MenuSearch/fetch_channel_thumbnails.py at main · ndk6879/MenuSearch · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
"""
fetch_channel_thumbnails.py
각 uploader의 샘플 영상 URL → video_id → channel_id → 채널 썸네일 URL 추출
결과를 src/channelData.js 로 저장
"""

import os
import re
import json
from googleapiclient.discovery import build
from dotenv import load_dotenv

load_dotenv()
API_KEY = os.getenv("YOUTUBE_API_KEY")

MENU_DATA_PATH = "src/menuData_kr.js"
OUTPUT_PATH = "src/channelData.js"


def extract_video_id(url):
    m = re.search(r"(?:youtu\.be/|v=)([\w-]{11})", url)
    return m.group(1) if m else None


def parse_menu_data():
    """menuData_kr.js에서 uploader별 첫 번째 video_id 추출"""
    with open(MENU_DATA_PATH, encoding="utf-8") as f:
        content = f.read()

    # 중괄호 단위로 각 레시피 블록 분리
    blocks = re.split(r'\},\s*\{', content)

    uploader_video = {}
    for block in blocks:
        url_m = re.search(r'"url":\s*"([^"]+)"', block)
        upl_m = re.search(r'"uploader":\s*"([^"]+)"', block)
        if not url_m or not upl_m:
            continue
        uploader = upl_m.group(1)
        url = url_m.group(1)
        if uploader and uploader not in uploader_video:
            vid = extract_video_id(url)
            if vid:
                uploader_video[uploader] = vid

    return uploader_video


def fetch_thumbnails(uploader_video):
    youtube = build("youtube", "v3", developerKey=API_KEY)
    result = {}

    video_ids = list(uploader_video.values())
    # YouTube API는 한 번에 최대 50개
    for i in range(0, len(video_ids), 50):
        batch = video_ids[i:i+50]
        resp = youtube.videos().list(part="snippet", id=",".join(batch)).execute()

        # video_id → channel_id 매핑
        vid_to_channel = {}
        channel_ids = []
        for item in resp.get("items", []):
            cid = item["snippet"]["channelId"]
            vid_to_channel[item["id"]] = cid
            channel_ids.append(cid)

        # channel_id → 썸네일 URL
        ch_resp = youtube.channels().list(
            part="snippet",
            id=",".join(set(channel_ids))
        ).execute()

        channel_thumbs = {}
        for item in ch_resp.get("items", []):
            cid = item["id"]
            thumb = (
                item["snippet"]["thumbnails"].get("medium", {}).get("url")
                or item["snippet"]["thumbnails"].get("default", {}).get("url")
            )
            channel_thumbs[cid] = thumb

        # uploader → 썸네일 연결
        for uploader, vid in uploader_video.items():
            if vid in vid_to_channel:
                cid = vid_to_channel[vid]
                if cid in channel_thumbs:
                    result[uploader] = channel_thumbs[cid]

    return result


def write_channel_data(profiles):
    lines = ["// Auto-generated by fetch_channel_thumbnails.py",
             "// uploader 이름 → YouTube 채널 프로필 이미지 URL",
             "",
             "const channelProfiles = {"]
    for uploader, url in sorted(profiles.items()):
        escaped = uploader.replace('"', '\\"')
        lines.append(f'  "{escaped}": "{url}",')
    lines.append("};")
    lines.append("")
    lines.append("export default channelProfiles;")

    with open(OUTPUT_PATH, "w", encoding="utf-8") as f:
        f.write("\n".join(lines))

    print(f"✅ {len(profiles)}개 채널 프로필 저장 → {OUTPUT_PATH}")
    for k, v in profiles.items():
        print(f"  {k}: {v}")


if __name__ == "__main__":
    print("📋 menuData_kr.js 파싱 중...")
    uploader_video = parse_menu_data()
    print(f"  발견된 uploader {len(uploader_video)}명: {list(uploader_video.keys())}")

    print("\n🌐 YouTube API 호출 중...")
    profiles = fetch_thumbnails(uploader_video)

    print("\n💾 channelData.js 작성 중...")
    write_channel_data(profiles)