ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Update pdf and screenshot usage documentation. ref #1230

Browse Source
This commit is contained in:
ntohidi
2025-06-18 19:04:32 +02:00
parent 6cd34b3157
commit b7a6e02236
2 changed files with 38 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
deploy/docker/c4ai-doc-context.md
View File

@@ -5433,29 +5433,38 @@ Sometimes you need a visual record of a page or a PDF “printout.” Crawl4AI c
```python
import os, asyncio
from base64 import b64decode
from crawl4ai import AsyncWebCrawler, CacheMode
from crawl4ai import AsyncWebCrawler, CacheMode, CrawlerRunConfig
async def main():
run_config = CrawlerRunConfig(
cache_mode=CacheMode.BYPASS,
screenshot=True,
pdf=True
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://en.wikipedia.org/wiki/List_of_common_misconceptions",
cache_mode=CacheMode.BYPASS,
pdf=True,
screenshot=True
config=run_config
)
if result.success:
# Save screenshot
print(f"Screenshot data present: {result.screenshot is not None}")
print(f"PDF data present: {result.pdf is not None}")
if result.screenshot:
print(f"[OK] Screenshot captured, size: {len(result.screenshot)} bytes")
with open("wikipedia_screenshot.png", "wb") as f:
f.write(b64decode(result.screenshot))
# Save PDF
else:
print("[WARN] Screenshot data is None.")
if result.pdf:
print(f"[OK] PDF captured, size: {len(result.pdf)} bytes")
with open("wikipedia_page.pdf", "wb") as f:
f.write(result.pdf)
print("[OK] PDF & screenshot captured.")
else:
print("[WARN] PDF data is None.")
else:
print("[ERROR]", result.error_message)

29
docs/md_v2/advanced/advanced-features.md
View File

@@ -66,29 +66,38 @@ Sometimes you need a visual record of a page or a PDF “printout.” Crawl4AI c
```python
import os, asyncio
from base64 import b64decode
from crawl4ai import AsyncWebCrawler, CacheMode
from crawl4ai import AsyncWebCrawler, CacheMode, CrawlerRunConfig
async def main():
run_config = CrawlerRunConfig(
cache_mode=CacheMode.BYPASS,
screenshot=True,
pdf=True
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://en.wikipedia.org/wiki/List_of_common_misconceptions",
cache_mode=CacheMode.BYPASS,
pdf=True,
screenshot=True
config=run_config
)
if result.success:
# Save screenshot
print(f"Screenshot data present: {result.screenshot is not None}")
print(f"PDF data present: {result.pdf is not None}")
if result.screenshot:
print(f"[OK] Screenshot captured, size: {len(result.screenshot)} bytes")
with open("wikipedia_screenshot.png", "wb") as f:
f.write(b64decode(result.screenshot))
# Save PDF
else:
print("[WARN] Screenshot data is None.")
if result.pdf:
print(f"[OK] PDF captured, size: {len(result.pdf)} bytes")
with open("wikipedia_page.pdf", "wb") as f:
f.write(result.pdf)
print("[OK] PDF & screenshot captured.")
else:
print("[WARN] PDF data is None.")
else:
print("[ERROR]", result.error_message)