| 1 | from core.url_parser import URLParser |
| 2 | |
| 3 | |
| 4 | def test_parse_video_url(): |
| 5 | url = "https://www.douyin.com/video/7320876060210373923" |
| 6 | parsed = URLParser.parse(url) |
| 7 | |
| 8 | assert parsed is not None |
| 9 | assert parsed["type"] == "video" |
| 10 | assert parsed["aweme_id"] == "7320876060210373923" |
| 11 | |
| 12 | |
| 13 | def test_parse_gallery_url_sets_aweme_id(): |
| 14 | url = "https://www.douyin.com/note/7320876060210373923" |
| 15 | parsed = URLParser.parse(url) |
| 16 | |
| 17 | assert parsed is not None |
| 18 | assert parsed["type"] == "gallery" |
| 19 | assert parsed["aweme_id"] == "7320876060210373923" |
| 20 | assert parsed["note_id"] == "7320876060210373923" |
| 21 | |
| 22 | |
| 23 | def test_parse_gallery_path_url_sets_aweme_id(): |
| 24 | url = "https://www.douyin.com/gallery/7320876060210373923" |
| 25 | parsed = URLParser.parse(url) |
| 26 | |
| 27 | assert parsed is not None |
| 28 | assert parsed["type"] == "gallery" |
| 29 | assert parsed["aweme_id"] == "7320876060210373923" |
| 30 | assert parsed["note_id"] == "7320876060210373923" |
| 31 | |
| 32 | |
| 33 | def test_parse_collection_url_sets_mix_id(): |
| 34 | url = "https://www.douyin.com/collection/7320876060210373923" |
| 35 | parsed = URLParser.parse(url) |
| 36 | |
| 37 | assert parsed is not None |
| 38 | assert parsed["type"] == "collection" |
| 39 | assert parsed["mix_id"] == "7320876060210373923" |
| 40 | |
| 41 | |
| 42 | def test_parse_music_url_sets_music_id(): |
| 43 | url = "https://www.douyin.com/music/7320876060210373923" |
| 44 | parsed = URLParser.parse(url) |
| 45 | |
| 46 | assert parsed is not None |
| 47 | assert parsed["type"] == "music" |
| 48 | assert parsed["music_id"] == "7320876060210373923" |
| 49 | |
| 50 | |
| 51 | def test_parse_unsupported_url_returns_none(): |
| 52 | url = "https://www.douyin.com/hashtag/123456" |
| 53 | assert URLParser.parse(url) is None |
| 54 | |
| 55 | |
| 56 | def test_parse_short_url_marks_as_short(): |
| 57 | # 短链在 parser 层统一标记为 'short'，交由 CLI 预先解析真实链接。 |
| 58 | for url in ( |
| 59 | "https://v.douyin.com/ab12cd/", |
| 60 | "http://v.douyin.com/ab12cd", |
| 61 | "v.douyin.com/ab12cd", |
| 62 | "https://v.iesdouyin.com/xyz789/", |
| 63 | ): |
| 64 | parsed = URLParser.parse(url) |
| 65 | assert parsed is not None, url |
| 66 | assert parsed["type"] == "short", url |
| 67 | |
| 68 | |
| 69 | def test_parse_live_url(): |
| 70 | parsed = URLParser.parse("https://live.douyin.com/123456789") |
| 71 | assert parsed is not None |
| 72 | assert parsed["type"] == "live" |
| 73 | assert parsed["room_id"] == "123456789" |
| 74 | |
| 75 | parsed = URLParser.parse("https://www.douyin.com/follow/live/987654321") |
| 76 | assert parsed is not None |
| 77 | assert parsed["type"] == "live" |
| 78 | assert parsed["room_id"] == "987654321" |
| 79 |