peter
ae14aa1c6a
The FB Sharing Debugger confirmed the real cause of the missing desktop-Messenger preview: the
scraper fetches og:image ASYNCHRONOUSLY on a URL's first scrape ("The provided 'og:image'
properties are not yet available… specify the dimensions using 'og:image:width'/'og:image:height'"),
so a freshly shared /watch link unfurled title-only. Read the poster JPEG's real dimensions from its
SOF marker (Pillow isn't a dep; the poster aspect differs from the video's, so the stored video
width/height won't do) and emit og:image:width/height. Only runs on a crawler hit. Unit-tested.
65 lines
2.5 KiB
Python
65 lines
2.5 KiB
Python
"""JPEG dimension parsing for the /watch OG image tags (S2, item 6).
|
|
|
|
Facebook's scraper fetches og:image asynchronously on first scrape, so the card is image-less
|
|
unless og:image:width/height are declared — which needs the poster's real dimensions, read from the
|
|
JPEG header without an image library. This pins that parser."""
|
|
import struct
|
|
|
|
from app.downloads.og import _jpeg_size
|
|
|
|
|
|
def _jpeg(width: int, height: int, sof_marker: int = 0xC0) -> bytes:
|
|
"""A minimal but well-formed JPEG: SOI + a JFIF APP0 segment (which the parser must SKIP) + a
|
|
SOFn frame header carrying the dimensions + EOI. sof_marker=0xC0 baseline, 0xC2 progressive."""
|
|
soi = b"\xff\xd8"
|
|
# APP0 JFIF: length 0x0010 (16) = the 2 length bytes + 14 payload bytes.
|
|
app0 = b"\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00"
|
|
# SOFn: length 0x0011 (17) = 2 + precision(1) + height(2) + width(2) + 1 comp * 9? Payload here is
|
|
# precision + h + w + numComp(1) + 3 components * 3 bytes = 1+2+2+1+9 = 15, +2 length = 17.
|
|
sof = (
|
|
b"\xff"
|
|
+ bytes([sof_marker])
|
|
+ b"\x00\x11\x08"
|
|
+ struct.pack(">H", height)
|
|
+ struct.pack(">H", width)
|
|
+ b"\x03\x01\x22\x00\x02\x11\x01\x03\x11\x01"
|
|
)
|
|
return soi + app0 + sof + b"\xff\xd9"
|
|
|
|
|
|
def test_reads_baseline_jpeg_dimensions(tmp_path):
|
|
p = tmp_path / "poster.jpg"
|
|
p.write_bytes(_jpeg(1280, 720))
|
|
assert _jpeg_size(p) == (1280, 720)
|
|
|
|
|
|
def test_reads_progressive_jpeg_dimensions(tmp_path):
|
|
# ffmpeg posters can be progressive (SOF2); the width/height live in the same place.
|
|
p = tmp_path / "poster.jpg"
|
|
p.write_bytes(_jpeg(640, 1138, sof_marker=0xC2))
|
|
assert _jpeg_size(p) == (640, 1138)
|
|
|
|
|
|
def test_skips_preceding_segments(tmp_path):
|
|
# The JFIF APP0 segment sits before the SOF; a naive scan that didn't skip it by length would
|
|
# misread. The helper builds that layout, so a correct result proves the skip.
|
|
p = tmp_path / "poster.jpg"
|
|
p.write_bytes(_jpeg(1920, 3413))
|
|
assert _jpeg_size(p) == (1920, 3413)
|
|
|
|
|
|
def test_non_jpeg_returns_none(tmp_path):
|
|
p = tmp_path / "not.jpg"
|
|
p.write_bytes(b"\x89PNG\r\n\x1a\n" + b"\x00" * 32)
|
|
assert _jpeg_size(p) is None
|
|
|
|
|
|
def test_truncated_before_sof_returns_none(tmp_path):
|
|
p = tmp_path / "trunc.jpg"
|
|
p.write_bytes(b"\xff\xd8\xff\xe0\x00\x10JFIF\x00") # SOI + start of APP0, then nothing
|
|
assert _jpeg_size(p) is None
|
|
|
|
|
|
def test_missing_file_returns_none(tmp_path):
|
|
assert _jpeg_size(tmp_path / "nope.jpg") is None
|