From b6ff7c81aafed0061d0c52defc2c54d89015ca35 Mon Sep 17 00:00:00 2001
From: starmen1265 <starmen1265@163.com>
Date: Sun, 15 Mar 2026 22:39:43 +0800
Subject: [PATCH] fix(zhihu): handle lazy-load images in markdown conversion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

知乎使用图片懒加载机制，`<img>` 标签的 `src` 属性包含 SVG 占位符，
真实图片 URL 在 `data-actualsrc` 或 `data-original` 属性中。
`markdownify` 只读取 `src`，导致转换后得到无效占位符。

修复：在转换前预处理 HTML，将真实图片 URL 替换到 `src` 属性。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 kb-zhihu-metadata/markdown_converter.py       |  50 +++++-
 .../test_markdown_converter.py                | 148 ++++++++++++++++++
 2 files changed, 196 insertions(+), 2 deletions(-)
 create mode 100644 tests/test_zhihu_metadata/test_markdown_converter.py

diff --git a/kb-zhihu-metadata/markdown_converter.py b/kb-zhihu-metadata/markdown_converter.py
index c0f912d..81faa54 100644
--- a/kb-zhihu-metadata/markdown_converter.py
+++ b/kb-zhihu-metadata/markdown_converter.py
@@ -1,7 +1,14 @@
+import re
+from bs4 import BeautifulSoup
 from markdownify import MarkdownConverter as _MarkdownConverter
 
 class MarkdownConverter:
-    """HTML 转 Markdown 转换器，保留完整格式"""
+    """HTML 转 Markdown 转换器，保留完整格式
+
+    处理知乎等平台的图片懒加载机制：
+    - 知乎图片的 src 属性可能是 SVG 占位符 (data:image/svg+xml;...)
+    - 真实图片 URL 存储在 data-actualsrc 或 data-original 属性中
+    """
 
     def __init__(self):
         self.converter = _MarkdownConverter(
@@ -13,5 +20,44 @@ class MarkdownConverter:
         )
 
