diff options
Diffstat (limited to 'youtube/comments.py')
| -rw-r--r-- | youtube/comments.py | 129 |
1 files changed, 67 insertions, 62 deletions
diff --git a/youtube/comments.py b/youtube/comments.py index d47c826..c4e30dd 100644 --- a/youtube/comments.py +++ b/youtube/comments.py @@ -8,9 +8,6 @@ import settings import json import base64 -import urllib -import re -import traceback import flask from flask import request @@ -34,7 +31,7 @@ def make_comment_ctoken(video_id, sort=0, offset=0, lc='', secret_key=''): secret_key = proto.as_bytes(secret_key) - page_info = proto.string(4,video_id) + proto.uint(6, sort) + page_info = proto.string(4, video_id) + proto.uint(6, sort) offset_information = proto.nested(4, page_info) + proto.uint(5, offset) if secret_key: offset_information = proto.string(1, secret_key) + offset_information @@ -47,25 +44,23 @@ def make_comment_ctoken(video_id, sort=0, offset=0, lc='', secret_key=''): return base64.urlsafe_b64encode(result).decode('ascii') -mobile_headers = { - 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_1 like Mac OS X) AppleWebKit/603.1.30 (KHTML, like Gecko) Version/10.0 Mobile/14E304 Safari/602.1', - 'Accept': '*/*', - 'Accept-Language': 'en-US,en;q=0.5', - 'X-YouTube-Client-Name': '2', - 'X-YouTube-Client-Version': '2.20180823', -} - - def request_comments(ctoken, replies=False): - base_url = 'https://m.youtube.com/watch_comment?' - if replies: - base_url += 'action_get_comment_replies=1&ctoken=' - else: - base_url += 'action_get_comments=1&ctoken=' - url = base_url + ctoken.replace("=", "%3D") + "&pbj=1" + url = 'https://m.youtube.com/youtubei/v1/next' + url += '?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8' + data = json.dumps({ + 'context': { + 'client': { + 'hl': 'en', + 'gl': 'US', + 'clientName': 'MWEB', + 'clientVersion': '2.20210804.02.00', + }, + }, + 'continuation': ctoken.replace('=', '%3D'), + }) content = util.fetch_url( - url, headers=mobile_headers, + url, headers=util.mobile_xhr_headers + util.json_header, data=data, report_text='Retrieved comments', debug_name='request_comments') content = content.decode('utf-8') @@ -83,7 +78,7 @@ def single_comment_ctoken(video_id, comment_id): def post_process_comments_info(comments_info): for comment in comments_info['comments']: - comment['author'] = strip_non_ascii(comment['author']) + comment['author'] = strip_non_ascii(comment['author']) if comment.get('author') else "" comment['author_url'] = concat_or_none( '/', comment['author_url']) comment['author_avatar'] = concat_or_none( @@ -102,26 +97,26 @@ def post_process_comments_info(comments_info): ctoken = comment['reply_ctoken'] ctoken, err = proto.set_protobuf_value( ctoken, - 'base64p', 6, 3, 9, value=250) + 'base64p', 6, 3, 9, value=200) if err: print('Error setting ctoken value:') print(err) comment['replies_url'] = None comment['replies_url'] = concat_or_none( util.URL_ORIGIN, - '/comments?replies=1&ctoken=' + ctoken) + f'/comments?replies=1&ctoken={ctoken}') if reply_count == 0: comment['view_replies_text'] = 'Reply' elif reply_count == 1: comment['view_replies_text'] = '1 reply' else: - comment['view_replies_text'] = str(reply_count) + ' replies' + comment['view_replies_text'] = f'{reply_count} replies' - if comment['like_count'] == 1: + if comment['approx_like_count'] == '1': comment['likes_text'] = '1 like' else: - comment['likes_text'] = str(comment['like_count']) + ' likes' + comment['likes_text'] = f"{comment['approx_like_count']} likes" comments_info['include_avatars'] = settings.enable_comment_avatars if comments_info['ctoken']: @@ -131,7 +126,7 @@ def post_process_comments_info(comments_info): # change max_replies field to 250 in ctoken new_ctoken, err = proto.set_protobuf_value( ctoken, - 'base64p', 6, 3, 9, value=250) + 'base64p', 6, 3, 9, value=200) if err: print('Error setting ctoken value:') print(err) @@ -142,7 +137,10 @@ def post_process_comments_info(comments_info): comments_info['more_comments_url'] = concat_or_none( util.URL_ORIGIN, '/comments?ctoken=', ctoken, replies_param) - comments_info['page_number'] = page_number = str(int(comments_info['offset']/20) + 1) + if comments_info['offset'] is None: + comments_info['page_number'] = None + else: + comments_info['page_number'] = int(comments_info['offset']/20) + 1 if not comments_info['is_replies']: comments_info['sort_text'] = 'top' if comments_info['sort'] == 0 else 'newest' @@ -151,54 +149,53 @@ def post_process_comments_info(comments_info): util.URL_ORIGIN, '/watch?v=', comments_info['video_id']) comments_info['video_thumbnail'] = concat_or_none( settings.img_prefix, 'https://i.ytimg.com/vi/', - comments_info['video_id'], '/mqdefault.jpg' + comments_info['video_id'], '/hqdefault.jpg' ) def video_comments(video_id, sort=0, offset=0, lc='', secret_key=''): + if not settings.comments_mode: + return {} + + # Initialize the result dict up-front so that any exception path below + # can safely attach an 'error' field without risking UnboundLocalError. + comments_info = {'error': None} try: - if settings.comments_mode: - comments_info = {'error': None} - other_sort_url = ( - util.URL_ORIGIN + '/comments?ctoken=' - + make_comment_ctoken(video_id, sort=1 - sort, lc=lc) - ) - other_sort_text = 'Sort by ' + ('newest' if sort == 0 else 'top') + other_sort_url = ( + f"{util.URL_ORIGIN}/comments?ctoken=" + f"{make_comment_ctoken(video_id, sort=1 - sort, lc=lc)}" + ) + other_sort_text = f'Sort by {"newest" if sort == 0 else "top"}' - this_sort_url = (util.URL_ORIGIN - + '/comments?ctoken=' - + make_comment_ctoken(video_id, sort=sort, lc=lc)) + this_sort_url = (f"{util.URL_ORIGIN}/comments?ctoken=" + f"{make_comment_ctoken(video_id, sort=sort, lc=lc)}") - comments_info['comment_links'] = [ - (other_sort_text, other_sort_url), - ('Direct link', this_sort_url) - ] + comments_info['comment_links'] = [ + (other_sort_text, other_sort_url), + ('Direct link', this_sort_url) + ] - comments_info.update(yt_data_extract.extract_comments_info( - request_comments( - make_comment_ctoken(video_id, sort, offset, lc, secret_key) - ) - )) - post_process_comments_info(comments_info) + ctoken = make_comment_ctoken(video_id, sort, offset, lc) + comments_info.update(yt_data_extract.extract_comments_info( + request_comments(ctoken), ctoken=ctoken + )) + post_process_comments_info(comments_info) - return comments_info - else: - return {} + return comments_info except util.FetchError as e: if e.code == '429' and settings.route_tor: - comments_info['error'] = 'Error: Youtube blocked the request because the Tor exit node is overutilized.' + comments_info['error'] = 'Error: YouTube blocked the request because the Tor exit node is overutilized.' if e.error_message: - comments_info['error'] += '\n\n' + e.error_message - comments_info['error'] += '\n\nExit node IP address: %s' % e.ip + comments_info['error'] += f'\n\n{e.error_message}' + comments_info['error'] += f'\n\nExit node IP address: {e.ip}' else: - comments_info['error'] = traceback.format_exc() + comments_info['error'] = f'YouTube blocked the request. Error: {e}' except Exception as e: - comments_info['error'] = traceback.format_exc() + comments_info['error'] = f'YouTube blocked the request. Error: {e}' if comments_info.get('error'): - print('Error retrieving comments for ' + str(video_id) + ':\n' + - comments_info['error']) + print(f'Error retrieving comments for {video_id}:\n{comments_info["error"]}') return comments_info @@ -208,12 +205,20 @@ def get_comments_page(): ctoken = request.args.get('ctoken', '') replies = request.args.get('replies', '0') == '1' - comments_info = yt_data_extract.extract_comments_info(request_comments(ctoken, replies)) + comments_info = yt_data_extract.extract_comments_info( + request_comments(ctoken, replies), ctoken=ctoken + ) post_process_comments_info(comments_info) if not replies: - other_sort_url = util.URL_ORIGIN + '/comments?ctoken=' + make_comment_ctoken(comments_info['video_id'], sort=1 - comments_info['sort']) - other_sort_text = 'Sort by ' + ('newest' if comments_info['sort'] == 0 else 'top') + if comments_info['sort'] is None or comments_info['video_id'] is None: + other_sort_url = None + else: + other_sort_url = ( + f'{util.URL_ORIGIN}/comments?ctoken=' + f'{make_comment_ctoken(comments_info["video_id"], sort=1-comments_info["sort"])}' + ) + other_sort_text = f'Sort by {"newest" if comments_info["sort"] == 0 else "top"}' comments_info['comment_links'] = [(other_sort_text, other_sort_url)] return flask.render_template( |