Barbagus
56c1e8468a
Significant rewrite after model modification: introducing `*Sources` objects that encapsulate metadata and fetch information (urls, protocols). The API (#20) is organized as pipe elements with sources being what flows through the pipe. 1. fetch program sources 2. fetch rendition sources 3. fetch variant sources 4. fetch targets 5. process (download+mux) targets Some user selection filter or modifiers could then be applied at any step of the pipe. Our __main__.py is an implementation of that scheme. Implied modifications include: - Later failure on unsupported protocols, used to be in `api`, now in `hls`. This offers the possibility to filter and/or support them later. - Give up honoring the http ranges for mp4 download, stream-download them by fixed chunk instead. - Cleaning up of the `hls` module moving the main download function to __init__ and specific (mp4/vtt) download functions to a new `download` module. On the side modifications include: - The progress handler showing downloading rates. - The naming utilities providing rendition and variant code insertion. - Download parts to working directories and skip unnecessary re-downloads on failure. This was a big change for a single commit... too big of a change maybe.
53 lines
1.4 KiB
Python
53 lines
1.4 KiB
Python
# License: GNU AGPL v3: http://www.gnu.org/licenses/
|
|
# This file is part of `delarte` (https://git.afpy.org/fcode/delarte.git)
|
|
|
|
"""Provide download utilities."""
|
|
import os
|
|
|
|
from . import subtitles
|
|
|
|
_CHUNK = 64 * 1024
|
|
|
|
|
|
def download_mp4_media(url, file_name, http_session, on_progress):
|
|
"""Download a MP4 (video or audio) to given file."""
|
|
on_progress(file_name, 0, 0)
|
|
|
|
if os.path.isfile(file_name):
|
|
on_progress(file_name, 1, 1)
|
|
return
|
|
|
|
temp_file = f"{file_name}.tmp"
|
|
|
|
with open(temp_file, "w+b") as f:
|
|
r = http_session.get(url, timeout=5, stream=True)
|
|
r.raise_for_status()
|
|
total = int(r.headers["content-length"])
|
|
|
|
for content in r.iter_content(_CHUNK):
|
|
f.write(content)
|
|
on_progress(file_name, f.tell(), total)
|
|
|
|
os.rename(temp_file, file_name)
|
|
|
|
|
|
def download_vtt_media(url, file_name, http_session, on_progress):
|
|
"""Download a VTT and SRT-convert it to to given file."""
|
|
on_progress(file_name, 0, 0)
|
|
|
|
if os.path.isfile(file_name):
|
|
on_progress(file_name, 1, 1)
|
|
return
|
|
|
|
temp_file = f"{file_name}.tmp"
|
|
|
|
with open(temp_file, "w", encoding="utf-8") as f:
|
|
r = http_session.get(url, timeout=5)
|
|
r.raise_for_status()
|
|
r.encoding = "utf-8"
|
|
|
|
subtitles.convert(r.text, f)
|
|
on_progress(file_name, f.tell(), f.tell())
|
|
|
|
os.rename(temp_file, file_name)
|