OpenClaw Agent
5507b1d986
- kb-link-parser: Multi-platform URL parser (Bilibili, YouTube, Zhihu) - kb-bilibili-metadata: Bilibili video/article/up主 metadata extractor - kb-zhihu-metadata: Zhihu question/answer/user metadata extractor - kb-bilibili-content: Bilibili video download and content extraction - kb-ocr-processor: OCR text extraction from video frames - kb-deep-analyzer: AI-powered deep content analysis - kb-workflow: Workflow orchestration (inbox, archive, subscriptions, report) Also add: - ARCHITECTURE_FLOWCHART.md: System architecture diagrams - DETAILED_DESIGN.md: Complete design documentation
386 lines
13 KiB
Python
386 lines
13 KiB
Python
"""
|
||
知乎 Playwright 内容提取器
|
||
使用 Playwright 浏览器自动化工具抓取知乎内容
|
||
"""
|
||
|
||
import re
|
||
import sys
|
||
import os
|
||
from typing import Dict, Optional, Any
|
||
from urllib.parse import urlparse
|
||
|
||
# 添加当前目录到 Python 路径以支持绝对导入
|
||
current_dir = os.path.dirname(os.path.abspath(__file__))
|
||
if current_dir not in sys.path:
|
||
sys.path.insert(0, current_dir)
|
||
|
||
try:
|
||
from .markdown_converter import MarkdownConverter
|
||
except ImportError:
|
||
from markdown_converter import MarkdownConverter
|
||
|
||
|
||
class PlaywrightBrowser:
|
||
"""Playwright 浏览器管理器"""
|
||
|
||
def __init__(self, headless: bool = True, timeout: int = 30):
|
||
self.headless = headless
|
||
self.timeout = timeout * 1000
|
||
self.browser = None
|
||
self.context = None
|
||
self.page = None
|
||
|
||
def start(self):
|
||
"""启动浏览器"""
|
||
from playwright.sync_api import sync_playwright
|
||
self.playwright = sync_playwright().start()
|
||
self.browser = self.playwright.chromium.launch(headless=self.headless)
|
||
self.context = self.browser.new_context(
|
||
user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
|
||
)
|
||
self.page = self.context.new_page()
|
||
self.page.set_default_timeout(self.timeout)
|
||
|
||
def close(self):
|
||
"""关闭浏览器"""
|
||
if self.page:
|
||
self.page.close()
|
||
if self.context:
|
||
self.context.close()
|
||
if self.browser:
|
||
self.browser.close()
|
||
if hasattr(self, 'playwright'):
|
||
self.playwright.stop()
|
||
|
||
def goto(self, url: str, wait_until: str = "networkidle"):
|
||
"""导航到指定URL"""
|
||
return self.page.goto(url, wait_until=wait_until)
|
||
|
||
def wait_for_selector(self, selector: str, timeout: int = None):
|
||
"""等待选择器出现"""
|
||
timeout_ms = timeout * 1000 if timeout else self.timeout
|
||
return self.page.wait_for_selector(selector, timeout=timeout_ms)
|
||
|
||
def query_selector(self, selector: str):
|
||
"""查询选择器"""
|
||
return self.page.query_selector(selector)
|
||
|
||
def query_selector_all(self, selector: str):
|
||
"""查询所有匹配的选择器"""
|
||
return self.page.query_selector_all(selector)
|
||
|
||
def evaluate(self, script: str):
|
||
"""执行 JavaScript 代码"""
|
||
return self.page.evaluate(script)
|
||
|
||
|
||
class ZhihuPlaywrightExtractor:
|
||
"""知乎内容提取器 - 使用 Playwright"""
|
||
|
||
URL_PATTERNS = {
|
||
'answer': r'zhihu\.com/question/\d+/answer/(\d+)',
|
||
'article': r'zhuanlan\.zhihu\.com/p/(\d+)',
|
||
'question': r'zhihu\.com/question/(\d+)(?:$|/)',
|
||
}
|
||
|
||
def __init__(self, headless: bool = True, timeout: int = 30):
|
||
"""
|
||
初始化提取器
|
||
|
||
Args:
|
||
headless: 是否使用无头浏览器
|
||
timeout: 超时时间（秒）
|
||
"""
|
||
self.browser = PlaywrightBrowser(headless=headless, timeout=timeout)
|
||
self.markdown_converter = MarkdownConverter()
|
||
|
||
def identify_url_type(self, url: str) -> Optional[str]:
|
||
"""
|
||
识别 URL 类型
|
||
|
||
Returns:
|
||
'answer', 'article', 'question' 或 None
|
||
"""
|
||
for url_type, pattern in self.URL_PATTERNS.items():
|
||
if re.search(pattern, url):
|
||
return url_type
|
||
return None
|
||
|
||
def extract_id(self, url: str) -> Optional[str]:
|
||
"""
|
||
从 URL 中提取内容 ID
|
||
|
||
Returns:
|
||
内容 ID 或 None
|
||
"""
|
||
url_type = self.identify_url_type(url)
|
||
if url_type:
|
||
pattern = self.URL_PATTERNS[url_type]
|
||
match = re.search(pattern, url)
|
||
if match:
|
||
return match.group(1)
|
||
return None
|
||
|
||
def _extract_text_content(self, element) -> str:
|
||
"""提取元素的文本内容"""
|
||
if element is None:
|
||
return ''
|
||
return element.inner_text() if hasattr(element, 'inner_text') else ''
|
||
|
||
def _extract_html_content(self, element) -> str:
|
||
"""提取元素的 HTML 内容"""
|
||
if element is None:
|
||
return ''
|
||
return element.inner_html() if hasattr(element, 'inner_html') else ''
|
||
|
||
def _extract_answer_content(self) -> Dict[str, Any]:
|
||
"""提取回答内容"""
|
||
result = {
|
||
'type': 'answer',
|
||
'title': '',
|
||
'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}")
|
||
|
||
# 尝试保存页面快照用于调试
|
||
try:
|
||
import os
|
||
debug_dir = '/home/admin/.openclaw/workspace/debug'
|
||
os.makedirs(debug_dir, exist_ok=True)
|
||
self.browser.page.screenshot(path=os.path.join(debug_dir, 'zhihu_screenshot.png'))
|
||
with open(os.path.join(debug_dir, 'zhihu_page.html'), 'w', encoding='utf-8') as f:
|
||
f.write(self.browser.page.content())
|
||
print(f"页面快照已保存到 {debug_dir}")
|
||
except Exception as e:
|
||
print(f"保存页面快照时出错: {e}")
|
||
|
||
# 尝试多个可能的选择器
|
||
selectors = {
|
||
'title': ['h1.QuestionHeader-title', 'h1', '.QuestionHeader-main'],
|
||
'author': ['.AuthorInfo-name', '.AuthorInfo .Text', '[itemprop="name"]'],
|
||
'content': ['.RichContent-inner', '.RichContent', '.List-itemText', '[data-zop-feedlist] article'],
|
||
'time': ['.ContentItem-time', '[itemprop="dateCreated"]'],
|
||
'vote': ['.VoteButton--up .VoteButton-label', '.VoteButton--up']
|
||
}
|
||
|
||
for selector in selectors['title']:
|
||
title_elem = self.browser.query_selector(selector)
|
||
if title_elem:
|
||
result['title'] = self._extract_text_content(title_elem)
|
||
print(f"找到标题（使用选择器 {selector}）: {result['title'][:50]}...")
|
||
break
|
||
|
||
for selector in selectors['author']:
|
||
author_elem = self.browser.query_selector(selector)
|
||
if author_elem:
|
||
result['author'] = self._extract_text_content(author_elem)
|
||
print(f"找到作者（使用选择器 {selector}）: {result['author']}")
|
||
break
|
||
|
||
for selector in selectors['content']:
|
||
content_elem = self.browser.query_selector(selector)
|
||
if content_elem:
|
||
html_content = self._extract_html_content(content_elem)
|
||
result['content'] = html_content
|
||
result['content_markdown'] = self.markdown_converter.convert(html_content)
|
||
print(f"找到内容（使用选择器 {selector}），长度: {len(result['content_markdown'])}")
|
||
break
|
||
|
||
for selector in selectors['time']:
|
||
time_elem = self.browser.query_selector(selector)
|
||
if time_elem:
|
||
result['publish_time'] = time_elem.get_attribute('data-tooltip') or self._extract_text_content(time_elem)
|
||
break
|
||
|
||
for selector in selectors['vote']:
|
||
vote_elem = self.browser.query_selector(selector)
|
||
if vote_elem:
|
||
vote_text = self._extract_text_content(vote_elem)
|
||
try:
|
||
result['vote_up'] = int(vote_text.replace(',', ''))
|
||
except (ValueError, AttributeError):
|
||
pass
|
||
break
|
||
|
||
return result
|
||
|
||
def _extract_article_content(self) -> Dict[str, Any]:
|
||
"""提取文章内容"""
|
||
result = {
|
||
'type': 'article',
|
||
'title': '',
|
||
'author': '',
|
||
'content': '',
|
||
'content_markdown': '',
|
||
'publish_time': '',
|
||
'vote_up': 0,
|
||
}
|
||
|
||
# 提取文章标题
|
||
title_elem = self.browser.query_selector('.Post-Title')
|
||
if title_elem:
|
||
result['title'] = self._extract_text_content(title_elem)
|
||
|
||
# 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)
|
||
|
||
# 提取文章内容
|
||
content_elem = self.browser.query_selector('.Post-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)
|
||
|
||
# 提取发布时间
|
||
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 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]:
|
||
"""提取问题内容（问题页本身）"""
|
||
result = {
|
||
'type': 'question',
|
||
'title': '',
|
||
'author': '',
|
||
'content': '',
|
||
'content_markdown': '',
|
||
'publish_time': '',
|
||
'vote_up': 0,
|
||
}
|
||
|
||
# 提取问题标题
|
||
title_elem = self.browser.query_selector('h1.QuestionHeader-title')
|
||
if title_elem:
|
||
result['title'] = self._extract_text_content(title_elem)
|
||
|
||
# 提取问题详情
|
||
detail_elem = self.browser.query_selector('.QuestionHeader-detail')
|
||
if detail_elem:
|
||
html_content = self._extract_html_content(detail_elem)
|
||
result['content'] = html_content
|
||
result['content_markdown'] = self.markdown_converter.convert(html_content)
|
||
|
||
# 问题的作者通常是提问者
|
||
author_elem = self.browser.query_selector('.AuthorInfo-name')
|
||
if author_elem:
|
||
result['author'] = self._extract_text_content(author_elem)
|
||
|
||
return result
|
||
|
||
def extract(self, url: str) -> Optional[Dict[str, Any]]:
|
||
"""
|
||
从 URL 提取知乎内容
|
||
|
||
Args:
|
||
url: 知乎 URL
|
||
|
||
Returns:
|
||
包含提取内容的字典，结构如下:
|
||
{
|
||
'type': 'answer' | 'article' | 'question',
|
||
'title': str,
|
||
'author': str,
|
||
'content': str (HTML),
|
||
'content_markdown': str (Markdown),
|
||
'publish_time': str,
|
||
'vote_up': int,
|
||
}
|
||
如果提取失败返回 None
|
||
"""
|
||
try:
|
||
# 识别 URL 类型
|
||
url_type = self.identify_url_type(url)
|
||
if not url_type:
|
||
print(f"无法识别 URL 类型: {url}")
|
||
return None
|
||
|
||
print(f"URL 类型: {url_type}")
|
||
print(f"启动浏览器...")
|
||
|
||
# 启动浏览器
|
||
self.browser.start()
|
||
|
||
print(f"访问页面: {url}")
|
||
# 访问页面
|
||
self.browser.goto(url, wait_until="domcontentloaded")
|
||
|
||
print("等待页面加载...")
|
||
import time
|
||
time.sleep(3) # 等待 JavaScript 执行
|
||
|
||
# 尝试多个可能的选择器
|
||
if url_type == 'answer':
|
||
selectors = ['.RichContent-inner', '.RichContent', '.List-itemText', '[data-zop-feedlist]']
|
||
print(f"尝试查找选择器: {selectors}")
|
||
result = self._extract_answer_content()
|
||
elif url_type == 'article':
|
||
selectors = ['.Post-RichText', '.Post-Title']
|
||
print(f"尝试查找选择器: {selectors}")
|
||
result = self._extract_article_content()
|
||
else: # question
|
||
selectors = ['.QuestionHeader-title', 'h1']
|
||
print(f"尝试查找选择器: {selectors}")
|
||
result = self._extract_question_content()
|
||
|
||
# 添加额外信息
|
||
result['url'] = url
|
||
result['content_id'] = self.extract_id(url)
|
||
|
||
print(f"提取成功! 标题: {result['title'][:50]}...")
|
||
return result
|
||
|
||
except Exception as e:
|
||
print(f"提取知乎内容时出错: {e}")
|
||
import traceback
|
||
traceback.print_exc()
|
||
return None
|
||
finally:
|
||
# 关闭浏览器
|
||
self.browser.close()
|
||
|
||
def __enter__(self):
|
||
"""上下文管理器入口"""
|
||
return self
|
||
|
||
def __exit__(self, exc_type, exc_val, exc_tb):
|
||
"""上下文管理器出口"""
|
||
self.browser.close()
|
||
return False
|
||
|
||
|
||
# 便捷函数
|
||
def extract_zhihu_content(url: str, headless: bool = True, timeout: int = 30) -> Optional[Dict[str, Any]]:
|
||
"""
|
||
便捷函数：提取知乎内容
|
||
|
||
Args:
|
||
url: 知乎 URL
|
||
headless: 是否使用无头浏览器
|
||
timeout: 超时时间（秒）
|
||
|
||
Returns:
|
||
提取的内容字典
|
||
"""
|
||
with ZhihuPlaywrightExtractor(headless=headless, timeout=timeout) as extractor:
|
||
return extractor.extract(url)
|