Last active
June 28, 2022 23:45
-
-
Save darmiel/8d3d93dc72d19f49ffc7f386db73ed89 to your computer and use it in GitHub Desktop.
Crawl twitch chat from a past broadcast
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests | |
| import json | |
| # change me | |
| BROADCAST_ID: str = "" | |
| CLIENT_ID: str = "" | |
| # --- | |
| START_URL: str = f"https://api.twitch.tv/v5/videos/{BROADCAST_ID}/comments?content_offset_seconds=0" | |
| CURSOR_URL: str = f"https://api.twitch.tv/v5/videos/{BROADCAST_ID}/comments?cursor=" | |
| HEADERS = {"client-id": CLIENT_ID} | |
| # avoid maximum recursion depth exceeded while calling a Python object | |
| # https://stackoverflow.com/questions/5061582/setting-stacksize-in-a-python-script/16248113#16248113 | |
| import sys | |
| import resource | |
| resource.setrlimit(resource.RLIMIT_STACK, (2**29,-1)) | |
| sys.setrecursionlimit(10**6) | |
| # --- | |
| def load_comments(token: str, all_comments: list) -> list: | |
| url: str | |
| if token == "": | |
| url = START_URL | |
| else: | |
| url = CURSOR_URL + token | |
| resp = requests.get(url, headers=HEADERS) | |
| jr = json.loads(resp.text) | |
| next_token = jr['_next'] | |
| comments = jr['comments'] | |
| # debug | |
| print("loaded", len(comments), "comments (", len(all_comments), "total )") | |
| print(" >> next token:", next_token) | |
| for c in comments: | |
| all_comments.append(c) | |
| if next_token != "": | |
| load_comments(next_token, all_comments) | |
| def main(): | |
| all_comments = [] | |
| load_comments("", all_comments) | |
| print("loaded a total of", len(all_comments), "comments. saving to file...") | |
| jr = json.dumps(all_comments) | |
| with open("resp.json", "w+") as f: | |
| f.write(jr) | |
| print(" >> done!") | |
| if __name__ == '__main__': | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment