Use raw strings for less escaping

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index 653d0c65d8d781790aceaff6d59f91a742a277ca..a19045cbfde8ba813d8f549650592ce27c746bf1 100644 (file)
--- 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.
 
 # 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 import BeautifulSoup

-from bs4.element import Tag

 
 from args import spec_from_commandline_args
 
 from args import spec_from_commandline_args

+from glowfic import chunkDOMs, flatURL, makeChunk

 from spec import Spec
 
 
 from spec import Spec
 
 


@@ -20,35 +17,40 @@ def parse(content: bytes) -> BeautifulSoup:
     return BeautifulSoup(content, 'html.parser')
 
 
     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:
 
 
 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(br'''\documentclass{article}
+\usepackage{booktabs}
+\usepackage{graphicx}
+\usepackage{longtable}
+\usepackage{soul}
+\usepackage{varwidth}
+\usepackage{wrapstuff}
+''')
+    if spec.geometry is not None:
+        spec.texout.write(br'\usepackage[' +
+                          spec.geometry.encode('UTF-8') +
+                          b']{geometry}\n')
+    spec.texout.write(br'''\begin{document}
+\newcommand{\href}[2]{#2\footnote{\detokenize{#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')
 
 
     spec.texout.write(b'\\end{document}\n')