added Bitchute scraper, minor change to Bitchute scraper to correctly extract author name and id

cisticola/scraper/bitchute.py

@@ -236,8 +236,8 @@ def append_details(video, detail):
         video["video_url"] = soup.select_one("video#player source").get("src")
         video["thumbnail_image"] = soup.select_one("video#player").get("poster")
         video["subject"] = soup.select_one("h1#video-title").text
-        video["author"] = soup.select_one("div.channel-banner p.name a").text
-        video["author_id"] = soup.select_one("div.channel-banner p.name a").get("href").split("/")[2]
+        video["author_id"] = soup.select_one("p.owner a").get("href").split("/")[2]
+        video["author"] = soup.select_one("div.channel-banner p.name a").get("href").split("/")[2]
         video["body"] = soup.select_one("div#video-description").encode_contents().decode("utf-8").strip()
 
         # we need *two more requests* to get the comment count and like/dislike counts

cisticola/transformer/__init__.py

@@ -1,2 +1,3 @@
 from . import base 
-from .twitter import TwitterTransformer
+from .twitter import TwitterTransformer
+from .bitchute import BitchuteTransformer

cisticola/transformer/bitchute.py

@@ -0,0 +1,51 @@
+import json
+from loguru import logger
+from typing import Generator
+
+from bs4 import BeautifulSoup 
+
+from cisticola.transformer.base import Transformer 
+from cisticola.base import ScraperResult, TransformedResult, Image, Video, Media
+
+class BitchuteTransformer(Transformer):
+    """A Bitchute specific ScraperResult, with a method ETL/transforming"""
+
+    __version__ = "BitchuteTransformer 0.0.1"
+
+    def can_handle(self, data: ScraperResult) -> bool:
+        scraper = data.scraper.split(' ')
+        if scraper[0] == "BitchuteScraper":
+            return True
+
+        return False        
+
+    def transform_media(self, data: ScraperResult, transformed: TransformedResult) -> Generator[Media, None, None]:
+        raw = json.loads(data.raw_data)
+
+        orig = raw['video_url']
+        new = data.archived_urls[orig]
+
+        m = Video(url=new, post=transformed.id, raw_id=data.id, original_url=orig)
+
+        yield m
+
+    def transform(self, data: ScraperResult) -> TransformedResult:
+        raw = json.loads(data.raw_data)
+
+        soup = BeautifulSoup(raw['body'], features = 'html.parser')
+        content = soup.find_all('p')[-1].text
+
+        transformed = TransformedResult(
+            raw_id=data.id,
+            scraper=data.scraper,
+            transformer=self.__version__,
+            platform=data.platform,
+            channel=data.channel,
+            date=data.date,
+            date_archived=data.date_archived,
+            url=raw['url'],
+            content=content,
+            author_id=raw['author_id'],
+            author_username=raw['author'])
+
+        return transformed