huanghai/aiData
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

'commit'

Browse Source
This commit is contained in:
HuangHai
2026-01-21 07:29:40 +08:00
parent 9efe1d3872
commit f56a2744b9
2 changed files with 0 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
test_marked.html
View File

@@ -1,31 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<script src="https://cdnjs.cloudflare.com/ajax/libs/marked/12.0.0/marked.min.js"></script>
</head>
<body>
<div id="output"></div>
<div id="error" style="color: red;"></div>
<script>
try {
marked.use({
gfm: true,
breaks: true,
renderer: {
code(code, language) {
if (language === 'echarts') {
return 'ECHARTS';
}
return false;
}
}
});
const text = "- **Test Bold**";
const html = marked.parse(text);
document.getElementById('output').innerHTML = html;
} catch (e) {
document.getElementById('error').innerText = e.toString();
}
</script>
</body>
</html>

53
test_title_extraction.py
View File

@@ -1,53 +0,0 @@
import sys
import os
import re
# Mock class since we can't import easily without full env
class DouYinDownloaderMock:
def extract_title_from_text(self, text: str) -> str:
"""
Extract title from share text by removing URLs and common prefixes
"""
# 1. Remove URLs
clean_text = re.sub(r'http[s]?://\S+', '', text)
# 2. Remove "Copy open Douyin..." prefix patterns
# Example: "3.00 12/28 d@n.dN VYZ:/ 复制打开抖音极速版，看看【聚合能研的作品】..."
# Pattern: Any chars + "复制打开抖音" + any chars + "，看看"
clean_text = re.sub(r'.*?复制打开抖音.*?，看看', '', clean_text)
# 3. Remove 【...】 if it's at the start (usually author name)
clean_text = re.sub(r'^\s*【.*?】', '', clean_text)
# 4. Clean up whitespace
clean_text = clean_text.strip()
return clean_text if clean_text else "Unknown Title"
def test():
downloader = DouYinDownloaderMock()
# Case 1: User example
text1 = "3.00 12/28 d@n.dN VYZ:/ 复制打开抖音极速版，看看【聚合能研的作品】2026年，电力市场的 “大洗牌” 正式开始 告别... https://v.douyin.com/gHWfWVgDVRo/"
title1 = downloader.extract_title_from_text(text1)
print(f"Input 1: {text1}")
print(f"Title 1: {title1}")
print("-" * 20)
# Case 2: Pure text
text2 = "2026年，电力市场的 “大洗牌” 正式开始 告别..."
title2 = downloader.extract_title_from_text(text2)
print(f"Input 2: {text2}")
print(f"Title 2: {title2}")
print("-" * 20)
# Case 3: Text with URL only
text3 = "Check this out https://v.douyin.com/abc/"
title3 = downloader.extract_title_from_text(text3)
print(f"Input 3: {text3}")
print(f"Title 3: {title3}")
print("-" * 20)
if __name__ == "__main__":
test()