Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-04-20 15:55:49 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Only import yt-dlp if we're using it

Browse Source
This commit is contained in:
Alex Dempsey 2025-03-04 13:58:52 -08:00 committed by Misty De Méo
parent 01e19fdf70
commit 72e549694c
2 changed files with 36 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
brozzler/worker.py
View File

@ -39,7 +39,6 @@ import urlcanon
from requests.structures import CaseInsensitiveDict
import rethinkdb as rdb
from . import metrics
from . import ydl
r = rdb.RethinkDB()
@ -260,6 +259,38 @@ class BrozzlerWorker:
img.save(out, "jpeg", quality=95)
return out.getbuffer()
def should_ytdlp(self, logger, site, page, page_status, skip_av_seeds):
# called only after we've passed needs_browsing() check
if page_status != 200:
logger.info("skipping ytdlp: non-200 page status", page_status=page_status)
return False
if site.skip_ytdlp:
logger.info("skipping ytdlp: site marked skip_ytdlp")
return False
ytdlp_url = page.redirect_url if page.redirect_url else page.url
if "chrome-error:" in ytdlp_url:
return False
ytdlp_seed = (
site["metadata"]["ait_seed_id"]
if "metadata" in site and "ait_seed_id" in site["metadata"]
else None
)
# TODO: develop UI and refactor
if ytdlp_seed:
if site.skip_ytdlp is None and ytdlp_seed in skip_av_seeds:
logger.info("skipping ytdlp: site in skip_av_seeds")
site.skip_ytdlp = True
return False
else:
site.skip_ytdlp = False
return True
@metrics.brozzler_page_processing_duration_seconds.time()
@metrics.brozzler_in_progress_pages.track_inprogress()
def brozzle_page(
@ -293,10 +324,12 @@ class BrozzlerWorker:
except brozzler.PageInterstitialShown:
page_logger.info("page interstitial shown (http auth)")
if enable_youtube_dl and ydl.should_ytdlp(
site, page, status_code, self._skip_av_seeds
if enable_youtube_dl and self.should_ytdlp(
page_logger, site, page, status_code, self._skip_av_seeds
):
try:
from . import ydl
ydl_outlinks = ydl.do_youtube_dl(
self, site, page, self._ytdlp_proxy_endpoints
)

33
brozzler/ydl.py
View File

@ -43,39 +43,6 @@ YTDLP_MAX_REDIRECTS = 5
logger = structlog.get_logger(logger_name=__name__)
def should_ytdlp(site, page, page_status, skip_av_seeds):
# called only after we've passed needs_browsing() check
if page_status != 200:
logger.info("skipping ytdlp: non-200 page status", page_status=page_status)
return False
if site.skip_ytdlp:
logger.info("skipping ytdlp: site marked skip_ytdlp")
return False
ytdlp_url = page.redirect_url if page.redirect_url else page.url
if "chrome-error:" in ytdlp_url:
return False
ytdlp_seed = (
site["metadata"]["ait_seed_id"]
if "metadata" in site and "ait_seed_id" in site["metadata"]
else None
)
# TODO: develop UI and refactor
if ytdlp_seed:
if site.skip_ytdlp is None and ytdlp_seed in skip_av_seeds:
logger.info("skipping ytdlp: site in skip_av_seeds")
site.skip_ytdlp = True
return False
else:
site.skip_ytdlp = False
return True
def isyoutubehost(url):
# split 1 splits scheme from url, split 2 splits path from hostname, split 3 splits query string on hostname
return "youtube.com" in url.split("//")[-1].split("/")[0].split("?")[0]