Skip to content

<fix>: fix parse_single in MapItemToHtmlTagsParser for single html extraction #459

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

Merged
yogacc33 merged 1 commit into from
Jun 16, 2025
Merged

<fix>: fix parse_single in MapItemToHtmlTagsParser for single html extraction #459

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
5 changes: 2 additions & 3 deletions llm_web_kit/main_html_parser/parser/tag_mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,9 +178,8 @@ def iter_process(elem):
else:
# 非正文节点直接删除
parent = elem.getparent()
if parent is None:
return
parent.remove(elem)
if parent is not None:
parent.remove(elem)
for elem_child in elem:
iter_process(elem_child)

Expand Down
17 changes: 17 additions & 0 deletions tests/llm_web_kit/main_html_parser/processor/test_tag_mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,3 +77,20 @@ def test_parse_single(self):
content_list = pre_data[PreDataJsonKey.HTML_TARGET_LIST]
self.assertEqual(content_list, mock_dict['expected_content_list'])
self.assertEqual(len(pre_data['typical_main_html']), 2269)

def test_parse_single_empty(self):
data = []
raw_html_path = base_dir.joinpath('assets/test_tag_mapping_web.jsonl')
with open(raw_html_path, 'r', encoding='utf-8') as f:
for line in f:
data.append(json.loads(line.strip())) # 解析每行 JSON
mock_dict = data[0]
pre_data = PreDataJson(mock_dict['pre_data'])
llm_response = pre_data[PreDataJsonKey.LLM_RESPONSE]
llm_response['item_id 5'] = 0
llm_response['item_id 7'] = 0
pre_data[PreDataJsonKey.LLM_RESPONSE] = llm_response
pre_data[PreDataJsonKey.TYPICAL_RAW_HTML] = pre_data[PreDataJsonKey.TYPICAL_RAW_TAG_HTML]
parser = MapItemToHtmlTagsParser({})
pre_data = parser.parse_single(pre_data)
self.assertEqual(pre_data['typical_main_html'], '<html lang="it-IT" prefix="og: http://ogp.me/ns#"></html>')