# Free Software Foundation, version 3.
-from dataclasses import dataclass
+import dataclasses
import itertools
from urllib.parse import parse_qsl, urlencode, urljoin, urlparse, urlunparse
-from typing import Iterable
+from typing import Any, Iterable
from bs4 import BeautifulSoup
from bs4.element import Tag
from texify import Texifier
+def ilen(it: Iterable[Any]) -> int:
+ return sum(1 for _ in it)
+
+
def _removeViewFromURL(url: str) -> str:
u = urlparse(url)
old_qs = parse_qsl(u.query)
return urlunparse(u._replace(query=urlencode(qs)))
-@dataclass(frozen=True)
+@dataclasses.dataclass(frozen=True)
class Chunk:
icon: str | None
character: Tag | None
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")
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 / num_chunks
+ self._spec.log(
+ f'Processing {title} {i} 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()
+
def makeChunk(chunk_dom: Tag, image_store: ImageStore) -> Chunk: