GettrScraper(Scraper):
 
         return username
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
         client = PublicClient()
         username = GettrScraper.get_username_from_url(channel.url)
         scraper = client.user_activity(username=username, type="posts")
@@ -30,25 +30,25 @@ class GettrScraper(Scraper):
 
             archived_urls = {}
 
-            if media:
+            if archive_media:
 
                 if 'imgs' in post:
                     for img in post['imgs']:
                         url = "https://media.gettr.com/" + img
                         media_blob, content_type, key = self.url_to_blob(url)
-                        archived_url = self.archive_media(media_blob, content_type, key)
+                        archived_url = self.archive_blob(media_blob, content_type, key)
                         archived_urls[img] = archived_url
 
                 if 'main' in post:
                     url = "https://media.gettr.com/" + post['main']
                     media_blob, content_type, key = self.url_to_blob(url)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[post['main']] = archived_url
 
                 if 'vid' in post:
                     url = "https://media.gettr.com/" + post['vid']
                     media_blob, content_type, key = self.m3u8_url_to_blob(url)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[post['vid']] = archived_url
 
             yield ScraperResult(
@@ -57,7 +57,7 @@ class GettrScraper(Scraper):
                 channel=channel.id,
                 platform_id=post['_id'],
                 date=datetime.fromtimestamp(post['cdate']/1000.),
-                date_archived=datetime.now(),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=json.dumps(post),
                 archived_urls=archived_urls)
 

cisticola/scraper/odysee.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 import json
 from typing import Generator
 from urllib.parse import urlparse
@@ -19,7 +19,7 @@ class OdyseeScraper(Scraper):
 
         return username
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
 
         username = OdyseeScraper.get_username_from_url(channel.url)
         odysee_channel = OdyseeChannel(channel_name = username)
@@ -32,7 +32,7 @@ class OdyseeScraper(Scraper):
 
             archived_urls = {}
 
-            if media:
+            if archive_media:
                 url = video.info['streaming_url']
 
                 # Check if file is a video file or an m3u8 file
@@ -42,7 +42,7 @@ class OdyseeScraper(Scraper):
                 else:
                     media_blob, content_type, key = self.url_to_blob(url)
 
-                archived_url = self.archive_media(media_blob, content_type, key)
+                archived_url = self.archive_blob(media_blob, content_type, key)
                 archived_urls[url] = archived_url
 
             all_comments = video.get_all_comments()
@@ -53,7 +53,7 @@ class OdyseeScraper(Scraper):
                 channel=channel.id,
                 platform_id=video.info['claim_id'],
                 date=datetime.fromtimestamp(video.info['created']),
-                date_archived=datetime.now(),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=json.dumps(video.info),
                 archived_urls=archived_urls)
 

cisticola/scraper/rumble.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 import json
 from typing import Generator, Tuple
 import tempfile
@@ -22,7 +22,7 @@ class RumbleScraper(Scraper):
 
         return username
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
 
         username = RumbleScraper.get_username_from_url(channel.url)
         scraper = get_channel_videos(username)
@@ -33,12 +33,12 @@ class RumbleScraper(Scraper):
 
             archived_urls = {}
 
-            if media:
+            if archive_media:
 
                 url = post['media_url']
 
                 media_blob, content_type, key = self.url_to_blob(url)
-                archived_url = self.archive_media(media_blob, content_type, key)
+                archived_url = self.archive_blob(media_blob, content_type, key)
                 archived_urls[post['media_url']] = archived_url
 
             yield ScraperResult(
@@ -46,8 +46,8 @@ class RumbleScraper(Scraper):
                 platform="Rumble",
                 channel=channel.id,
                 platform_id=post['media_url'].split('/')[-2],
-                date=datetime.fromisoformat(post['datetime']).replace(tzinfo=None),
-                date_archived=datetime.now(),
+                date=datetime.fromisoformat(post['datetime']).replace(tzinfo=timezone.utc),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=json.dumps(post),
                 archived_urls=archived_urls)
 

cisticola/scraper/telegram_snscrape.py

@@ -14,7 +14,7 @@ class TelegramSnscrapeScraper(Scraper):
         if channel.platform == "Telegram" and channel.public and not channel.chat:
             return True
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
         scr = snscrape.modules.telegram.TelegramChannelScraper(
             channel.screenname)
 
