2c680e23e4
download_media now shells out to gallery-dl (handles X.com auth/403/video->mp4) instead of urllib, returns the downloaded files, + media_files_for_post glob helper + --cookies CLI. render_markdown embeds images with  and videos with an HTML <video controls> tag (were plain links). extract_corpus uses the package download_media (one download path). Tests rewritten for the gallery-dl API. Corpus: 4 threads, 33 media (32 img embeds + 1 video), 0 missing.
125 lines
4.3 KiB
Python
125 lines
4.3 KiB
Python
"""Render ThreadData into a Markdown file with YAML front-matter."""
|
|
from __future__ import annotations
|
|
import argparse
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
try:
|
|
from scripts.twitter_threads.error_types import ErrorInfo, make_error, Result, ThreadData, PostData, thread_from_dict
|
|
except ImportError:
|
|
from error_types import ErrorInfo, make_error, Result, ThreadData, PostData, thread_from_dict
|
|
|
|
_EM_DASH = "\u2014"
|
|
|
|
def _build_id_to_index(thread: ThreadData) -> dict[str, int]:
|
|
return {post.post_id: i + 1 for i, post in enumerate(thread.posts)}
|
|
|
|
def _format_view_count(value: int | None) -> str:
|
|
if value is None:
|
|
return "null"
|
|
return str(value)
|
|
|
|
def _root_post(thread: ThreadData) -> PostData:
|
|
for p in thread.posts:
|
|
if p.post_id == thread.root_post_id:
|
|
return p
|
|
return thread.posts[0]
|
|
|
|
def _render_yaml(thread: ThreadData, title: str) -> list[str]:
|
|
root = _root_post(thread)
|
|
return [
|
|
"---",
|
|
f'title: "{title}"',
|
|
f'author: "{root.author}"',
|
|
f'handle: "@{root.handle}"',
|
|
f'post_url: "{thread.source_url}"',
|
|
f'post_id: "{thread.root_post_id}"',
|
|
f'timestamp: "{root.timestamp}"',
|
|
f'post_count: {len(thread.posts)}',
|
|
f'reply_count: {root.metrics.reply_count}',
|
|
f'repost_count: {root.metrics.repost_count}',
|
|
f'like_count: {root.metrics.like_count}',
|
|
f'view_count: {_format_view_count(root.metrics.view_count)}',
|
|
"---",
|
|
]
|
|
|
|
def _media_line(index: int, name: str) -> str:
|
|
ext = name.rsplit(".", 1)[-1].lower() if "." in name else ""
|
|
if ext in ("mp4", "mov", "webm", "m4v"):
|
|
return f'<video controls src="./media/{name}"></video>'
|
|
if ext in ("jpg", "jpeg", "png", "gif", "webp", "bmp"):
|
|
return f""
|
|
return f"[Media {index}](./media/{name})"
|
|
|
|
def _render_post(post: PostData, n: int, id_to_index: dict[str, int], media_names: dict[str, list[str]]) -> list[str]:
|
|
lines: list[str] = []
|
|
header = f"## Post {n} ({post.timestamp})"
|
|
if post.reply_to_id is not None and post.reply_to_id in id_to_index:
|
|
header += f" {_EM_DASH} reply to Post {id_to_index[post.reply_to_id]}"
|
|
lines.append(header)
|
|
lines.append("")
|
|
lines.append(post.text)
|
|
lines.append("")
|
|
if post.quote_of_id is not None:
|
|
lines.append(f"> [Quoting post {post.quote_of_id}](https://x.com/i/web/status/{post.quote_of_id})")
|
|
lines.append("")
|
|
names = media_names.get(post.post_id, [])
|
|
if names:
|
|
for k, name in enumerate(names, start=1):
|
|
lines.append(_media_line(k, name))
|
|
lines.append("")
|
|
return lines
|
|
|
|
def render_markdown(thread: ThreadData, media_names: dict[str, list[str]], output: Path) -> Result[Path]:
|
|
lines: list[str] = []
|
|
id_to_index = _build_id_to_index(thread)
|
|
root = _root_post(thread)
|
|
first_line = root.text.splitlines()[0] if root.text.splitlines() else ""
|
|
title = first_line[:80]
|
|
lines.extend(_render_yaml(thread, title))
|
|
lines.append("")
|
|
lines.append(f"# @{root.handle} {_EM_DASH} {title}")
|
|
lines.append("")
|
|
for i, post in enumerate(thread.posts):
|
|
n = i + 1
|
|
lines.extend(_render_post(post, n, id_to_index, media_names))
|
|
content = "\n".join(lines)
|
|
try:
|
|
output.write_text(content, encoding="utf-8")
|
|
except OSError as e:
|
|
return Result.err(make_error("WriteError", "render_markdown", str(e)))
|
|
return Result.ok(output)
|
|
|
|
def main(argv: list[str] | None = None) -> int:
|
|
parser = argparse.ArgumentParser(description="Render a Twitter/X thread_data.json to Markdown.")
|
|
parser.add_argument("--input", type=Path, required=True, help="thread_data.json path")
|
|
parser.add_argument("--media-dir", type=Path, required=True, help="media directory to link")
|
|
parser.add_argument("--output", type=Path, required=True, help="output .md path")
|
|
args = parser.parse_args(argv)
|
|
try:
|
|
raw = args.input.read_text(encoding="utf-8")
|
|
except OSError as e:
|
|
sys.stderr.write(f"error: ReadError: {e}\n")
|
|
return 1
|
|
try:
|
|
data = json.loads(raw)
|
|
except json.JSONDecodeError as e:
|
|
sys.stderr.write(f"error: JsonParseError: {e}\n")
|
|
return 1
|
|
thread = thread_from_dict(data)
|
|
media_names: dict[str, list[str]] = {}
|
|
for post in thread.posts:
|
|
if args.media_dir.exists():
|
|
files = sorted(f.name for f in args.media_dir.glob(f"{post.post_id}_*"))
|
|
if files:
|
|
media_names[post.post_id] = files
|
|
result = render_markdown(thread, media_names, args.output)
|
|
if not result.is_ok:
|
|
sys.stderr.write(f"error: {result.error.kind}: {result.error.detail}\n")
|
|
return 1
|
|
print(str(args.output))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main()) |