feat: 添加知乎问答支持
- zhihu_extractor.py: - 添加 URL_PATTERNS 支持 answer 和 question - 添加 _extract_answer_content() 方法提取知乎回答 - 添加 _extract_question_content() 方法提取知乎问题 - zhihu_metadata.py: - 添加 extract_answer() 函数 - 添加 extract_question() 函数 - 更新命令行参数支持 answer/question 类型 - 更新帮助文档
This commit is contained in:
@@ -2,9 +2,11 @@
|
||||
"""
|
||||
知乎元数据获取工具
|
||||
|
||||
仅支持两种内容类型:
|
||||
支持以下内容类型:
|
||||
- zvideo: 知乎视频 (https://www.zhihu.com/zvideo/xxx)
|
||||
- zhuanlan: 知乎专栏文章 (https://zhuanlan.zhihu.com/p/xxx)
|
||||
- answer: 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy)
|
||||
- question: 知乎问题 (https://www.zhihu.com/question/xxx)
|
||||
"""
|
||||
|
||||
import argparse
|
||||
@@ -51,6 +53,38 @@ def extract_zhuanlan(article_id: str, headless: bool = True) -> Dict[str, Any]:
|
||||
return _extract_metadata(url, "zhuanlan", headless)
|
||||
|
||||
|
||||
def extract_answer(answer_id: str, headless: bool = True) -> Dict[str, Any]:
|
||||
"""
|
||||
获取知乎回答元数据
|
||||
|
||||
Args:
|
||||
answer_id: 回答 ID (数字字符串)
|
||||
headless: 是否使用无头浏览器
|
||||
|
||||
Returns:
|
||||
回答元数据字典
|
||||
"""
|
||||
# 回答需要构建包含问题ID的URL,但answer_id本身足以识别
|
||||
# 使用一个占位符问题ID,因为提取器会从URL中提取answer_id
|
||||
url = f"https://www.zhihu.com/question/0/answer/{answer_id}"
|
||||
return _extract_metadata(url, "answer", headless)
|
||||
|
||||
|
||||
def extract_question(question_id: str, headless: bool = True) -> Dict[str, Any]:
|
||||
"""
|
||||
获取知乎问题元数据
|
||||
|
||||
Args:
|
||||
question_id: 问题 ID (数字字符串)
|
||||
headless: 是否使用无头浏览器
|
||||
|
||||
Returns:
|
||||
问题元数据字典
|
||||
"""
|
||||
url = f"https://www.zhihu.com/question/{question_id}"
|
||||
return _extract_metadata(url, "question", headless)
|
||||
|
||||
|
||||
def _extract_metadata(url: str, content_type: str, headless: bool) -> Dict[str, Any]:
|
||||
"""
|
||||
内部函数:提取元数据
|
||||
@@ -97,24 +131,28 @@ def main():
|
||||
支持的类型:
|
||||
zvideo - 知乎视频 (https://www.zhihu.com/zvideo/123456)
|
||||
zhuanlan - 知乎专栏文章 (https://zhuanlan.zhihu.com/p/123456)
|
||||
answer - 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy)
|
||||
question - 知乎问题 (https://www.zhihu.com/question/xxx)
|
||||
|
||||
示例:
|
||||
python zhihu_metadata.py --id "123456" --type zvideo
|
||||
python zhihu_metadata.py --id "123456" --type zhuanlan
|
||||
python zhihu_metadata.py --id "123456" --type answer
|
||||
python zhihu_metadata.py --id "123456" --type question
|
||||
"""
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--id", "-i",
|
||||
required=True,
|
||||
help="知乎内容 ID (视频ID或文章ID)"
|
||||
help="知乎内容 ID (视频ID/文章ID/回答ID/问题ID)"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--type", "-t",
|
||||
required=True,
|
||||
choices=["zvideo", "zhuanlan"],
|
||||
help="内容类型: zvideo=视频, zhuanlan=专栏文章"
|
||||
choices=["zvideo", "zhuanlan", "answer", "question"],
|
||||
help="内容类型: zvideo=视频, zhuanlan=专栏文章, answer=回答, question=问题"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
@@ -135,8 +173,15 @@ def main():
|
||||
# 提取元数据
|
||||
if args.type == "zvideo":
|
||||
result = extract_zvideo(args.id, headless=args.headless)
|
||||
else: # zhuanlan
|
||||
elif args.type == "zhuanlan":
|
||||
result = extract_zhuanlan(args.id, headless=args.headless)
|
||||
elif args.type == "answer":
|
||||
result = extract_answer(args.id, headless=args.headless)
|
||||
elif args.type == "question":
|
||||
result = extract_question(args.id, headless=args.headless)
|
||||
else:
|
||||
print(f"不支持的类型: {args.type}")
|
||||
sys.exit(1)
|
||||
|
||||
# 输出结果
|
||||
json_output = json.dumps(result, ensure_ascii=False, indent=2)
|
||||
|
||||
Reference in New Issue
Block a user