def create_episode(
db: Session,
podcast_id: int,
title: str,
subtitle: str,
summary: str,
long_summary: str,
duration: timedelta,
upload_file: UploadFile,
) -> models.Episode:
db_episode = models.Episode(
summary=summary,
long_summary=long_summary,
title=title,
subtitle=subtitle,
url="",
size=0,
duration=duration,
podcast_id=podcast_id,
)
db.add(db_episode)
db.commit()
db.refresh(db_episode)
filename = upload_file.filename
upload_dir = Path(UPLOAD_DIR) / f"podcast_{podcast_id}" / f"episode_{db_episode.id}"
upload_path = upload_dir / filename
if not upload_dir == upload_path.parent:
raise HTTPException(status_code=404, detail="Invalid filename")
try:
upload_dir.mkdir(parents=True, exist_ok=True)
with upload_path.open("wb") as buffer:
shutil.copyfileobj(upload_file.file, buffer)
except OSError as e:
db.delete(db_episode)
upload_file.file.close()
logging.exception("Unable to store upload to disk. %s", e)
raise HTTPException(500, "Unable to store upload to disk. " + str(e))
finally:
upload_file.file.close()
db_episode.url = "%s/download/podcast_%d/episode_%d/%s" % (
PUBLIC_URL,
podcast_id,
db_episode.id,
quote(filename),
)
db_episode.size = os.path.getsize(str(upload_path))
db.commit()
db.refresh(db_episode)
return db_episode
def __init__(self, anime_url: str):
"""
Constructor for AnimeScraper.
Scrapes some information about anime, which is used later for further
scraping and downloading.
:param anime_url: Anime URL
"""
# Soup object for scraping
anime_soup = BeautifulSoup(
requests.get(anime_url, headers=settings.REQUEST_HEADERS).text,
"html.parser",
)
# GET request parameters for ajax URL
id_ = anime_soup.find(id="movie_id")["value"]
alias = anime_soup.find(id="alias_anime")["value"]
last_ep = anime_soup.find(
id="episode_page").find_all("a")[-1]["ep_end"]
# We collect the list of all episodes and their links using this URL
ajax_url = (
"https://ajax.gogocdn.net/ajax/load-list-episode?ep_start=0&default_ep=0"
f"&ep_end={last_ep}&id={id_}&alias={alias}")
# Remove bad characters from anime title
t = anime_soup.title.text.replace("at Gogoanime",
"").replace("Watch ", "").strip()
t = re.sub('[<>?":/|]', "", t)
# Model object for anime. Episodes will be scraped and added to it
self.anime = mdl.Anime(title=t, url=anime_url, episodes=[])
ajax_soup = BeautifulSoup(
requests.get(ajax_url, headers=settings.REQUEST_HEADERS).text,
"html.parser",
)
# Collect information of all episodes for further scraping later
for li in reversed(ajax_soup.find_all("li")):
# Remove bad characters from scarped episode title
ep_title = re.sub('[<>?":/|]', "", " ".join(li.text.split()))
