2021-05-23 18:34:49 +02:00
|
|
|
|
import io
|
|
|
|
|
|
import quopri
|
|
|
|
|
|
import re
|
|
|
|
|
|
import uuid
|
|
|
|
|
|
|
|
|
|
|
|
from .fragment import FragmentFD
|
2022-07-30 21:59:02 +02:00
|
|
|
|
from ..compat import imghdr
|
2022-04-12 00:32:57 +02:00
|
|
|
|
from ..utils import escapeHTML, formatSeconds, srt_subtitles_timecode, urljoin
|
2021-05-23 18:34:49 +02:00
|
|
|
|
from ..version import __version__ as YT_DLP_VERSION
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class MhtmlFD(FragmentFD):
|
2024-06-12 01:09:58 +02:00
|
|
|
|
_STYLESHEET = '''\
|
2021-05-23 18:34:49 +02:00
|
|
|
|
html, body {
|
|
|
|
|
|
margin: 0;
|
|
|
|
|
|
padding: 0;
|
|
|
|
|
|
height: 100vh;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
html {
|
|
|
|
|
|
overflow-y: scroll;
|
|
|
|
|
|
scroll-snap-type: y mandatory;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
body {
|
|
|
|
|
|
scroll-snap-type: y mandatory;
|
|
|
|
|
|
display: flex;
|
|
|
|
|
|
flex-flow: column;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
body > figure {
|
|
|
|
|
|
max-width: 100vw;
|
|
|
|
|
|
max-height: 100vh;
|
|
|
|
|
|
scroll-snap-align: center;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
body > figure > figcaption {
|
|
|
|
|
|
text-align: center;
|
|
|
|
|
|
height: 2.5em;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
body > figure > img {
|
|
|
|
|
|
display: block;
|
|
|
|
|
|
margin: auto;
|
|
|
|
|
|
max-width: 100%;
|
|
|
|
|
|
max-height: calc(100vh - 5em);
|
|
|
|
|
|
}
|
2024-06-12 01:09:58 +02:00
|
|
|
|
'''
|
2021-05-23 18:34:49 +02:00
|
|
|
|
_STYLESHEET = re.sub(r'\s+', ' ', _STYLESHEET)
|
|
|
|
|
|
_STYLESHEET = re.sub(r'\B \B|(?<=[\w\-]) (?=[^\w\-])|(?<=[^\w\-]) (?=[\w\-])', '', _STYLESHEET)
|
|
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
|
def _escape_mime(s):
|
|
|
|
|
|
return '=?utf-8?Q?' + (b''.join(
|
|
|
|
|
|
bytes((b,)) if b >= 0x20 else b'=%02X' % b
|
2022-05-09 13:54:28 +02:00
|
|
|
|
for b in quopri.encodestring(s.encode(), header=True)
|
2021-05-23 18:34:49 +02:00
|
|
|
|
)).decode('us-ascii') + '?='
|
|
|
|
|
|
|
|
|
|
|
|
def _gen_cid(self, i, fragment, frag_boundary):
|
2024-06-12 01:09:58 +02:00
|
|
|
|
return f'{i}.{frag_boundary}@yt-dlp.github.io.invalid'
|
2021-05-23 18:34:49 +02:00
|
|
|
|
|
|
|
|
|
|
def _gen_stub(self, *, fragments, frag_boundary, title):
|
|
|
|
|
|
output = io.StringIO()
|
|
|
|
|
|
|
2024-06-12 01:09:58 +02:00
|
|
|
|
output.write(
|
2021-05-23 18:34:49 +02:00
|
|
|
|
'<!DOCTYPE html>'
|
|
|
|
|
|
'<html>'
|
|
|
|
|
|
'<head>'
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'<meta name="generator" content="yt-dlp {escapeHTML(YT_DLP_VERSION)}">'
|
|
|
|
|
|
f'<title>{escapeHTML(title)}</title>'
|
|
|
|
|
|
f'<style>{self._STYLESHEET}</style>'
|
|
|
|
|
|
'<body>')
|
2021-05-23 18:34:49 +02:00
|
|
|
|
|
|
|
|
|
|
t0 = 0
|
|
|
|
|
|
for i, frag in enumerate(fragments):
|
|
|
|
|
|
output.write('<figure>')
|
|
|
|
|
|
try:
|
|
|
|
|
|
t1 = t0 + frag['duration']
|
|
|
|
|
|
output.write((
|
|
|
|
|
|
'<figcaption>Slide #{num}: {t0} – {t1} (duration: {duration})</figcaption>'
|
|
|
|
|
|
).format(
|
|
|
|
|
|
num=i + 1,
|
|
|
|
|
|
t0=srt_subtitles_timecode(t0),
|
|
|
|
|
|
t1=srt_subtitles_timecode(t1),
|
2024-06-12 01:09:58 +02:00
|
|
|
|
duration=formatSeconds(frag['duration'], msec=True),
|
2021-05-23 18:34:49 +02:00
|
|
|
|
))
|
|
|
|
|
|
except (KeyError, ValueError, TypeError):
|
|
|
|
|
|
t1 = None
|
2024-06-12 01:09:58 +02:00
|
|
|
|
output.write(f'<figcaption>Slide #{i + 1}</figcaption>')
|
|
|
|
|
|
output.write(f'<img src="cid:{self._gen_cid(i, frag, frag_boundary)}">')
|
2021-05-23 18:34:49 +02:00
|
|
|
|
output.write('</figure>')
|
|
|
|
|
|
t0 = t1
|
|
|
|
|
|
|
|
|
|
|
|
return output.getvalue()
|
|
|
|
|
|
|
|
|
|
|
|
def real_download(self, filename, info_dict):
|
|
|
|
|
|
fragment_base_url = info_dict.get('fragment_base_url')
