Sourcelane

YouTube Live Chat Scraper

YouTube

Operated by Sourcelane✓ verified

Extract the full chat from any YouTube livestream or premiere - every message with its author, timestamp, membership badge and Super Chat amount.

Read full description

A scraper for YouTube live chat that extracts every chat message from livestreams, premieres, and archived replays into one message-level record per chat entry. Outputs include message text with custom emoji preserved as shortcodes, message classification (regular messages, paid messages, paid stickers, memberships and membership gifts), the message timestamp and offset within the stream, author metadata and badges, membership and moderation status, gift counts for gifted memberships, and parsed paid-contribution details (numeric amount and currency across YouTube-supported currencies). The connector also produces per-video chat aggregates with message counts by type, unique chatter counts, per-currency paid totals, top chatters and the chat time range, and it can capture new messages while a stream is actively running.

Verified Sep 28, 3:56 AM

$0.0005

per chat message

Up to 100 per call. Only pay for results returned; failed calls are refunded.

What people use it for

You give it

  • Livestream URLsrequired

    URLs or IDs of YouTube livestreams, premieres or their archived replays.

Optional settings

Max messages per videoMessage typesStart offset (seconds)End offset (seconds)Live collection window (seconds)

You get back

Text & content
Channel title
People & accounts
Author nameAuthor channel IDVerified
Numbers & stats
Offset secondsAmount textAmount valueAmount currencyGift count
Dates
Published at
Links & media
Video IDVideo URLVideo titleAuthor channel URLAuthor photo URL
Other details
ReplayMessage IDMessage typeOffset timestampOwnerModeratorMemberMember badge+1 more

Trust & reliability

7d uptime trend
WindowUptimeSuccess ratep50p95Calls
24h————0
7d————0
30d————0

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://api.usesourcelane.com/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"youtube-live-chat-scraper","params":{"videoUrls":["https://www.youtube.com/watch?v=Z1sqWFs86uU"]},"maxResults":10}'

Request params

FieldTypeRequiredDescription
videoUrlsarrayrequiredURLs or IDs of YouTube livestreams, premieres or their archived replays. Up to 20 per run.
maxMessagesPerVideointegeroptionalStop after this many chat messages per video. Set 0 to read the whole chat.
messageTypesstringoptionalWhich chat items to keep. Paid only is the cheapest way to pull a stream's Super Chat revenue.
startOffsetSecsintegeroptionalFor replays: only keep chat from this point in the video onwards. 0 starts at the beginning. YouTube serves chat replay in order, so earlier chat is still read - it is simply not returned.
endOffsetSecsintegeroptionalFor replays: stop at this point in the video. 0 reads to the end of the stream.
liveCollectSecsintegeroptionalFor streams that are live right now: how long to keep listening for new messages before finishing the run.

Each result contains

FieldTypeDescription
videoIdstringVideo Id
videoUrlstringVideo Url
videoTitlestringVideo Title
channelTitlestringChannel Title
isReplaybooleanIs Replay
messageIdstringMessage Id
messageTypestringMessage Type
offsetSecondsnullOffset Seconds
offsetTimestampnullOffset Timestamp
publishedAtstringPublished At
authorNamestringAuthor Name
authorChannelIdstringAuthor Channel Id
authorChannelUrlstring—
authorPhotoUrlstring—
isOwnerboolean—
isModeratorboolean—
isVerifiedboolean—
isMemberboolean—
memberBadgenull—
messagestring—
amountTextnull—
amountValuenull—
amountCurrencynull—
giftCountnull—

Use YouTube Live Chat Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Get the transcript of this video and turn it into a blog outline: <url>”

Connect Claude

Web, desktop and mobile. One click, then confirm.

  1. 1Click Add to Claude — claude.ai opens with Sourcelane filled in
  2. 2Click Continue to confirm — it then works in Claude desktop and mobile too
Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json
{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.usesourcelane.com/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json
{
  "mcpServers": {
    "sourcelane": {
      "url": "https://api.usesourcelane.com/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json
{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://api.usesourcelane.com/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL
https://usesourcelane.com/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl
curl -X POST https://api.usesourcelane.com/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"youtube-live-chat-scraper","params":{"videoUrls":["https://www.youtube.com/watch?v=Z1sqWFs86uU"]},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python
import requests

res = requests.post(
    "https://api.usesourcelane.com/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "youtube-live-chat-scraper",
        "params": {"videoUrls":["https://www.youtube.com/watch?v=Z1sqWFs86uU"]},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

5
0
4
0
3
0
2
0
1
0

Leave a review

Loading reviews…

Related YouTube connectors

See all YouTube data connectors →