Support _ in URLs

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index 05b068f6c6993015df844e7a6b7b3a3f40dc7387..72ec1a5669f48595fba7b640aff98de2da1b6069 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -35,10 +35,14 @@ def process(spec: Spec) -> None:
                           spec.geometry.encode('UTF-8') +
                           b']{geometry}\n')
     spec.texout.write(b'''\\begin{document}
-\\newcommand{\\href}[2]{#2\\footnote{#1}}
+\\newcommand{\\href}[2]{#2\\footnote{\\detokenize{#1}}}
 ''')
     url = flatURL(spec.url)
-    dom = parse(spec.htmlfilter(spec.fetcher.fetch(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