mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-02-23 00:20:48 +08:00
157ddfb21b
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>
109 lines
3.9 KiB
Python
109 lines
3.9 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (c) 2025 relakkes@gmail.com
|
|
#
|
|
# This file is part of MediaCrawler project.
|
|
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/kuaishou/help.py
|
|
# GitHub: https://github.com/NanmiCoder
|
|
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
|
|
#
|
|
|
|
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
|
# 1. 不得用于任何商业用途。
|
|
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
|
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
|
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
|
# 5. 不得用于任何非法或不当的用途。
|
|
#
|
|
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
|
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
|
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
import re
|
|
from model.m_kuaishou import VideoUrlInfo, CreatorUrlInfo
|
|
|
|
|
|
def parse_video_info_from_url(url: str) -> VideoUrlInfo:
|
|
"""
|
|
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: Kuaishou video link or video ID
|
|
Returns:
|
|
VideoUrlInfo: Object containing video 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")
|
|
|
|
# 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"Unable to parse video ID from URL: {url}")
|
|
|
|
|
|
def parse_creator_info_from_url(url: str) -> CreatorUrlInfo:
|
|
"""
|
|
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: Kuaishou creator homepage link or user_id
|
|
Returns:
|
|
CreatorUrlInfo: Object containing creator 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)
|
|
|
|
# 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"Unable to parse creator ID from URL: {url}")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# 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",
|
|
]
|
|
for url in test_video_urls:
|
|
try:
|
|
result = parse_video_info_from_url(url)
|
|
print(f"✓ URL: {url[:80]}...")
|
|
print(f" Result: {result}\n")
|
|
except Exception as e:
|
|
print(f"✗ URL: {url}")
|
|
print(f" Error: {e}\n")
|
|
|
|
# Test creator URL parsing
|
|
print("=== Creator URL Parsing Test ===")
|
|
test_creator_urls = [
|
|
"https://www.kuaishou.com/profile/3x84qugg4ch9zhs",
|
|
"3x4sm73aye7jq7i",
|
|
]
|
|
for url in test_creator_urls:
|
|
try:
|
|
result = parse_creator_info_from_url(url)
|
|
print(f"✓ URL: {url[:80]}...")
|
|
print(f" Result: {result}\n")
|
|
except Exception as e:
|
|
print(f"✗ URL: {url}")
|
|
print(f" Error: {e}\n")
|