+ spec.log('Fetching HTML...\r')
+ html = spec.fetcher.fetch(spec.url)
+ flat_html = spec.fetcher.fetch(flatURL(spec.url))
+ spec.log('Parsing HTML...\r')
+ self._next_thread = find_next_thread(
+ BeautifulSoup(spec.htmlfilter(html), 'html.parser'))
+ self._dom = BeautifulSoup(spec.htmlfilter(flat_html), 'html.parser')
+ self._spec = spec
+
+ def title(self) -> str | None:
+ span = self._dom.findChild("span", id="post-title")
+ if not isinstance(span, Tag):
+ return None
+ return span.text.strip()
+
+ def next_thread(self) -> str | None:
+ return self._next_thread
+
+ def chunkDOMs(self) -> Iterable[Tag]:
+ def text() -> Tag:
+ body = self._dom.body
+ assert body
+ text = body.find_next("div", class_="post-post")
+ assert isinstance(text, Tag)
+ return text
+
+ def the_replies() -> Iterable[Tag]:
+ rs = self._dom.find_all("div", class_="post-reply")
+ assert all(isinstance(r, Tag) for r in rs)
+ return rs
+
+ return itertools.chain([text()], the_replies())
+
+ def emit(self) -> None:
+ self._spec.log('Counting chunks...\r')
+ num_chunks = ilen(self.chunkDOMs())
+ title = self.title() or "chunk"
+ for i, r in enumerate(self.chunkDOMs()):
+ percent = 100.0 * (i + 1) / num_chunks
+ self._spec.log(
+ f'Processing {title} {i+1} of {num_chunks} ({percent:.1f}%)\r')
+ self._spec.domfilter(r)
+ chunk = makeChunk(r, self._spec.images)
+ self._spec.texout.write(
+ self._spec.texfilter(renderChunk(self._spec.texifier, chunk)))
+ self._spec.log('')
+ next_url = self.next_thread()
+ if next_url is not None:
+ Thread(dataclasses.replace(self._spec, url=next_url)).emit()