@@ -29,18 +29,18 @@ class TelegramSnscrapeScraper(Scraper):
 
             archived_urls = {}
 
-            if media:
+            if archive_media:
 
                 for image_url in post.images:
                     logger.debug(f'Archiving image: {image_url}')
                     media_blob, content_type, key = self.url_to_blob(image_url)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[image_url] = archived_url
 
                 if post.video:
                     logger.debug(f'Archiving video: {post.video}')
                     media_blob, content_type, key = self.url_to_blob(post.video)
-                    archived_url = self.archive_media(media_blob, content_type, key)
+                    archived_url = self.archive_blob(media_blob, content_type, key)
                     archived_urls[post.video] = archived_url
 
             yield ScraperResult(

cisticola/scraper/telegram_telethon.py

@@ -26,7 +26,7 @@ class TelegramTelethonScraper(Scraper):
         if channel.platform == "Telegram" and channel.public and not channel.chat:
             return True
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
 
         username = self.get_username_from_url(channel.url)
 
@@ -47,7 +47,7 @@ class TelegramTelethonScraper(Scraper):
 
                 archived_urls = {}
 
-                if media:
+                if archive_media:
 
                     if post.media is not None:
                         with tempfile.TemporaryDirectory() as temp_dir:
@@ -61,7 +61,7 @@ class TelegramTelethonScraper(Scraper):
                                 blob = f.read()
                         
                         # TODO specify Content-Type
-                        archived_url = self.archive_media(blob = blob, content_type = '', key = output_file_with_ext)
+                        archived_url = self.archive_blob(blob = blob, content_type = '', key = output_file_with_ext)
                         archived_urls[post_url] = archived_url
 
                 yield ScraperResult(

cisticola/scraper/twitter.py

@@ -12,7 +12,7 @@ class TwitterScraper(Scraper):
     """An implementation of a Scraper for Twitter, using snscrape library"""
     __version__ = "TwitterScraper 0.0.1"
 
-    def get_posts(self, channel: Channel, since: ScraperResult = None, media: bool = True) -> Generator[ScraperResult, None, None]:
+    def get_posts(self, channel: Channel, since: ScraperResult = None, archive_media: bool = True) -> Generator[ScraperResult, None, None]:
         scraper = TwitterProfileScraper(channel.platform_id)
 
         first = True
@@ -28,24 +28,26 @@ class TwitterScraper(Scraper):
 
             archived_urls = {}
 
-            if tweet.media:
-                for media in tweet.media:
-                    if type(media) == Video:
-                        variant = max(
-                            [v for v in media.variants if v.bitrate], key=lambda v: v.bitrate)
-                        url = variant.url
-                    elif type(media) == Gif:
-                        url = media.variants[0].url
-                    elif type(media) == Photo:
-                        url = media.fullUrl
-                    else:
-                        logger.warning(f"Could not get media URL of {media}")
-                        url = None
+            if archive_media:
 
-                    if url is not None:
-                        media_blob, content_type, key = self.url_to_blob(url)
-                        archived_url = self.archive_media(media_blob, content_type, key)
-                        archived_urls[url] = archived_url
+                if tweet.media:
+                    for media in tweet.media:
+                        if type(media) == Video:
+                            variant = max(
+                                [v for v in media.variants if v.bitrate], key=lambda v: v.bitrate)
+                            url = variant.url
+                        elif type(media) == Gif:
+                            url = media.variants[0].url
+                        elif type(media) == Photo:
+                            url = media.fullUrl
+                        else:
+                            logger.warning(f"Could not get media URL of {media}")
+                            url = None
+
+                        if url is not None:
+                            media_blob, content_type, key = self.url_to_blob(url)
+                            archived_url = self.archive_blob(media_blob, content_type, key)
+                            archived_urls[url] = archived_url
 
             yield ScraperResult(
                 scraper=self.__version__,
@@ -53,7 +55,7 @@ class TwitterScraper(Scraper):
                 channel=channel.id,
                 platform_id=tweet.id,
                 date=tweet.date,
-                date_archived=datetime.now(),
+                date_archived=datetime.now(timezone.utc),
                 raw_data=tweet.json(),
                 archived_urls=archived_urls)
 

russian_telegram_ingest.py

@@ -13,48 +13,48 @@ logger.add(sys.stderr, level="INFO")
 logger.add("../russian_telegram_ingest.log")
 
 test_channels = [
-    # Channel(
-    #     id=0, 
-    #     name="QAnon Россия", 
-    #     platform_id=-1001319637748,
-    #     category="Qanon", 
-    #     followers=94048, 
-    #     platform="Telegram",
-    #     url="https://t.me/qanonrus", 
-    #     screenname="qanonrus", 
-    #     country="RU",
-    #     influencer=None, 
-    #     public=True, 
-    #     chat=False,
-    #     notes=""),
-    # Channel(
-    #     id=1, 
-    #     name="The Great Awakening | Q", 
-    #     platform_id=-1001325597521,
-    #     category="Qanon", 
-    #     followers=5715,
-    #     platform="Telegram",
-    #     url="https://t.me/greatawakin", 
-    #     screenname="greatawakin", 
-    #     country="RU",
-    #     influencer=None, 
-    #     public=True, 
-    #     chat=False, 
-    #     notes=""),
-    # Channel(
-    #     id=2, 
-    #     name="Великое Пробуждение", 
-    #     platform_id=-1001285898079,
-    #     category="Qanon", 
-    #     followers=5861, 
-    #     platform="Telegram",
-    #     url="https://t.me/greatawakeningrus", 
-    #     screenname="greatawakeningrus", 
-    #     country="RU",
-    #     influencer=None, 
-    #     public=True, 
-    #     chat=False, 
-    #     notes=""),
+    Channel(
+        id=0, 
+        name="QAnon Россия", 
+        platform_id=-1001319637748,
+        category="Qanon", 
+        followers=94048, 
+        platform="Telegram",
+        url="https://t.me/qanonrus", 
+        screenname="qanonrus", 
+        country="RU",
+        influencer=None, 
+        public=True, 
+        chat=False,
+        notes=""),
+    Channel(
+        id=1, 
+        name="The Great Awakening | Q", 
+        platform_id=-1001325597521,
+        category="Qanon", 
+        followers=5715,
+        platform="Telegram",
+        url="https://t.me/greatawakin", 
+        screenname="greatawakin", 
+        country="RU",
+        influencer=None, 
+        public=True, 
+        chat=False, 
+        notes=""),
+    Channel(
+        id=2, 
+        name="Великое Пробуждение", 
+        platform_id=-1001285898079,
+        category="Qanon", 
+        followers=5861, 
+        platform="Telegram",
+        url="https://t.me/greatawakeningrus", 
+        screenname="greatawakeningrus", 
+        country="RU",
+        influencer=None, 
+        public=True, 
+        chat=False, 
+        notes=""),
     Channel(
         id=3, 
         name="T🕊Редакция Президент Гордон🕊", 
@@ -134,5 +134,5 @@ controller.register_scraper(telegram)
 engine = create_engine('sqlite:///russian_telegram.db')
 controller.connect_to_db(engine)
 
-controller.scrape_channels(test_channels)
+controller.scrape_channels(test_channels, archive_media = False)
 

test.py

@@ -1,4 +1,5 @@
 from sqlalchemy import create_engine
+from loguru import logger
 
 from cisticola.base import Channel
 from cisticola.scraper import (
@@ -12,6 +13,8 @@ from cisticola.scraper import (
     TelegramTelethonScraper,
     TwitterScraper)
 
