Browse Source
clean rag word_extractor. (#19397)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>tags/1.4.0
湛露先生
5 months ago
1 changed files with 3 additions and 4 deletions
+ 3
- 4
api/core/rag/extractor/word_extractor.py
View File
| parsed = urlparse(url) | parsed = urlparse(url) | ||||
| return bool(parsed.netloc) and bool(parsed.scheme) | return bool(parsed.netloc) and bool(parsed.scheme) | ||||
| def _extract_images_from_docx(self, doc, image_folder): | |||||
| os.makedirs(image_folder, exist_ok=True) | |||||
| def _extract_images_from_docx(self, doc): | |||||
| image_count = 0 | image_count = 0 | ||||
| image_map = {} | image_map = {} | ||||
| content = [] | content = [] | ||||
| image_map = self._extract_images_from_docx(doc, image_folder) | |||||
| image_map = self._extract_images_from_docx(doc) | |||||
| hyperlinks_url = None | hyperlinks_url = None | ||||
| url_pattern = re.compile(r"http://[^\s+]+//|https://[^\s+]+") | url_pattern = re.compile(r"http://[^\s+]+//|https://[^\s+]+") | ||||
| xml = ElementTree.XML(run.element.xml) | xml = ElementTree.XML(run.element.xml) | ||||
| x_child = [c for c in xml.iter() if c is not None] | x_child = [c for c in xml.iter() if c is not None] | ||||
| for x in x_child: | for x in x_child: | ||||
| if x_child is None: | |||||
| if x is None: | |||||
| continue | continue | ||||
| if x.tag.endswith("instrText"): | if x.tag.endswith("instrText"): | ||||
| if x.text is None: | if x.text is None: |
Loading…