X-Git-Url: http://git.scottworley.com/paperdoorknob/blobdiff_plain/23f3187945d1cf4f3a9cdc43462be2ca39e7023a..69169c2c71234aa0bc60e15b331369263db0e4b8:/paperdoorknob.py?ds=inline

diff --git a/paperdoorknob.py b/paperdoorknob.py
index 653d0c6..0fd1fde 100644
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -4,15 +4,12 @@
 # under the terms of the GNU General Public License as published by the
 # Free Software Foundation, version 3.
 
-
-import itertools
-
-from typing import Iterable
+from typing import Any, Iterable
 
 from bs4 import BeautifulSoup
-from bs4.element import Tag
 
 from args import spec_from_commandline_args
+from glowfic import chunkDOMs, flatURL, makeChunk
 from spec import Spec
 
 
@@ -20,35 +17,40 @@ def parse(content: bytes) -> BeautifulSoup:
     return BeautifulSoup(content, 'html.parser')
 
 
-def clean(html: BeautifulSoup) -> BeautifulSoup:
-    for eb in html.find_all("div", class_="post-edit-box"):
-        eb.decompose()
-    for footer in html.find_all("div", class_="post-footer"):
-        footer.decompose()
-    return html
-
-
-def replies(html: BeautifulSoup) -> Iterable[Tag]:
-    def text() -> Tag:
-        body = html.body
-        assert body
-        text = body.find_next("div", class_="post-post")
-        assert isinstance(text, Tag)
-        return text
-
-    def the_replies() -> Iterable[Tag]:
-        rs = html.find_all("div", class_="post-reply")
-        assert all(isinstance(r, Tag) for r in rs)
-        return rs
-
-    return itertools.chain([text()], the_replies())
+def ilen(it: Iterable[Any]) -> int:
+    return sum(1 for _ in it)
 
 
 def process(spec: Spec) -> None:
-    spec.texout.write(b'\\documentclass{article}\n\\begin{document}\n')
-    html = clean(parse(spec.fetcher.fetch(spec.url)))
-    for r in replies(html):
-        spec.texout.write(spec.texifier.texify(r))
+    spec.texout.write(b'''\\documentclass{article}
+\\usepackage{booktabs}
+\\usepackage{graphicx}
+\\usepackage{longtable}
+\\usepackage{soul}
+\\usepackage{varwidth}
+\\usepackage{wrapstuff}
+''')
+    if spec.geometry is not None:
+        spec.texout.write(b'\\usepackage[' +
+                          spec.geometry.encode('UTF-8') +
+                          b']{geometry}\n')
+    spec.texout.write(b'''\\begin{document}
+\\newcommand{\\href}[2]{#2\\footnote{#1}}
+''')
+    url = flatURL(spec.url)
+    spec.log('Fetching HTML...\r')
+    html = spec.fetcher.fetch(url)
+    spec.log('Parsing HTML...\r')
+    dom = parse(spec.htmlfilter(html))
+    spec.log('Counting chunks...\r')
+    num_chunks = ilen(chunkDOMs(dom))
+    for i, r in enumerate(chunkDOMs(dom)):
+        percent = 100.0 * i / num_chunks
+        spec.log(f'Processing chunk {i} of {num_chunks} ({percent:.1f}%)\r')
+        spec.domfilter(r)
+        chunk = makeChunk(r, spec.images)
+        spec.texout.write(spec.texfilter(spec.layout.renderChunk(chunk)))
+    spec.log('')
     spec.texout.write(b'\\end{document}\n')