Add examples of scraping Hacker News

Author: mdmintz

examples/cdp_mode/playwright/raw_yc_news_async.py

@@ -0,0 +1,24 @@
+import asyncio
+from playwright.async_api import async_playwright
+from seleniumbase import cdp_driver
+
+
+async def main():
+    driver = await cdp_driver.start_async()
+    endpoint_url = driver.get_endpoint_url()
+
+    async with async_playwright() as p:
+        browser = await p.chromium.connect_over_cdp(endpoint_url)
+        context = browser.contexts[0]
+        page = context.pages[0]
+        url = "https://news.ycombinator.com/submitted?id=seleniumbase"
+        await page.goto(url)
+        items = page.locator("span.titleline > a")
+        for i in range(await (items.count())):
+            item_text = await (items.nth(i)).inner_text()
+            print("* " + item_text)
+
+
+if __name__ == "__main__":
+    loop = asyncio.new_event_loop()
+    loop.run_until_complete(main())

examples/cdp_mode/playwright/raw_yc_news_sync.py

@@ -0,0 +1,15 @@
+from playwright.sync_api import sync_playwright
+from seleniumbase import sb_cdp
+
+sb = sb_cdp.Chrome()
+endpoint_url = sb.get_endpoint_url()
+
+with sync_playwright() as p:
+    browser = p.chromium.connect_over_cdp(endpoint_url)
+    context = browser.contexts[0]
+    page = context.pages[0]
+    page.goto("https://news.ycombinator.com/submitted?id=seleniumbase")
+    items = page.locator("span.titleline > a")
+    for i in range(items.count()):
+        item_text = items.nth(i).inner_text()
+        print("* " + item_text)

examples/cdp_mode/raw_cdp_yc_news.py

@@ -0,0 +1,7 @@
+from seleniumbase import sb_cdp
+
+url = "https://news.ycombinator.com/submitted?id=seleniumbase"
+sb = sb_cdp.Chrome(url)
+elements = sb.find_elements("span.titleline > a")
+for element in elements:
+    print("* " + element.text)

examples/cdp_mode/raw_hacker_news.py

@@ -0,0 +1,8 @@
+from seleniumbase import SB
+
+with SB(uc=True) as sb:
+    url = "https://news.ycombinator.com/submitted?id=seleniumbase"
+    sb.activate_cdp_mode(url)
+    elements = sb.find_elements("span.titleline > a")
+    for element in elements:
+        print("* " + element.text)