Skip to content

<fix>: fix tag map get_feature None error #449

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 12, 2025
Merged

<fix>: fix tag map get_feature None error #449

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
2 changes: 2 additions & 0 deletions llm_web_kit/input/pre_data_json.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,8 @@ class PreDataJsonKey:
TYPICAL_DICT_HTML = 'typical_dict_html'
# 动态id开关
DYNAMIC_ID_ENABLE = 'dynamic_id_enable'
# 动态classid开关
DYNAMIC_CLASSID_ENABLE = 'dynamic_classid_enable'
# 推广原网页
HTML_SOURCE = 'html_source'
# 推广网页提取正文成功标签, bool类型
Expand Down
6 changes: 4 additions & 2 deletions llm_web_kit/main_html_parser/parser/layout_batch_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,8 +65,10 @@ def parse(self, pre_data: PreDataJson) -> PreDataJson:
layer = self.__get_max_width_layer(template_data)
feature1 = get_feature(template_main_html)
feature2 = get_feature(body)
sim = similarity(feature1, feature2, layer_n=layer)
if sim < SIMILARITY_THRESHOLD:
sim = None
if feature1 is not None and feature2 is not None:
sim = similarity(feature1, feature2, layer_n=layer)
if sim is None or sim < SIMILARITY_THRESHOLD:
pre_data[PreDataJsonKey.MAIN_HTML_SUCCESS] = False
else:
pre_data[PreDataJsonKey.MAIN_HTML_SUCCESS] = True
Expand Down
6 changes: 4 additions & 2 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 @@ -52,10 +52,12 @@ def parse(self, pre_data: PreDataJson) -> PreDataJson:
feature1 = get_feature(template_raw_html)
feature2 = get_feature(template_extract_html)
layer = self.__get_max_width_layer(element_dict)
template_sim = similarity(feature1, feature2, layer_n=layer)
template_sim = None
if feature1 is not None and feature2 is not None:
template_sim = similarity(feature1, feature2, layer_n=layer)

# 比较模版正文html与原html相似度
if template_sim > SIMILAR_THRESHOLD:
if template_sim is None or template_sim > SIMILAR_THRESHOLD:
pre_data[PreDataJsonKey.TYPICAL_MAIN_HTML_SUCCESS] = False
else:
pre_data[PreDataJsonKey.TYPICAL_MAIN_HTML_SUCCESS] = True
Expand Down
1 change: 1 addition & 0 deletions tests/llm_web_kit/input/test_pre_data_json.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,6 +391,7 @@ def test_pre_data_json_key_constants(self):
assert hasattr(PreDataJsonKey, 'MAIN_HTML_SUCCESS')
assert hasattr(PreDataJsonKey, 'TYPICAL_DICT_HTML')
assert hasattr(PreDataJsonKey, 'DYNAMIC_ID_ENABLE')
assert hasattr(PreDataJsonKey, 'DYNAMIC_CLASSID_ENABLE')

# Check actual values
assert PreDataJsonKey.DOMAIN_NAME == 'domain_name'
Expand Down
6 changes: 3 additions & 3 deletions tests/llm_web_kit/main_html_parser/parser/test_layout_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,7 @@ def test_dynamic_id(self):
# 推广
pre_data[PreDataJsonKey.HTML_SOURCE] = expand_source
pre_data[PreDataJsonKey.DYNAMIC_ID_ENABLE] = True
pre_data['dynamic_classid_enable'] = True
pre_data[PreDataJsonKey.DYNAMIC_CLASSID_ENABLE] = True
parser = LayoutBatchParser(element_dict)
parts = parser.parse(pre_data)
main_html_body = parts[PreDataJsonKey.MAIN_HTML_BODY]
Expand Down Expand Up @@ -207,7 +207,7 @@ def test_dynamic_classid(self):
# 推广
pre_data[PreDataJsonKey.HTML_SOURCE] = expand_source
pre_data[PreDataJsonKey.DYNAMIC_ID_ENABLE] = True
pre_data['dynamic_classid_enable'] = True
pre_data[PreDataJsonKey.DYNAMIC_CLASSID_ENABLE] = True
parser = LayoutBatchParser(element_dict)
parts = parser.parse(pre_data)
main_html_body = parts[PreDataJsonKey.MAIN_HTML_BODY]
Expand All @@ -230,7 +230,7 @@ def test_dynamic_classid(self):
# 推广
pre_data[PreDataJsonKey.HTML_SOURCE] = expand_source2
pre_data[PreDataJsonKey.DYNAMIC_ID_ENABLE] = True
pre_data['dynamic_classid_enable'] = True
pre_data[PreDataJsonKey.DYNAMIC_CLASSID_ENABLE] = True
parser = LayoutBatchParser(element_dict)
parts = parser.parse(pre_data)
main_html_body = parts[PreDataJsonKey.MAIN_HTML_BODY]
Expand Down