Strip all graphics and images from final results (Markdown, HTML, text, and UI)

thread_ripper/models.py

@@ -39,7 +39,8 @@ class RippedThread(BaseModel):
 class RipRequest(BaseModel):
     url: str
     mode: str = "author_only"  # 'author_only' or 'all_replies'
-    max_scrolls: int = 6
+    include_images: bool = False
+    max_scrolls: int = 4
 
 class HistorySummary(BaseModel):
     id: str

thread_ripper/scraper.py

@@ -42,7 +42,7 @@ class ThreadScraper:
                 await self._playwright.stop()
                 self._playwright = None
 
-    async def rip(self, url: str, mode: str = "author_only", max_scrolls: int = 4) -> RippedThread:
+    async def rip(self, url: str, mode: str = "author_only", include_images: bool = False, max_scrolls: int = 4) -> RippedThread:
         """Scrapes and rips a Threads post and chained continuation posts with optimized speed."""
         browser = await self.get_browser()
         context: BrowserContext = await browser.new_context(
@@ -58,7 +58,7 @@ class ThreadScraper:
                 "**/*",
                 lambda route: route.abort()
                 if route.request.resource_type in ["image", "media", "font"]
-                else route.continue_()
+                else route.continue_(),
             )
 
             # 2. Fast navigation using domcontentloaded instead of networkidle
@@ -172,16 +172,17 @@ class ThreadScraper:
                     continue
                 seen_texts.add(text_hash)
 
-                # Extract post images
-                imgs = await c.query_selector_all("img")
+                # Extract post images (only real content photos, never profile avatars)
                 post_images: List[MediaItem] = []
-                for img in imgs:
-                    src = await img.get_attribute("src")
-                    alt = await img.get_attribute("alt") or ""
-                    if src:
-                        if "profile_pic" in src or ("scontent" in src and "206x206" in src):
-                            continue
-                        post_images.append(MediaItem(type="image", url=src, alt_text=alt))
+                if include_images:
+                    imgs = await c.query_selector_all("img")
+                    for img in imgs:
+                        src = await img.get_attribute("src")
+                        alt = await img.get_attribute("alt") or ""
+                        if src:
+                            if "profile_pic" in src or "profile picture" in alt.lower() or ("scontent" in src and "206x206" in src):
+                                continue
+                            post_images.append(MediaItem(type="image", url=src, alt_text=alt))
 
                 raw_segments.append(
                     PostSegment(
@@ -211,10 +212,10 @@ class ThreadScraper:
                     )
                 )
 
-            # Build stitched outputs
-            markdown_out = build_markdown(author_name, author_handle, canonical_url, raw_segments)
+            # Build stitched outputs without graphics by default
+            markdown_out = build_markdown(author_name, author_handle, canonical_url, raw_segments, include_images=include_images)
             plain_text_out = build_plain_text(author_name, author_handle, canonical_url, raw_segments)
-            html_out = build_standalone_html(author_name, author_handle, author_avatar, canonical_url, raw_segments)
+            html_out = build_standalone_html(author_name, author_handle, canonical_url, raw_segments, include_images=include_images)
 
             thread_id = hashlib.md5(canonical_url.split("?")[0].encode("utf-8")).hexdigest()[:12]
             title = raw_segments[0].text.split("\n")[0] if raw_segments and raw_segments[0].text else f"Thread by @{author_handle}"

thread_ripper/server.py

@@ -42,7 +42,12 @@ async def rip_endpoint(req: RipRequest):
         raise HTTPException(status_code=400, detail="Invalid Threads URL. Please provide a valid threads.net or threads.com link.")
 
     try:
-        ripped = await scraper.rip(url=req.url, mode=req.mode, max_scrolls=req.max_scrolls)
+        ripped = await scraper.rip(
+            url=req.url,
+            mode=req.mode,
+            include_images=req.include_images,
+            max_scrolls=req.max_scrolls
+        )
         storage.save(ripped)
         return ripped
     except Exception as e:

thread_ripper/static/app.js

@@ -94,7 +94,7 @@ document.addEventListener("DOMContentLoaded", () => {
       const response = await fetch("/api/rip", {
         method: "POST",
         headers: { "Content-Type": "application/json" },
-        body: JSON.stringify({ url, mode, max_scrolls: 4 })
+        body: JSON.stringify({ url, mode, include_images: false, max_scrolls: 4 })
       });
 
       if (!response.ok) {
@@ -161,16 +161,11 @@ document.addEventListener("DOMContentLoaded", () => {
   function renderThread(thread) {
     resultSection.classList.remove("hidden");
 
-    // Header info
+    // Header info (clean text header, no graphic avatar)
     resAuthorName.textContent = thread.author_name;
     resAuthorLink.textContent = `@${thread.author_handle}`;
     resAuthorLink.href = thread.canonical_url;
-    if (thread.author_avatar) {
-      resAvatar.src = thread.author_avatar;
-      resAvatar.classList.remove("hidden");
-    } else {
-      resAvatar.classList.add("hidden");
-    }
+    resAvatar.classList.add("hidden");
 
     resSegmentCount.textContent = thread.segment_count;
     resWordCount.textContent = thread.total_words;

thread_ripper/stitcher.py

@@ -5,7 +5,6 @@ from .models import PostSegment
 def clean_segment_text(text: str) -> str:
     """Clean up whitespace and trailing artifacts from text."""
     lines = [l.strip() for l in text.split("\n")]
-    # Remove empty lines while preserving deliberate paragraph breaks
     cleaned_lines = []
     prev_blank = False
     for line in lines:
@@ -17,8 +16,8 @@ def clean_segment_text(text: str) -> str:
             prev_blank = True
     return "\n".join(cleaned_lines).strip()
 