+logger.add("../test.log")
+
 test_channels = [
     Channel(
         id=0, 
@@ -118,12 +121,12 @@ scrapers = [
     OdyseeScraper(),
     RumbleScraper(),
     TelegramSnscrapeScraper(),
-    TwitterScraper()
-    TelegramTelethonScraper()]
+    TelegramTelethonScraper(),
+    TwitterScraper()]
 
 controller.register_scrapers(scrapers)
 
 engine = create_engine('sqlite:///test3.db')
 controller.connect_to_db(engine)
 
-controller.scrape_channels(test_channels, media = True)
+controller.scrape_channels(test_channels, archive_media = False)

tests/conftest.py

@@ -113,7 +113,7 @@ TWITTER_CHANNEL_KWARGS = {
 
 #+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++#
 
-@pytest.fixture(scope='package')
+@pytest.fixture(scope='function')
 def controller(tmpdir_factory):
 
     """Initialize ScraperController and SQLite database file to be used for all 

tests/scraper/bitchute.py

@@ -5,10 +5,10 @@ def test_scrape_bitchute_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['bitchute'])]
     controller.register_scraper(scraper = BitchuteScraper())
-    controller.scrape_channels(channels = channels, media = False)
-    
+    controller.scrape_channels(channels = channels, archive_media = False)
+
 def test_scrape_bitchute_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['bitchute'])]
     controller.register_scraper(scraper = BitchuteScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/gab.py

@@ -5,10 +5,10 @@ def test_scrape_gab_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['gab'])]
     controller.register_scraper(scraper = GabScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_gab_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['gab'])]
     controller.register_scraper(scraper = GabScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/gettr.py

@@ -5,10 +5,10 @@ def test_scrape_gettr_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['gettr'])]
     controller.register_scraper(scraper = GettrScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_gettr_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['gettr'])]
     controller.register_scraper(scraper = GettrScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/odysee.py

@@ -5,10 +5,10 @@ def test_scrape_odysee_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['odysee'])]
     controller.register_scraper(scraper = OdyseeScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_odysee_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['odysee'])]
     controller.register_scraper(scraper = OdyseeScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/rumble.py

@@ -5,10 +5,10 @@ def test_scrape_rumble_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['rumble'])]
     controller.register_scraper(scraper = RumbleScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_rumble_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['rumble'])]
     controller.register_scraper(scraper = RumbleScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/telegram_snscrape.py

@@ -5,10 +5,10 @@ def test_scrape_telegram_snscrape_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['telegram'])]
     controller.register_scraper(scraper = TelegramSnscrapeScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_telegram_snscrape_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['telegram'])]
     controller.register_scraper(scraper = TelegramSnscrapeScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/telegram_telethon.py

@@ -5,10 +5,10 @@ def test_scrape_telegram_telethon_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['telegram'])]
     controller.register_scraper(scraper = TelegramTelethonScraper())
-    controller.scrape_channels(channels = channels, media = False)
-    
+    controller.scrape_channels(channels = channels, archive_media = False)
+
 def test_scrape_telegram_telethon_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['telegram'])]
     controller.register_scraper(scraper = TelegramTelethonScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)

tests/scraper/twitter.py

@@ -5,10 +5,10 @@ def test_scrape_twitter_channel_no_media(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['twitter'])]
     controller.register_scraper(scraper = TwitterScraper())
-    controller.scrape_channels(channels = channels, media = False)
+    controller.scrape_channels(channels = channels, archive_media = False)
 
 def test_scrape_twitter_channel(controller, channel_kwargs):
 
     channels = [Channel(**channel_kwargs['twitter'])]
     controller.register_scraper(scraper = TwitterScraper())
-    controller.scrape_channels(channels = channels, media = True)
+    controller.scrape_channels(channels = channels, archive_media = True)