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:
@@ -80,6 +80,8 @@ class ZhihuPlaywrightExtractor:
|
||||
URL_PATTERNS = {
|
||||
'zvideo': r'zhihu\.com/zvideo/(\d+)',
|
||||
'zhuanlan': r'zhuanlan\.zhihu\.com/p/(\d+)',
|
||||
'answer': r'zhihu\.com/question/\d+/answer/(\d+)',
|
||||
'question': r'zhihu\.com/question/(\d+)',
|
||||
}
|
||||
|
||||
def __init__(self, headless: bool = True, timeout: int = 30):
|
||||
@@ -242,6 +244,115 @@ class ZhihuPlaywrightExtractor:
|
||||
|
||||
return result
|
||||
|
||||
def _extract_answer_content(self) -> Dict[str, Any]:
|
||||
"""提取知乎回答内容"""
|
||||
result = {
|
||||
'type': 'answer',
|
||||
'title': '', # 问题标题
|
||||
'question_id': '',
|
||||
'answer_id': '',
|
||||
'author': '',
|
||||
'content': '',
|
||||
'content_markdown': '',
|
||||
'publish_time': '',
|
||||
'vote_up': 0,
|
||||
}
|
||||
|
||||
# 打印页面标题用于调试
|
||||
page_title = self.browser.page.title()
|
||||
print(f"页面标题: {page_title}")
|
||||
|
||||
# 提取问题标题
|
||||
question_title_elem = self.browser.query_selector('.QuestionHeader-title')
|
||||
if not question_title_elem:
|
||||
question_title_elem = self.browser.query_selector('.QuestionHeader-content h1')
|
||||
if question_title_elem:
|
||||
result['title'] = self._extract_text_content(question_title_elem)
|
||||
|
||||
# 提取回答内容
|
||||
content_elem = self.browser.query_selector('.RichText')
|
||||
if not content_elem:
|
||||
content_elem = self.browser.query_selector('.AnswerItem-richText')
|
||||
if not content_elem:
|
||||
content_elem = self.browser.query_selector('[class*="RichText"]')
|
||||
if content_elem:
|
||||
html_content = self._extract_html_content(content_elem)
|
||||
result['content'] = html_content
|
||||
result['content_markdown'] = self.markdown_converter.convert(html_content)
|
||||
|
||||
# 提取作者信息
|
||||
author_elem = self.browser.query_selector('.AuthorInfo-name')
|
||||
if author_elem:
|
||||
result['author'] = self._extract_text_content(author_elem)
|
||||
|
||||
# 提取发布时间
|
||||
time_elem = self.browser.query_selector('.AnswerItem-time')
|
||||
if not time_elem:
|
||||
time_elem = self.browser.query_selector('.ContentItem-time')
|
||||
if time_elem:
|
||||
result['publish_time'] = time_elem.get_attribute('data-tooltip') or self._extract_text_content(time_elem)
|
||||
|
||||
# 提取点赞数
|
||||
vote_elem = self.browser.query_selector('.VoteButton--up .VoteButton-label')
|
||||
if not vote_elem:
|
||||
vote_elem = self.browser.query_selector('.VoteButton .Count')
|
||||
if vote_elem:
|
||||
vote_text = self._extract_text_content(vote_elem)
|
||||
try:
|
||||
result['vote_up'] = int(vote_text.replace(',', ''))
|
||||
except (ValueError, AttributeError):
|
||||
pass
|
||||
|
||||
return result
|
||||
|
||||
def _extract_question_content(self) -> Dict[str, Any]:
|
||||
"""提取知乎问题内容(包含所有回答)"""
|
||||
result = {
|
||||
'type': 'question',
|
||||
'title': '',
|
||||
'question_id': '',
|
||||
'author': '',
|
||||
'content': '',
|
||||
'content_markdown': '',
|
||||
'publish_time': '',
|
||||
'answer_count': 0,
|
||||
}
|
||||
|
||||
# 打印页面标题用于调试
|
||||
page_title = self.browser.page.title()
|
||||
print(f"页面标题: {page_title}")
|
||||
|
||||
# 提取问题标题
|
||||
title_elem = self.browser.query_selector('.QuestionHeader-title')
|
||||
if not title_elem:
|
||||
title_elem = self.browser.query_selector('.QuestionHeader-content h1')
|
||||
if title_elem:
|
||||
result['title'] = self._extract_text_content(title_elem)
|
||||
|
||||
# 提取问题描述
|
||||
desc_elem = self.browser.query_selector('.QuestionHeader-detail')
|
||||
if not desc_elem:
|
||||
desc_elem = self.browser.query_selector('.QuestionRichText')
|
||||
if desc_elem:
|
||||
html_content = self._extract_html_content(desc_elem)
|
||||
result['content'] = html_content
|
||||
result['content_markdown'] = self.markdown_converter.convert(html_content)
|
||||
|
||||
# 提取回答数量
|
||||
answer_count_elem = self.browser.query_selector('.List-headerText span')
|
||||
if answer_count_elem:
|
||||
count_text = self._extract_text_content(answer_count_elem)
|
||||
try:
|
||||
# 提取数字
|
||||
import re
|
||||
match = re.search(r'(\d+)', count_text)
|
||||
if match:
|
||||
result['answer_count'] = int(match.group(1))
|
||||
except (ValueError, AttributeError):
|
||||
pass
|
||||
|
||||
return result
|
||||
|
||||
def extract(self, url: str) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
从 URL 提取知乎内容
|
||||
@@ -288,6 +399,10 @@ class ZhihuPlaywrightExtractor:
|
||||
result = self._extract_zvideo_content()
|
||||
elif url_type == 'zhuanlan':
|
||||
result = self._extract_zhuanlan_content()
|
||||
elif url_type == 'answer':
|
||||
result = self._extract_answer_content()
|
||||
elif url_type == 'question':
|
||||
result = self._extract_question_content()
|
||||
else:
|
||||
print(f"不支持的类型: {url_type}")
|
||||
return None
|
||||
|
||||
Reference in New Issue
Block a user