def __init__(self, dom: BeautifulSoup) -> None:
self._dom = dom
+ 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 chunkDOMs(self) -> Iterable[Tag]:
def text() -> Tag:
body = self._dom.body
PandocTexifier("pandoc").texify(c.character), b'{Keltham}\n')
+class TestThread(unittest.TestCase):
+
+ def testTitle(self) -> None:
+ t = Thread(BeautifulSoup(b'''
+ <html><body>
+ <div class="content-header">
+ <span id="post-title">
+ <a href="/posts/1234">Teh Story!</a>
+ </span>
+ </div>
+ <div class="post-container post-post">The "post"</div>
+ </body></html>''', 'html.parser'))
+ self.assertEqual(t.title(), 'Teh Story!')
+
+
if __name__ == '__main__':
unittest.main()
from typing import Any, Iterable
from bs4 import BeautifulSoup
-from bs4.element import Tag
from args import spec_from_commandline_args
from glowfic import flatURL, makeChunk, renderChunk, Thread
return sum(1 for _ in it)
-def get_title(dom: BeautifulSoup) -> str | None:
- span = dom.findChild("span", id="post-title")
- if not isinstance(span, Tag):
- return None
- return span.text
-
-
def process(spec: Spec) -> None:
spec.texout.write(br'''\documentclass{article}
\usepackage{booktabs}
thread = Thread(dom)
spec.log('Counting chunks...\r')
num_chunks = ilen(thread.chunkDOMs())
- title = get_title(dom) or "chunk"
+ title = thread.title() or "chunk"
for i, r in enumerate(thread.chunkDOMs()):
percent = 100.0 * i / num_chunks
spec.log(f'Processing {title} {i} of {num_chunks} ({percent:.1f}%)\r')
projects / paperdoorknob / commitdiff