|
|
|
|
|
|
fragments = info_dict['fragments'][:1] if self.params.get(
|
|
|
|
|
|
'test', False) else info_dict['fragments']
|
2021-11-20 03:57:47 +01:00
|
|
|
|
title = info_dict.get('title', info_dict['format_id'])
|
|
|
|
|
|
origin = info_dict.get('webpage_url', info_dict['url'])
|
2021-05-23 18:34:49 +02:00
|
|
|
|
|
|
|
|
|
|
ctx = {
|
|
|
|
|
|
'filename': filename,
|
|
|
|
|
|
'total_frags': len(fragments),
|
|
|
|
|
|
}
|
|
|
|
|
|
|
2021-07-21 19:28:43 +02:00
|
|
|
|
self._prepare_and_start_frag_download(ctx, info_dict)
|
2021-05-23 18:34:49 +02:00
|
|
|
|
|
|
|
|
|
|
extra_state = ctx.setdefault('extra_state', {
|
|
|
|
|
|
'header_written': False,
|
|
|
|
|
|
'mime_boundary': str(uuid.uuid4()).replace('-', ''),
|
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
|
|
frag_boundary = extra_state['mime_boundary']
|
|
|
|
|
|
|
|
|
|
|
|
if not extra_state['header_written']:
|
|
|
|
|
|
stub = self._gen_stub(
|
|
|
|
|
|
fragments=fragments,
|
|
|
|
|
|
frag_boundary=frag_boundary,
|
2024-06-12 01:09:58 +02:00
|
|
|
|
title=title,
|
2021-05-23 18:34:49 +02:00
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
ctx['dest_stream'].write((
|
|
|
|
|
|
'MIME-Version: 1.0\r\n'
|
|
|
|
|
|
'From: <nowhere@yt-dlp.github.io.invalid>\r\n'
|
|
|
|
|
|
'To: <nowhere@yt-dlp.github.io.invalid>\r\n'
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'Subject: {self._escape_mime(title)}\r\n'
|
2021-05-23 18:34:49 +02:00
|
|
|
|
'Content-type: multipart/related; '
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'boundary="{frag_boundary}"; '
|
|
|
|
|
|
'type="text/html"\r\n'
|
|
|
|
|
|
f'X.yt-dlp.Origin: {origin}\r\n'
|
2021-05-23 18:34:49 +02:00
|
|
|
|
'\r\n'
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'--{frag_boundary}\r\n'
|
2021-05-23 18:34:49 +02:00
|
|
|
|
'Content-Type: text/html; charset=utf-8\r\n'
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'Content-Length: {len(stub)}\r\n'
|
2021-05-23 18:34:49 +02:00
|
|
|
|
'\r\n'
|
2024-06-12 01:09:58 +02:00
|
|
|
|
f'{stub}\r\n').encode())
|
2021-05-23 18:34:49 +02:00
|
|
|
|
extra_state['header_written'] = True
|
|
|
|
|
|
|
|
|
|
|
|
for i, fragment in enumerate(fragments):
|
|
|
|
|
|
if (i + 1) <= ctx['fragment_index']:
|
|
|
|
|
|
continue
|
|
|
|
|
|
|
2022-03-13 23:03:40 +01:00
|
|
|
|
fragment_url = fragment.get('url')
|
|
|
|
|
|
if not fragment_url:
|
|
|
|
|
|
assert fragment_base_url
|
|
|
|
|
|
fragment_url = urljoin(fragment_base_url, fragment['path'])
|
|
|
|
|
|
|
2022-03-15 04:27:41 +01:00
|
|
|
|
success = self._download_fragment(ctx, fragment_url, info_dict)
|
2021-05-23 18:34:49 +02:00
|
|
|
|
if not success:
|
|
|
|
|
|
continue
|
2022-03-15 04:27:41 +01:00
|
|
|
|
frag_content = self._read_fragment(ctx)
|
2021-05-23 18:34:49 +02:00
|
|
|
|
|
|
|
|
|
|
frag_header = io.BytesIO()
|
|
|
|
|
|
frag_header.write(
|
|
|
|
|
|
b'--%b\r\n' % frag_boundary.encode('us-ascii'))
|
|
|
|
|
|
frag_header.write(
|
|
|
|
|
|
b'Content-ID: <%b>\r\n' % self._gen_cid(i, fragment, frag_boundary).encode('us-ascii'))
|
|
|
|
|
|
frag_header.write(
|
2022-07-30 21:59:02 +02:00
|
|
|
|
b'Content-type: %b\r\n' % f'image/{imghdr.what(h=frag_content) or "jpeg"}'.encode())
|
2021-05-23 18:34:49 +02:00
|
|
|
|
frag_header.write(
|
|
|
|
|
|
b'Content-length: %u\r\n' % len(frag_content))
|
|
|
|
|
|
frag_header.write(
|
|
|
|
|
|
b'Content-location: %b\r\n' % fragment_url.encode('us-ascii'))
|
|
|
|
|
|
frag_header.write(
|
|
|
|
|
|
b'X.yt-dlp.Duration: %f\r\n' % fragment['duration'])
|
|
|
|
|
|
frag_header.write(b'\r\n')
|
|
|
|
|
|
self._append_fragment(
|
|
|
|
|
|
ctx, frag_header.getvalue() + frag_content + b'\r\n')
|
|
|
|
|
|
|
|
|
|
|
|
ctx['dest_stream'].write(
|
|
|
|
|
|
b'--%b--\r\n\r\n' % frag_boundary.encode('us-ascii'))
|
2022-10-18 15:03:00 +02:00
|
|
|
|
return self._finish_frag_download(ctx, info_dict)
|
