Merge branch 'main' into feat/idempotency-key

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,35 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: "[BUG]"
+labels: bug
+assignees: ''
+
+---
+
+**Describe the Bug**
+Provide a clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the issue:
+1. Configure the environment or settings with '...'
+2. Run the command '...'
+3. Observe the error or unexpected output at '...'
+4. Log output/error message
+
+**Expected Behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots or copies of the command line output to help explain the issue.
+
+**Environment (please complete the following information):**
+- OS: [e.g. macOS, Linux, Windows]
+- Firecrawl Version: [e.g. 1.2.3]
+- Node.js Version: [e.g. 14.x]
+
+**Logs**
+If applicable, include detailed logs to help understand the problem.
+
+**Additional Context**
+Add any other context about the problem here, such as configuration specifics, network conditions, data volumes, etc.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,26 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: "[Feat]"
+labels: ''
+assignees: ''
+
+---
+
+**Problem Description**
+Describe the issue you're experiencing that has prompted this feature request. For example, "I find it difficult when..."
+
+**Proposed Feature**
+Provide a clear and concise description of the feature you would like implemented.
+
+**Alternatives Considered**
+Discuss any alternative solutions or features you've considered. Why were these alternatives not suitable?
+
+**Implementation Suggestions**
+If you have ideas on how the feature could be implemented, share them here. This could include technical details, API changes, or interaction mechanisms.
+
+**Use Case**
+Explain how this feature would be used and what benefits it would bring. Include specific examples to illustrate how this would improve functionality or user experience.
+
+**Additional Context**
+Add any other context such as comparisons with similar features in other products, or links to prototypes or mockups.

apps/api/.env.example

@@ -35,4 +35,11 @@ STRIPE_PRICE_ID_SCALE=
 HYPERDX_API_KEY=
 HDX_NODE_BETA_MODE=1
 
-FIRE_ENGINE_BETA_URL= # set if you'd like to use the fire engine closed beta
+FIRE_ENGINE_BETA_URL= # set if you'd like to use the fire engine closed beta
+
+# Proxy Settings for Playwright (Alternative you can can use a proxy service like oxylabs, which rotates IPs for you on every request)
+PROXY_SERVER=
+PROXY_USERNAME=
+PROXY_PASSWORD=
+# set if you'd like to block media requests to save proxy bandwidth
+BLOCK_MEDIA=

apps/api/src/scraper/WebScraper/utils/blocklist.ts

@@ -1,6 +1,7 @@
 const socialMediaBlocklist = [
   'facebook.com',
   'twitter.com',
+  'x.com',
   'instagram.com',
   'linkedin.com',
   'pinterest.com',
@@ -14,12 +15,25 @@ const socialMediaBlocklist = [
   'telegram.org',
 ];
 
-const allowedUrls = [
-  'linkedin.com/pulse'
+const allowedKeywords = [
+  'pulse',
+  'privacy',
+  'terms',
+  'policy',
+  'user-agreement',
+  'legal',
+  'help',
+  'support',
+  'contact',
+  'about',
+  'careers',
+  'blog',
+  'press',
+  'conditions',
 ];
 
 export function isUrlBlocked(url: string): boolean {
-  if (allowedUrls.some(allowedUrl => url.includes(allowedUrl))) {
+  if (allowedKeywords.some(keyword => url.includes(keyword))) {
     return false;
   }
 

apps/playwright-service/main.py

@@ -2,9 +2,16 @@
 from playwright.async_api import async_playwright, Browser
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel
+from os import environ
+
+PROXY_SERVER = environ.get('PROXY_SERVER', None)
+PROXY_USERNAME = environ.get('PROXY_USERNAME', None)
+PROXY_PASSWORD = environ.get('PROXY_PASSWORD', None)
+BLOCK_MEDIA = environ.get('BLOCK_MEDIA', 'False').upper() == 'TRUE'
 
 app = FastAPI()
 
+
 class UrlModel(BaseModel):
     url: str
     wait: int = None
@@ -27,11 +34,28 @@ async def shutdown_event():
 
 @app.post("/html")
 async def root(body: UrlModel):
-    context = await browser.new_context()
+    context = None
+    if PROXY_SERVER and PROXY_USERNAME and PROXY_PASSWORD:
+        context = await browser.new_context(proxy={"server": PROXY_SERVER,
+                                                   "username": PROXY_USERNAME,
+                                                   "password": PROXY_PASSWORD})
+    else:
+        context = await browser.new_context()
+
+    if BLOCK_MEDIA:
+        await context.route("**/*.{png,jpg,jpeg,gif,svg,mp3,mp4,avi,flac,ogg,wav,webm}",
+                            handler=lambda route, request: route.abort())
+
     page = await context.new_page()
-    await page.goto(body.url, timeout=15000)  # Set max timeout to 15s
-    if body.wait:  # Check if wait parameter is provided in the request body
-        await page.wait_for_timeout(body.wait)  # Convert seconds to milliseconds for playwright
+    await page.goto(
+        body.url,
+        wait_until="load",
+        timeout=body.timeout if body.timeout else 15000,
+    )
+    # Wait != timeout. Wait is the time to wait after the page is loaded - useful in some cases were "load" / "networkidle" is not enough
+    if body.wait:
+        await page.wait_for_timeout(body.wait)
+
     page_content = await page.content()
     await context.close()
     json_compatible_item_data = {"content": page_content}

apps/python-sdk/.pylintrc

@@ -0,0 +1,2 @@
+[FORMAT]
+max-line-length = 120