Skip to content

fix: return longer placeholder in PDFCrawlerStrategy to bypass anti-bot detection #2169

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Battleplus wants to merge 1 commit into from
+12 −4
Closed

fix: return longer placeholder in PDFCrawlerStrategy to bypass anti-bot detection #2169

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions crawl4ai/async_webcrawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -504,8 +504,12 @@ async def arun(
crawl_result.cache_status = "miss"

# Check if blocked (skip for raw: URLs —
# caller-provided content, anti-bot N/A)
if _is_raw_url:
# caller-provided content, anti-bot N/A;
# skip for non-HTML Content-Type like application/pdf
# where minimal HTML is expected by design)
_ct = async_response.response_headers.get("Content-Type", "")
_non_html = _ct and not _ct.startswith("text/html")
if _is_raw_url or _non_html:
_blocked = False
_block_reason = ""
else:
Expand Down Expand Up @@ -552,9 +556,11 @@ async def arun(
# Skip for raw: URLs — fallback expects a real URL, not raw HTML content.
_fallback_fn = getattr(config, "fallback_fetch_function", None)
if _fallback_fn and not _done and not _is_raw_url:
_ct2 = (getattr(crawl_result, "response_headers", None) or {}).get("Content-Type", "")
_non_html2 = _ct2 and not _ct2.startswith("text/html")
_needs_fallback = (
crawl_result is None # All proxies threw exceptions
or is_blocked(crawl_result.status_code, crawl_result.html or "")[0]
or (not _non_html2 and is_blocked(crawl_result.status_code, crawl_result.html or "")[0])
)
if _needs_fallback:
self.logger.warning(
Expand Down Expand Up @@ -625,7 +631,9 @@ async def arun(
# empty by design, and is_blocked() would misread "0 bytes
# html" as a block.
_has_download = bool(getattr(crawl_result, "downloaded_files", None))
if not _fallback_succeeded and not _is_raw_url and not _has_download:
_ct = (crawl_result.response_headers or {}).get("Content-Type", "")
_non_html = _ct and not _ct.startswith("text/html")
if not _fallback_succeeded and not _is_raw_url and not _has_download and not _non_html:
_blocked, _block_reason = is_blocked(
crawl_result.status_code, crawl_result.html or "")
if _blocked:
Expand Down