mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-06-06 09:57:25 +08:00
i18n: translate all Chinese comments, docstrings, and logger messages to English
Comprehensive translation of Chinese text to English across the entire codebase: - api/: FastAPI server documentation and logger messages - cache/: Cache abstraction layer comments and docstrings - database/: Database models and MongoDB store documentation - media_platform/: All platform crawlers (Bilibili, Douyin, Kuaishou, Tieba, Weibo, Xiaohongshu, Zhihu) - model/: Data model documentation - proxy/: Proxy pool and provider documentation - store/: Data storage layer comments - tools/: Utility functions and browser automation - test/: Test file documentation Preserved: Chinese disclaimer header (lines 10-18) for legal compliance 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
@@ -26,59 +26,59 @@ from model.m_kuaishou import VideoUrlInfo, CreatorUrlInfo
|
||||
|
||||
def parse_video_info_from_url(url: str) -> VideoUrlInfo:
|
||||
"""
|
||||
从快手视频URL中解析出视频ID
|
||||
支持以下格式:
|
||||
1. 完整视频URL: "https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke?authorId=3x84qugg4ch9zhs&streamSource=search"
|
||||
2. 纯视频ID: "3x3zxz4mjrsc8ke"
|
||||
Parse video ID from Kuaishou video URL
|
||||
Supports the following formats:
|
||||
1. Full video URL: "https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke?authorId=3x84qugg4ch9zhs&streamSource=search"
|
||||
2. Pure video ID: "3x3zxz4mjrsc8ke"
|
||||
|
||||
Args:
|
||||
url: 快手视频链接或视频ID
|
||||
url: Kuaishou video link or video ID
|
||||
Returns:
|
||||
VideoUrlInfo: 包含视频ID的对象
|
||||
VideoUrlInfo: Object containing video ID
|
||||
"""
|
||||
# 如果不包含http且不包含kuaishou.com,认为是纯ID
|
||||
# If it doesn't contain http and doesn't contain kuaishou.com, consider it as pure ID
|
||||
if not url.startswith("http") and "kuaishou.com" not in url:
|
||||
return VideoUrlInfo(video_id=url, url_type="normal")
|
||||
|
||||
# 从标准视频URL中提取ID: /short-video/视频ID
|
||||
# Extract ID from standard video URL: /short-video/video_ID
|
||||
video_pattern = r'/short-video/([a-zA-Z0-9_-]+)'
|
||||
match = re.search(video_pattern, url)
|
||||
if match:
|
||||
video_id = match.group(1)
|
||||
return VideoUrlInfo(video_id=video_id, url_type="normal")
|
||||
|
||||
raise ValueError(f"无法从URL中解析出视频ID: {url}")
|
||||
raise ValueError(f"Unable to parse video ID from URL: {url}")
|
||||
|
||||
|
||||
def parse_creator_info_from_url(url: str) -> CreatorUrlInfo:
|
||||
"""
|
||||
从快手创作者主页URL中解析出创作者ID
|
||||
支持以下格式:
|
||||
1. 创作者主页: "https://www.kuaishou.com/profile/3x84qugg4ch9zhs"
|
||||
2. 纯ID: "3x4sm73aye7jq7i"
|
||||
Parse creator ID from Kuaishou creator homepage URL
|
||||
Supports the following formats:
|
||||
1. Creator homepage: "https://www.kuaishou.com/profile/3x84qugg4ch9zhs"
|
||||
2. Pure ID: "3x4sm73aye7jq7i"
|
||||
|
||||
Args:
|
||||
url: 快手创作者主页链接或user_id
|
||||
url: Kuaishou creator homepage link or user_id
|
||||
Returns:
|
||||
CreatorUrlInfo: 包含创作者ID的对象
|
||||
CreatorUrlInfo: Object containing creator ID
|
||||
"""
|
||||
# 如果不包含http且不包含kuaishou.com,认为是纯ID
|
||||
# If it doesn't contain http and doesn't contain kuaishou.com, consider it as pure ID
|
||||
if not url.startswith("http") and "kuaishou.com" not in url:
|
||||
return CreatorUrlInfo(user_id=url)
|
||||
|
||||
# 从创作者主页URL中提取user_id: /profile/xxx
|
||||
# Extract user_id from creator homepage URL: /profile/xxx
|
||||
user_pattern = r'/profile/([a-zA-Z0-9_-]+)'
|
||||
match = re.search(user_pattern, url)
|
||||
if match:
|
||||
user_id = match.group(1)
|
||||
return CreatorUrlInfo(user_id=user_id)
|
||||
|
||||
raise ValueError(f"无法从URL中解析出创作者ID: {url}")
|
||||
raise ValueError(f"Unable to parse creator ID from URL: {url}")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# 测试视频URL解析
|
||||
print("=== 视频URL解析测试 ===")
|
||||
# Test video URL parsing
|
||||
print("=== Video URL Parsing Test ===")
|
||||
test_video_urls = [
|
||||
"https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke?authorId=3x84qugg4ch9zhs&streamSource=search&area=searchxxnull&searchKey=python",
|
||||
"3xf8enb8dbj6uig",
|
||||
@@ -87,13 +87,13 @@ if __name__ == '__main__':
|
||||
try:
|
||||
result = parse_video_info_from_url(url)
|
||||
print(f"✓ URL: {url[:80]}...")
|
||||
print(f" 结果: {result}\n")
|
||||
print(f" Result: {result}\n")
|
||||
except Exception as e:
|
||||
print(f"✗ URL: {url}")
|
||||
print(f" 错误: {e}\n")
|
||||
print(f" Error: {e}\n")
|
||||
|
||||
# 测试创作者URL解析
|
||||
print("=== 创作者URL解析测试 ===")
|
||||
# Test creator URL parsing
|
||||
print("=== Creator URL Parsing Test ===")
|
||||
test_creator_urls = [
|
||||
"https://www.kuaishou.com/profile/3x84qugg4ch9zhs",
|
||||
"3x4sm73aye7jq7i",
|
||||
@@ -102,7 +102,7 @@ if __name__ == '__main__':
|
||||
try:
|
||||
result = parse_creator_info_from_url(url)
|
||||
print(f"✓ URL: {url[:80]}...")
|
||||
print(f" 结果: {result}\n")
|
||||
print(f" Result: {result}\n")
|
||||
except Exception as e:
|
||||
print(f"✗ URL: {url}")
|
||||
print(f" 错误: {e}\n")
|
||||
print(f" Error: {e}\n")
|
||||
|
||||
Reference in New Issue
Block a user