Skip to content

Tables should be passed through instead of being stripped out #55

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Tables should be passed through instead of being stripped out #55

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 21 additions & 3 deletions html2text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,6 +222,7 @@ def __init__(self, out=None, baseurl=''):
self.list = []
self.blockquote = 0
self.pre = 0
self.table = 0
self.startpre = 0
self.code = False
self.br_toggle = ''
Expand Down Expand Up @@ -467,7 +468,11 @@ def handle_tag(self, tag, attrs, start):
self.abbr_data = ''

if tag == "a" and not self.ignore_links:
if start:
if self.table and start:
self.o('<a href="' + attrs['href'] + '">')
elif self.table:
self.o("</a>")
elif start:
if has_key(attrs, 'href') and not (self.skip_internal_links and attrs['href'].startswith('#')):
self.astack.append(attrs)
self.maybe_automatic_link = attrs['href']
Expand Down Expand Up @@ -549,8 +554,21 @@ def handle_tag(self, tag, attrs, start):
self.o(str(li['num'])+". ")
self.start = 1

if tag in ["table", "tr"] and start: self.p()
if tag == 'td': self.pbr()
if tag == 'table':
if start:
self.table = 1
self.o("<"+tag+">")
else:
self.table = 0
self.o("</"+tag+">")

if tag in ["tr", "td", "th"]:
if tag == 'tr':
self.pbr()
if start:
self.o("<"+tag+">")
else:
self.o("</"+tag+">")

if tag == "pre":
if start:
Expand Down
12 changes: 12 additions & 0 deletions test/table.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
<html>
<body>
<p>Here is our price list:</p>

<table>
<tr><th>Item</th><th>Price</th></tr>
<tr><td><a href="http://www.example.com">Apple</a></td><td>1 USD</td></tr>
<tr><td>Orange</td><td>1.50 USD</td></tr>
</table>

</body>
</html>
16 changes: 16 additions & 0 deletions test/table.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
Here is our price list:

<table>

<tr><th>Item</th><th>Price</th>

</tr>

<tr><td><a href="http://www.example.com">Apple</a></td><td>1 USD</td>

</tr>

<tr><td>Orange</td><td>1.50 USD</td>

</tr> </table>