# Episode model object. Video data attribute will be set after scraping
# the specified range of episodes.
ep = mdl.Episode(title=f"{self.anime.title} - {ep_title}",
url="https://www.gogoanime.so{}".format(
li.find("a")["href"].strip()))
# Append to list of episodes in anime model object
self.anime.episodes.append(ep)
def test_episode_insert(db):
test_episode = {
"name": "TestEpisode",
"season": "3",
"nr": "1002",
"predecessor": "TestPrevEp",
"successor": "TestNextEp",
"imageLink": "-"
}
ep = models.Episode(**test_episode)
db.session.add(ep)
result = db.session.query(
models.Episode).filter(models.Episode.name == "TestEpisode").first()
TESTOR.assertEqual(result.season, "3")
TESTOR.assertEqual(result.nr, "1002")
TESTOR.assertEqual(result.predecessor, "TestPrevEp")
TESTOR.assertEqual(result.successor, "TestNextEp")
def select_episodes(): conn = None rows = None episodes = [] try: conn = db.connect() cur = conn.cursor() cur.execute(SQL_SELECT_EPISODE_RECORDS) rows = cur.fetchall() cur.close() except (Exception, psycopg2.DatabaseError) as error: print(error) traceback.print_exc() # likely a duplicate? finally: if conn is not None: conn.close() for row in rows: episodes.append(models.Episode(row)) return episodes
soup = BeautifulSoup(response.text, "html.parser")
text = [
str(script) for script in soup.find_all("script")
if ").innerHTML" in str(script)
][0]
text = "".join(text.rstrip("</script>").lstrip("<script>").split())
text = text.split("innerHTML=")[1].rstrip(";")
text = "".join(
[substr.strip('"').strip("'") for substr in text.split("+")])
download_link = f"https:{text}"
except Exception as e:
print(e)
return None
return download_link
if __name__ == "__main__":
# Example: https://streamtape.com/e/YqKyKxg23jivJDB/world-trigger-2nd-season-episode-10.mp4
epis = mdl.Episode(title="Test title",
url="Test URL",
video_data={
"embed-servers": {
"streamtape":
input("Enter streamtape embed URL: ")
}
})
print(get_download_link(epis))
if re.match("s\d+$", s) or re.match("www\d+$", s)
]
w3str = "www"
if len(w3str_possibles_list) != 0:
w3str = max(w3str_possibles_list, key=len)
download_link = "https://{}.mp4upload.com:{}/d/{}/video.mp4".format(
w3str, eval_items[eval_items.index(video_id) + 1], video_id)
except Exception as e:
print(e)
return None
return download_link
# A sample Mp4Upload embedded URL: https://www.mp4upload.com/embed-99r0hr81zk9k.html
if __name__ == "__main__":
print("\t\t=====================")
print("\t\t Mp4Upload Generator")
print("\t\t=====================")
epis = mdl.Episode(title="Test title",
url="Test URL",
video_data={
"embed-servers": {
"mp4upload":
input("\t- Enter Mp4Upload Embed URL: ")
}
})
d = get_download_link(epis)
print(f"- The generated download link: {d}")
:param ep: Episode model object
:return: Download link of video
"""
embed_url = ep.video_data.get("vidcdn")
if not embed_url:
return None
try:
soup = BeautifulSoup(
requests.get(embed_url, headers=settings.REQUEST_HEADERS).text,
"html.parser")
js_text = str(soup.find("div", class_="videocontent"))
download_link = re.findall("file: '(.+?)'", js_text)[0]
except Exception as e:
print(e)
return None
return download_link
# Example: https://vidstreaming.io/load.php?id=OTc2MzI=&title=Boruto%3A+Naruto+Next+Generations+Episode+1
if __name__ == "__main__":
epis = mdl.Episode(title="Test title",
url="Test URL",
video_data={
"embed-servers": {
"vidcdn": input("Enter vidcdn embed URL: ")
}
})
print(get_download_link(epis))
response = requests.get(embed_url, headers=settings.REQUEST_HEADERS)
# Return None if video server is not available
if "tb error" in response.text:
return None
video_details = re.findall("MDCore\|\|.+\|poster",
response.text)[0].split("|")
# Example:
# //s-delivery14.mxdcontent.net/v/59f0fcbf63176bff9792eb2b2c5218dd.mp4?
# s=dZk3d430Oi1bSCD5HfvMbA&e=1616377672&_t=1616359487
download_link = "https://{2}-{3}.{6}.{7}/v/{4}.{5}?{2}={9}&e={17}&{16}={18}".format(
*video_details)
except Exception as e:
print(e)
return None
return download_link
if __name__ == "__main__":
# Example: https://mixdrop.co/e/7rgov1qpuk4rq7
epis = mdl.Episode(title="Test episode",
url="Test URL",
video_data={
"embed-servers": {
"mixdrop": input("Enter mixdrop embed URL: ")
}
})
print(get_download_link(epis))