backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-24 06:59:52 +01:00
Code Issues Projects Releases Activity

tests: add parse_comment test for html_rewriter

Browse Source
This commit is contained in:
Ilya Kreymer 2016-03-10 10:10:51 -08:00
parent 8ae692d630
commit effd618bb3
1 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
pywb/rewrite/test/test_html_rewriter.py
View File

@ -159,6 +159,14 @@ ur"""
>>> parse('<!DOCTYPE html>Some Text without any tags <!-- comments -->', head_insert = '<script>load_stuff();</script>') >>> parse('<!DOCTYPE html>Some Text without any tags <!-- comments -->', head_insert = '<script>load_stuff();</script>')
<!DOCTYPE html>Some Text without any tags <!-- comments --><script>load_stuff();</script> <!DOCTYPE html>Some Text without any tags <!-- comments --><script>load_stuff();</script>
# no parse comments
>>> parse('<html><!-- <a href="/foo.html"> --></html>')
<html><!-- <a href="/foo.html"> --></html>
# with parse comments
>>> parse('<html><!-- <a href="/foo.html"> --></html>', parse_comments=True)
<html><!-- <a href="/web/20131226101010/http://example.com/foo.html"> --></html>
# rel=canonical: rewrite (default) # rel=canonical: rewrite (default)
>>> parse('<link rel=canonical href="http://example.com/">') >>> parse('<link rel=canonical href="http://example.com/">')
<link rel="canonical" href="/web/20131226101010oe_/http://example.com/"> <link rel="canonical" href="/web/20131226101010oe_/http://example.com/">
@ -236,8 +244,10 @@ urlrewriter_pencode = new_rewriter(rewrite_opts=dict(punycode_links=True))
no_base_canon_rewriter = new_rewriter(rewrite_opts=dict(rewrite_rel_canon=False, no_base_canon_rewriter = new_rewriter(rewrite_opts=dict(rewrite_rel_canon=False,
rewrite_base=False)) rewrite_base=False))
def parse(data, head_insert=None, urlrewriter=urlrewriter): def parse(data, head_insert=None, urlrewriter=urlrewriter, parse_comments=False):
parser = HTMLRewriter(urlrewriter, head_insert = head_insert, url = ORIGINAL_URL) parser = HTMLRewriter(urlrewriter, head_insert=head_insert,
url=ORIGINAL_URL,
parse_comments=parse_comments)
if isinstance(data, unicode): if isinstance(data, unicode):
data = data.encode('utf-8') data = data.encode('utf-8')