-def build_markdown(author_name: str, author_handle: str, canonical_url: str, segments: List[PostSegment]) -> str:
-    """Stitches segments into a single cohesive Markdown document."""
+def build_markdown(author_name: str, author_handle: str, canonical_url: str, segments: List[PostSegment], include_images: bool = False) -> str:
+    """Stitches segments into a single cohesive Markdown document without graphics."""
     lines = []
     title = segments[0].text.split("\n")[0] if segments and segments[0].text else "Threads Post"
     if len(title) > 80:
@@ -35,18 +34,17 @@ def build_markdown(author_name: str, author_handle: str, canonical_url: str, seg
 
     for idx, seg in enumerate(segments):
         cleaned_text = clean_segment_text(seg.text)
-        if not cleaned_text and not seg.images:
+        if not cleaned_text:
             continue
 
-        if cleaned_text:
-            lines.append(cleaned_text)
-            lines.append("")
+        lines.append(cleaned_text)
+        lines.append("")
 
-        # Include media images if any
-        for img in seg.images:
-            alt = img.alt_text or f"Thread Image {idx + 1}"
-            lines.append(f"![{alt}]({img.url})")
-            lines.append("")
+        if include_images:
+            for img in seg.images:
+                alt = img.alt_text or f"Image {idx + 1}"
+                lines.append(f"![{alt}]({img.url})")
+                lines.append("")
 
     lines.append("---")
     lines.append(f"*Ripped with Thread Ripper from [Threads]({canonical_url})*")
@@ -69,8 +67,8 @@ def build_plain_text(author_name: str, author_handle: str, canonical_url: str, s
     output.append("=" * 60)
     return "\n".join(output).strip()
 
-def build_standalone_html(author_name: str, author_handle: str, author_avatar: str, canonical_url: str, segments: List[PostSegment]) -> str:
-    """Generates an elegant, responsive standalone HTML file."""
+def build_standalone_html(author_name: str, author_handle: str, canonical_url: str, segments: List[PostSegment], include_images: bool = False) -> str:
+    """Generates an elegant, text-focused standalone HTML document without clutter."""
     title = segments[0].text.split("\n")[0] if segments and segments[0].text else f"Thread by @{author_handle}"
     if len(title) > 80:
         title = title[:77] + "..."
@@ -78,10 +76,11 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
     content_sections = []
     for idx, seg in enumerate(segments):
         cleaned_text = clean_segment_text(seg.text)
+        if not cleaned_text:
+            continue
         paragraphs = cleaned_text.split("\n")
         section_html = "<div class='thread-segment'>"
         
-        # Render bullet points or paragraphs cleanly
         in_list = False
         for p in paragraphs:
             p = p.strip()
@@ -100,15 +99,14 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
         if in_list:
             section_html += "</ul>"
 
-        # Attached images
-        for img in seg.images:
-            section_html += f"<div class='segment-image'><img src='{img.url}' alt='{img.alt_text or ''}' loading='lazy' /></div>"
+        if include_images:
+            for img in seg.images:
+                section_html += f"<div class='segment-image'><img src='{img.url}' alt='{img.alt_text or ''}' loading='lazy' /></div>"
 
         section_html += "</div>"
         content_sections.append(section_html)
 
     body_content = "\n".join(content_sections)
-    avatar_tag = f"<img class='avatar' src='{author_avatar}' alt='{author_handle}' />" if author_avatar else ""
 
     html = f"""<!DOCTYPE html>
 <html lang="en">
@@ -139,7 +137,7 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
     font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
     background: var(--bg);
     color: var(--text);
-    line-height: 1.65;
+    line-height: 1.7;
     margin: 0;
     padding: 32px 16px;
     display: flex;
@@ -155,22 +153,14 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
     box-shadow: 0 8px 30px rgba(0,0,0,0.12);
   }}
   .header {{
-    display: flex;
-    align-items: center;
-    gap: 16px;
     margin-bottom: 28px;
     padding-bottom: 20px;
     border-bottom: 1px solid var(--border);
   }}
-  .avatar {{
-    width: 54px;
-    height: 54px;
-    border-radius: 50%;
-    object-fit: cover;
-  }}
   .author-info h2 {{
-    margin: 0;
-    font-size: 1.25rem;
+    margin: 0 0 6px 0;
+    font-size: 1.35rem;
+    font-weight: 700;
   }}
   .author-info a {{
     color: var(--accent);
@@ -178,7 +168,7 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
     font-size: 0.95rem;
   }}
   .thread-segment {{
-    margin-bottom: 24px;
+    margin-bottom: 20px;
     font-size: 1.1rem;
   }}
   .thread-segment p {{
@@ -191,11 +181,6 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
   .thread-segment li {{
     margin-bottom: 8px;
   }}
-  .segment-image img {{
-    max-width: 100%;
-    border-radius: 12px;
-    margin-top: 12px;
-  }}
   .footer {{
     margin-top: 36px;
     padding-top: 20px;
@@ -214,7 +199,6 @@ def build_standalone_html(author_name: str, author_handle: str, author_avatar: s
 <body>
   <article class="article">
     <div class="header">
-      {avatar_tag}
       <div class="author-info">
         <h2>{author_name}</h2>
         <a href="{canonical_url}" target="_blank">@{author_handle} on Threads</a>