Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-02-23 08:09:48 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

mostly black'd

Browse Source
This commit is contained in:
Barbara Miller 2024-09-18 15:58:19 -07:00
parent 27cb104b45
commit 2aa1788637
1 changed files with 28 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
brozzler/ydl.py
View File

@ -34,7 +34,7 @@ import time
thread_local = threading.local()
PROXYRACK_PROXY = "@@@"
MAX_YTDLP_ATTEMPTS = 3
MAX_YTDLP_ATTEMPTS = 4
YTDLP_WAIT = 10
@ -184,28 +184,31 @@ def _build_youtube_dl(worker, destdir, site, page):
worker._proxy_for(site),
url,
)
with open(info_dict["filepath"], "rb") as f:
# include content-length header to avoid chunked
# transfer, which warcprox currently rejects
extra_headers = dict(site.extra_headers())
extra_headers["content-length"] = size
request, response = worker._warcprox_write_record(
warcprox_address=worker._proxy_for(site),
url=url,
warc_type="resource",
content_type=mimetype,
payload=f,
extra_headers=extra_headers,
try:
with open(info_dict["filepath"], "rb") as f:
# include content-length header to avoid chunked
# transfer, which warcprox currently rejects
extra_headers = dict(site.extra_headers())
extra_headers["content-length"] = size
request, response = worker._warcprox_write_record(
warcprox_address=worker._proxy_for(site),
url=url,
warc_type="resource",
content_type=mimetype,
payload=f,
extra_headers=extra_headers,
)
# consulted by _remember_videos()
ydl.pushed_videos.append(
{
"url": url,
"response_code": response.code,
"content-type": mimetype,
"content-length": size,
}
)
# consulted by _remember_videos()
ydl.pushed_videos.append(
{
"url": url,
"response_code": response.code,
"content-type": mimetype,
"content-length": size,
}
)
except:
traceback.print_exc()
def maybe_heartbeat_site_last_claimed(*args, **kwargs):
# in case yt-dlp takes a long time, heartbeat site.last_claimed
@ -306,7 +309,9 @@ def _remember_videos(page, pushed_videos=None):
def _try_youtube_dl(worker, ydl, site, page):
ytdlp_url = page.redirect_url if page.redirect_url else page.url
youtube_host = "youtube.com" in ytdlp_url.split("//")[-1].split("/")[0].split("?")[0]
youtube_host = (
"youtube.com" in ytdlp_url.split("//")[-1].split("/")[0].split("?")[0]
)
attempt = 0
while attempt < MAX_YTDLP_ATTEMPTS:
try: