| 1 | import re |
| 2 | from typing import Any, Dict, Optional |
| 3 | |
| 4 | from utils.logger import setup_logger |
| 5 | from utils.validators import parse_url_type |
| 6 | |
| 7 | logger = setup_logger("URLParser") |
| 8 | |
| 9 | |
| 10 | class URLParser: |
| 11 | @staticmethod |
| 12 | def parse(url: str) -> Optional[Dict[str, Any]]: |
| 13 | url_type = parse_url_type(url) |
| 14 | if not url_type: |
| 15 | logger.error("Unsupported URL type: %s", url) |
| 16 | return None |
| 17 | |
| 18 | result = { |
| 19 | "original_url": url, |
| 20 | "type": url_type, |
| 21 | } |
| 22 | |
| 23 | if url_type == "video": |
| 24 | aweme_id = URLParser._extract_video_id(url) |
| 25 | if aweme_id: |
| 26 | result["aweme_id"] = aweme_id |
| 27 | |
| 28 | elif url_type == "user": |
| 29 | sec_uid = URLParser._extract_user_id(url) |
| 30 | if sec_uid: |
| 31 | result["sec_uid"] = sec_uid |
| 32 | |
| 33 | elif url_type == "collection": |
| 34 | mix_id = URLParser._extract_mix_id(url) |
| 35 | if mix_id: |
| 36 | result["mix_id"] = mix_id |
| 37 | |
| 38 | elif url_type == "gallery": |
| 39 | note_id = URLParser._extract_note_id(url) |
| 40 | if note_id: |
| 41 | result["note_id"] = note_id |
| 42 | result["aweme_id"] = note_id |
| 43 | |
| 44 | elif url_type == "music": |
| 45 | music_id = URLParser._extract_music_id(url) |
| 46 | if music_id: |
| 47 | result["music_id"] = music_id |
| 48 | |
| 49 | elif url_type == "live": |
| 50 | room_id = URLParser._extract_room_id(url) |
| 51 | if room_id: |
| 52 | result["room_id"] = room_id |
| 53 | |
| 54 | return result |
| 55 | |
| 56 | @staticmethod |
| 57 | def _extract_video_id(url: str) -> Optional[str]: |
| 58 | match = re.search(r"/video/(\d+)", url) |
| 59 | if match: |
| 60 | return match.group(1) |
| 61 | |
| 62 | match = re.search(r"modal_id=(\d+)", url) |
| 63 | if match: |
| 64 | return match.group(1) |
| 65 | |
| 66 | return None |
| 67 | |
| 68 | @staticmethod |
| 69 | def _extract_user_id(url: str) -> Optional[str]: |
| 70 | match = re.search(r"/user/([A-Za-z0-9_-]+)", url) |
| 71 | if match: |
| 72 | return match.group(1) |
| 73 | return None |
| 74 | |
| 75 | @staticmethod |
| 76 | def _extract_mix_id(url: str) -> Optional[str]: |
| 77 | match = re.search(r"/collection/(\d+)", url) |
| 78 | if not match: |
| 79 | match = re.search(r"/mix/(\d+)", url) |
| 80 | if match: |
| 81 | return match.group(1) |
| 82 | return None |
| 83 | |
| 84 | @staticmethod |
| 85 | def _extract_note_id(url: str) -> Optional[str]: |
| 86 | match = re.search(r"/(?:note|gallery|slides)/(\d+)", url) |
| 87 | if match: |
| 88 | return match.group(1) |
| 89 | return None |
| 90 | |
| 91 | @staticmethod |
| 92 | def _extract_music_id(url: str) -> Optional[str]: |
| 93 | match = re.search(r"/music/(\d+)", url) |
| 94 | if match: |
| 95 | return match.group(1) |
| 96 | return None |
| 97 | |
| 98 | @staticmethod |
| 99 | def _extract_room_id(url: str) -> Optional[str]: |
| 100 | # 直播链接形态： |
| 101 | # https://live.douyin.com/123456789 |
| 102 | # https://www.douyin.com/follow/live/123456789 |
| 103 | match = re.search(r"/live/(\d+)", url) |
| 104 | if match: |
| 105 | return match.group(1) |
| 106 | match = re.search(r"live\.douyin\.com/(\d+)", url) |
| 107 | if match: |
| 108 | return match.group(1) |
| 109 | return None |
| 110 |