Updated to version 0.4.0 with new features
- Enhanced error handling in async crawler. - Added flexible options in Markdown generation. - Updated user agent settings for improved reliability. - Reflected changes in documentation and examples.
This commit is contained in:
@@ -547,19 +547,50 @@ async def generate_knowledge_graph():
|
||||
f.write(result.extracted_content)
|
||||
|
||||
async def fit_markdown_remove_overlay():
|
||||
async with AsyncWebCrawler(headless = False) as crawler:
|
||||
url = "https://janineintheworld.com/places-to-visit-in-central-mexico"
|
||||
async with AsyncWebCrawler(
|
||||
headless=True, # Set to False to see what is happening
|
||||
verbose=True,
|
||||
user_agent_mode="random",
|
||||
user_agent_generator_config={
|
||||
"device_type": "mobile",
|
||||
"os_type": "android"
|
||||
},
|
||||
) as crawler:
|
||||
result = await crawler.arun(
|
||||
url=url,
|
||||
url='https://www.kidocode.com/degrees/technology',
|
||||
cache_mode=CacheMode.BYPASS,
|
||||
word_count_threshold = 10,
|
||||
remove_overlay_elements=True,
|
||||
screenshot = True
|
||||
markdown_generator=DefaultMarkdownGenerator(
|
||||
content_filter=PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0),
|
||||
options={
|
||||
"ignore_links": True
|
||||
}
|
||||
),
|
||||
# markdown_generator=DefaultMarkdownGenerator(
|
||||
# content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0),
|
||||
# options={
|
||||
# "ignore_links": True
|
||||
# }
|
||||
# ),
|
||||
)
|
||||
# Save markdown to file
|
||||
with open(os.path.join(__location__, "mexico_places.md"), "w") as f:
|
||||
f.write(result.fit_markdown)
|
||||
|
||||
|
||||
if result.success:
|
||||
print(len(result.markdown_v2.raw_markdown))
|
||||
print(len(result.markdown_v2.markdown_with_citations))
|
||||
print(len(result.markdown_v2.fit_markdown))
|
||||
|
||||
# Save clean html
|
||||
with open(os.path.join(__location__, "output/cleaned_html.html"), "w") as f:
|
||||
f.write(result.cleaned_html)
|
||||
|
||||
with open(os.path.join(__location__, "output/output_raw_markdown.md"), "w") as f:
|
||||
f.write(result.markdown_v2.raw_markdown)
|
||||
|
||||
with open(os.path.join(__location__, "output/output_markdown_with_citations.md"), "w") as f:
|
||||
f.write(result.markdown_v2.markdown_with_citations)
|
||||
|
||||
with open(os.path.join(__location__, "output/output_fit_markdown.md"), "w") as f:
|
||||
f.write(result.markdown_v2.fit_markdown)
|
||||
|
||||
print("Done")
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user