guanjihuan/py.guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

0.1.137

Browse Source
This commit is contained in:
guanjihuan
2024-12-24 21:58:44 +08:00
parent 2b5991b7f2
commit e132cd8f75
3 changed files with 24 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
PyPI/src/guan/data_processing.py
View File

@@ -1255,25 +1255,28 @@ def convert_wordpress_xml_to_markdown(xml_file='./a.xml', convert_content=1, rep
title = item.find('title').text
content = item.find('.//content:encoded', namespaces={'content': 'http://purl.org/rss/1.0/modules/content/'}).text
if convert_content == 1:
content = re.sub(r'<!--.*?-->', '', content)
content = content.replace('<p>', '')
content = content.replace('</p>', '')
content = content.replace('<ol>', '')
content = content.replace('</ol>', '')
content = content.replace('<ul>', '')
content = content.replace('</ul>', '')
content = content.replace('<strong>', '')
content = content.replace('</strong>', '')
content = content.replace('</li>', '')
content = content.replace('<li>', '+ ')
content = content.replace('</h3>', '')
content = re.sub(r'<h2.*?>', '## ', content)
content = re.sub(r'<h3.*?>', '### ', content)
content = re.sub(r'<h4.*?>', '#### ', content)
for replace_item in replace_more:
content = content.replace(replace_item, '')
for _ in range(100):
content = content.replace('\n\n\n', '\n\n')
try:
content = re.sub(r'<!--.*?-->', '', content)
content = content.replace('<p>', '')
content = content.replace('</p>', '')
content = content.replace('<ol>', '')
content = content.replace('</ol>', '')
content = content.replace('<ul>', '')
content = content.replace('</ul>', '')
content = content.replace('<strong>', '')
content = content.replace('</strong>', '')
content = content.replace('</li>', '')
content = content.replace('<li>', '+ ')
content = content.replace('</h3>', '')
content = re.sub(r'<h2.*?>', '## ', content)
content = re.sub(r'<h3.*?>', '### ', content)
content = re.sub(r'<h4.*?>', '#### ', content)
for replace_item in replace_more:
content = content.replace(replace_item, '')
for _ in range(100):
content = content.replace('\n\n\n', '\n\n')
except:
print(f'提示：字符串替换出现问题！出现问题的内容为：{content}')
else:
pass
markdown_content = f"# {title}\n{content}"