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

Add recipe images, update README, and REST api example

Browse Source
This commit is contained in:
unclecode
2024-06-07 20:43:50 +08:00
parent 768d048e1c
commit a19379aa58
11 changed files with 66 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/examples/quickstart.py
View File

@@ -166,10 +166,11 @@ def interactive_extraction(crawler):
const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
loadMoreButton && loadMoreButton.click();
"""
crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
# crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
# crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
result = crawler.run(
url="https://www.nbcnews.com/business",
js = js_code
)
cprint("[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]")
print_result(result)
@@ -182,10 +183,11 @@ def multiple_scrip(crawler):
const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
loadMoreButton && loadMoreButton.click();
"""] * 2
crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
# crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
# crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
result = crawler.run(
url="https://www.nbcnews.com/business",
js = js_code
)
cprint("[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]")
print_result(result)