Use raw strings for less escaping

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index b364f4d63653d3fa486ca764bb60768967b60763..a19045cbfde8ba813d8f549650592ce27c746bf1 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -4,6 +4,7 @@
 # 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.
 

+from typing import Any, Iterable

 
 from bs4 import BeautifulSoup
 
 
 from bs4 import BeautifulSoup
 


@@ -16,25 +17,40 @@ def parse(content: bytes) -> BeautifulSoup:
     return BeautifulSoup(content, 'html.parser')
 
 
     return BeautifulSoup(content, 'html.parser')
 
 

+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}
-\\usepackage{booktabs}
-\\usepackage{graphicx}
-\\usepackage{longtable}
-\\usepackage{varwidth}
-\\usepackage{wrapstuff}
+    spec.texout.write(br'''\documentclass{article}
+\usepackage{booktabs}
+\usepackage{graphicx}
+\usepackage{longtable}
+\usepackage{soul}
+\usepackage{varwidth}
+\usepackage{wrapstuff}

 ''')
     if spec.geometry is not None:
 ''')
     if spec.geometry is not None:

-        spec.texout.write(b'\\usepackage[' +
+        spec.texout.write(br'\usepackage[' +

                           spec.geometry.encode('UTF-8') +
                           b']{geometry}\n')
                           spec.geometry.encode('UTF-8') +
                           b']{geometry}\n')

-    spec.texout.write(b'\\begin{document}\n')
+    spec.texout.write(br'''\begin{document}
+\newcommand{\href}[2]{#2\footnote{\detokenize{#1}}}
+''')

     url = flatURL(spec.url)
     url = flatURL(spec.url)

-    html = parse(spec.htmlfilter(spec.fetcher.fetch(url)))
-    for r in chunkDOMs(html):
+    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.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')