mirror of
https://github.com/DS4SD/docling.git
synced 2025-08-02 07:22:14 +00:00
fix: parse HTML files without body tag
Parse HTML files without 'body' tag, since it is optional in HTML5 specification. Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
parent
53327552e8
commit
baf622ffad
@ -78,10 +78,11 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
|
|
||||||
if self.is_valid():
|
if self.is_valid():
|
||||||
assert self.soup is not None
|
assert self.soup is not None
|
||||||
|
content = self.soup.body or self.soup
|
||||||
# Replace <br> tags with newline characters
|
# Replace <br> tags with newline characters
|
||||||
for br in self.soup.body.find_all("br"):
|
for br in content.find_all("br"):
|
||||||
br.replace_with("\n")
|
br.replace_with("\n")
|
||||||
doc = self.walk(self.soup.body, doc)
|
doc = self.walk(content, doc)
|
||||||
else:
|
else:
|
||||||
raise RuntimeError(
|
raise RuntimeError(
|
||||||
f"Cannot convert doc with {self.document_hash} because the backend failed to init."
|
f"Cannot convert doc with {self.document_hash} because the backend failed to init."
|
||||||
|
Loading…
Reference in New Issue
Block a user