with open("captions.srt", "w", encoding="utf-8") as f: f.write("\n".join(cues))
for idx, p in enumerate(root.xpath("//tt:p", namespaces=ns), start=1): begin = p.get("begin") end = p.get("end") text = "".join(p.itertext()).strip() if not begin or not end or not text: continue # Convert 00:00:02.000 → SRT time format (commas for ms) begin_srt = begin.replace(".", ",") end_srt = end.replace(".", ",") cues.append(f"{idx}\n{begin_srt} --> {end_srt}\n{text}\n")
But respect the source. Don’t hammer APIs. And always test your converted output—TTML’s richness is both its strength and its curse. ttml download
ffmpeg -i input.ttml output.vtt If you have seg_1.ttml , seg_2.ttml , etc.:
import requests from lxml import etree def download_ttml(url, headers=None, convert_to_srt=True): resp = requests.get(url, headers=headers) resp.raise_for_status() with open("captions
print(f"Converted {len(cues)} cues.") download_ttml("https://example.com/closedcaptions.ttml")
for f in sorted(glob.glob("seg_ .ttml")): tree = etree.parse(f) for p in tree.xpath("// [local-name()='p']"): div.append(p) ffmpeg -i input
cat seg_*.ttml > full.ttml But you must ( <?xml...> and <tt> ). Better to use a script: