Skip to content

fix: The export format is incorrect when the table tag contains < p >… #379

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
zhangboyi wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: The export format is incorrect when the table tag contains < p >… #379

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
139e575
fix: The export format is incorrect when the table tag contains < p >…
zhangboyi Mar 13, 2022
5962504
Delete .gitpod.yml
zhangboyi Mar 14, 2022
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
23 changes: 17 additions & 6 deletions html2text/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@ def __init__(
self.split_next_td = False
self.td_count = 0
self.table_start = False
self.table_label_start = False
self.unicode_snob = config.UNICODE_SNOB # covered in cli
self.escape_snob = config.ESCAPE_SNOB # covered in cli
self.links_each_paragraph = config.LINKS_EACH_PARAGRAPH
Expand Down Expand Up @@ -366,18 +367,26 @@ def handle_tag(
self.p()
else:
self.soft_br()
elif self.astack:
elif self.astack and tag == "div" :
pass
elif self.table_label_start and tag == "p" and start:
pass
elif self.table_label_start and tag == "p" and not start:
self.o("</br>")
else:
self.p()

if tag == "br" and start:
if self.astack:
self.space = True
elif self.blockquote > 0:
self.o(" \n> ")
if start:
if self.blockquote > 0:
self.o(" \n> ")
elif self.table_label_start:
pass
else:
self.o(" \n")
else:
self.o(" \n")
if self.table_label_start:
self.o("</br>")

if tag == "hr" and start:
self.p()
Expand Down Expand Up @@ -683,10 +692,12 @@ def link_url(self: HTML2Text, link: str, title: str = "") -> None:
if tag == "table":
if start:
self.table_start = True
self.table_label_start = True
if self.pad_tables:
self.o("<" + config.TABLE_MARKER_FOR_PAD + ">")
self.o(" \n")
else:
self.table_label_start = False
if self.pad_tables:
# add break in case the table is empty or its 1 row table
self.soft_br()
Expand Down