     def convert(self, html: str) -> str:
-        """转换 HTML 为 Markdown"""
+        """转换 HTML 为 Markdown
+
+        Args:
+            html: 输入的 HTML 字符串
+
+        Returns:
+            转换后的 Markdown 字符串
+        """
+        # 预处理：处理懒加载图片
+        html = self._fix_lazy_load_images(html)
         return self.converter.convert(html)
+
+    def _fix_lazy_load_images(self, html: str) -> str:
+        """修复懒加载图片的 src 属性
+
+        将 data-actualsrc 或 data-original 属性的值替换到 src 属性中，
+        以便 markdownify 能够正确提取真实图片 URL。
+
+        Args:
+            html: 输入的 HTML 字符串
+
+        Returns:
+            处理后的 HTML 字符串
+        """
+        soup = BeautifulSoup(html, 'html.parser')
+
+        for img in soup.find_all('img'):
+            src = img.get('src', '')
+
+            # 如果 src 不是占位符，保持原样
+            if not src or not src.startswith('data:'):
+                continue
+
+            # 尝试获取真实图片 URL
+            # 优先 data-actualsrc，其次 data-original
+            real_src = img.get('data-actualsrc') or img.get('data-original')
+
+            if real_src:
+                img['src'] = real_src
+
+        return str(soup)
diff --git a/tests/test_zhihu_metadata/test_markdown_converter.py b/tests/test_zhihu_metadata/test_markdown_converter.py
new file mode 100644
index 0000000..525d315
--- /dev/null
+++ b/tests/test_zhihu_metadata/test_markdown_converter.py
@@ -0,0 +1,148 @@
+"""Tests for MarkdownConverter in kb_zhihu_metadata
+
+Tests cover:
+- Normal image conversion
+- Zhihu lazy loading image handling (data-actualsrc)
+- Alternative lazy loading (data-original)
+- Mixed content with images
+"""
+
+import pytest
+import sys
+from pathlib import Path
+
+# Add kb_zhihu_metadata to path
+zhihu_metadata_path = Path(__file__).parent.parent.parent / "kb-zhihu-metadata"
+if str(zhihu_metadata_path) not in sys.path:
+    sys.path.insert(0, str(zhihu_metadata_path))
+
+from markdown_converter import MarkdownConverter
+
+
+class TestMarkdownConverterImages:
+    """Tests for image handling in MarkdownConverter"""
+
+    def test_normal_image_conversion(self):
+        """Test that normal images are converted correctly"""
+        html = '<img src="https://example.com/image.jpg" alt="test">'
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "![test](https://example.com/image.jpg)" in result
+
+    def test_zhihu_lazy_load_image_with_data_actualsrc(self):
+        """Test that Zhihu lazy loading images use data-actualsrc"""
+        html = '''<img src="data:image/svg+xml;utf8,<svg></svg>"
+                   data-actualsrc="https://pic1.zhimg.com/v2-real-image_b.jpg">'''
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "https://pic1.zhimg.com/v2-real-image_b.jpg" in result
+        assert "data:image/svg+xml" not in result
+
+    def test_lazy_load_image_with_data_original(self):
+        """Test that images with data-original use that URL"""
+        html = '''<img src="data:image/svg+xml;..." data-original="https://example.com/original.jpg">'''
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "https://example.com/original.jpg" in result
+        assert "data:image/svg+xml" not in result
+
+    def test_data_actualsrc_priority_over_data_original(self):
+        """Test that data-actualsrc takes priority over data-original"""
+        html = '''<img src="data:image/svg+xml;..."
+                   data-actualsrc="https://example.com/actual.jpg"
+                   data-original="https://example.com/original.jpg">'''
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "https://example.com/actual.jpg" in result
+        assert "https://example.com/original.jpg" not in result
+
+    def test_normal_image_not_modified(self):
+        """Test that normal images with http(s) src are not modified"""
+        html = '<img src="https://example.com/normal.jpg">'
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "https://example.com/normal.jpg" in result
+
+    def test_mixed_content_with_images(self):
+        """Test conversion of mixed content with text and images"""
+        html = '''
+        <div class="RichText">
+            <p>First paragraph.</p>
+            <figure>
+                <img src="data:image/svg+xml;..." data-actualsrc="https://pic.zhimg.com/image1.jpg">
+            </figure>
+            <p>Second paragraph.</p>
+            <img src="https://example.com/normal.jpg">
+        </div>
+        '''
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+
+        # Check text content
+        assert "First paragraph" in result
+        assert "Second paragraph" in result
+
+        # Check lazy loaded image
+        assert "https://pic.zhimg.com/image1.jpg" in result
+
+        # Check normal image
+        assert "https://example.com/normal.jpg" in result
+
+        # Ensure no SVG placeholders in result
+        assert "data:image/svg+xml" not in result
+
+    def test_figure_with_caption(self):
+        """Test that figure elements with captions are handled correctly"""
+        html = '''
+        <figure>
+            <img src="data:image/svg+xml;..." data-actualsrc="https://pic.zhimg.com/fig.jpg">
+            <figcaption>Image caption</figcaption>
+        </figure>
+        '''
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+
+        assert "https://pic.zhimg.com/fig.jpg" in result
+        assert "Image caption" in result
+
+    def test_empty_src_with_data_actualsrc(self):
+        """Test handling of empty src with data-actualsrc"""
+        html = '<img src="" data-actualsrc="https://example.com/fallback.jpg">'
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        # Empty src is not a data: URI, so it should stay as is
+        assert "https://example.com/fallback.jpg" not in result
+
+
+class TestMarkdownConverterBasicConversion:
+    """Tests for basic HTML to Markdown conversion"""
+
+    def test_paragraphs(self):
+        """Test paragraph conversion"""
+        html = "<p>First</p><p>Second</p>"
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "First" in result
+        assert "Second" in result
+
+    def test_headings(self):
+        """Test heading conversion"""
+        html = "<h1>Title</h1><h2>Subtitle</h2>"
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "# Title" in result
+        assert "## Subtitle" in result
+
+    def test_links(self):
+        """Test link conversion"""
+        html = '<a href="https://example.com">Link</a>'
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "[Link](https://example.com)" in result
+
+    def test_code_blocks(self):
+        """Test code block conversion"""
+        html = "<pre><code>def hello():\n    print('hello')</code></pre>"
+        converter = MarkdownConverter()
+        result = converter.convert(html)
+        assert "```" in result or "def hello():" in result