知乎提取器：从 Playwright 迁移到 DrissionPage 方案
- 使用 DrissionPage 替代 Playwright - 实现 Cookie 管理和反爬绕过 - 支持回答/文章/问题三种内容类型 - 灵活配置（文件/环境变量/配置文件） - 更新文档和配置文件
This commit is contained in:
OpenClaw Agent
@@ -296,6 +296,37 @@ class Config:
|
||||
"""Get bilibili extraction timeout in seconds."""
|
||||
return self.get('sources.bilibili.extraction.timeout', 30)
|
||||
|
||||
# Zhihu DrissionPage configuration
|
||||
@property
|
||||
def zhihu_enabled(self) -> bool:
|
||||
"""知乎是否启用"""
|
||||
return self.get('sources.zhihu.enabled', False)
|
||||
|
||||
@property
|
||||
def zhihu_use_drissionpage(self) -> bool:
|
||||
"""知乎是否使用 DrissionPage"""
|
||||
return self.get('sources.zhihu.use_drissionpage', True)
|
||||
|
||||
@property
|
||||
def zhihu_cookie_file(self) -> Optional[str]:
|
||||
"""知乎 Cookie 文件路径"""
|
||||
return self.get('sources.zhihu.cookie_file')
|
||||
|
||||
@property
|
||||
def zhihu_cookie_str(self) -> Optional[str]:
|
||||
"""知乎 Cookie 字符串"""
|
||||
return self.get('sources.zhihu.cookie_str')
|
||||
|
||||
@property
|
||||
def zhihu_timeout(self) -> int:
|
||||
"""知乎提取超时时间（秒）"""
|
||||
return self.get('sources.zhihu.timeout', 30)
|
||||
|
||||
@property
|
||||
def zhihu_headless(self) -> bool:
|
||||
"""知乎是否使用无头浏览器"""
|
||||
return self.get('sources.zhihu.headless', True)
|
||||
|
||||
def ensure_dirs(self) -> None:
|
||||
"""Ensure required directories exist."""
|
||||
self.vault_path.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
@@ -10,45 +10,49 @@ from models import Content
|
||||
|
||||
class SourceAdapter(ABC):
|
||||
"""内容源适配器基类"""
|
||||
|
||||
|
||||
@abstractmethod
|
||||
def fetch_new(self, since: datetime, **kwargs) -> List[Content]:
|
||||
"""
|
||||
获取新内容
|
||||
|
||||
|
||||
Args:
|
||||
since: 起始时间，只获取该时间之后的内容
|
||||
**kwargs: 额外的参数
|
||||
|
||||
|
||||
Returns:
|
||||
List[Content]: 新内容列表
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
@abstractmethod
|
||||
def extract_content(self, url: str, **kwargs) -> Optional[Content]:
|
||||
"""
|
||||
从URL提取内容
|
||||
|
||||
|
||||
Args:
|
||||
url: 内容URL
|
||||
**kwargs: 额外的参数
|
||||
|
||||
|
||||
Returns:
|
||||
Optional[Content]: 内容对象，如果提取失败返回None
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
@abstractmethod
|
||||
def get_transcript(self, content: Content, **kwargs) -> Optional[str]:
|
||||
"""
|
||||
获取字幕/文本
|
||||
|
||||
|
||||
Args:
|
||||
content: 内容对象
|
||||
**kwargs: 额外的参数
|
||||
|
||||
|
||||
Returns:
|
||||
Optional[str]: 字幕文本（SRT格式），如果没有字幕返回None
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
# 为向后兼容，提供 BaseSource 别名
|
||||
BaseSource = SourceAdapter
|
||||
|
||||
@@ -5,6 +5,14 @@ from typing import Optional
|
||||
from .base import BaseSource
|
||||
from ..models import Content, ContentType
|
||||
|
||||
try:
|
||||
from .zhihu_drission_extractor import ZhihuDrissionExtractor
|
||||
except ImportError:
|
||||
# DrissionPage 未安装
|
||||
import logging
|
||||
logger = logging.getLogger(__name__)
|
||||
logger.warning(f"DrissionPage 未安装，无法提取知乎内容")
|
||||
|
||||
|
||||
class ZhihuSource(BaseSource):
|
||||
"""知乎文章/回答源"""
|
||||
@@ -52,13 +60,16 @@ class ZhihuSource(BaseSource):
|
||||
def get_transcript(self, content: Content) -> Optional[str]:
|
||||
"""获取文章内容"""
|
||||
try:
|
||||
# 优先使用 Playwright 提取
|
||||
from .zhihu_playwright_extractor import ZhihuPlaywrightExtractor
|
||||
# 使用 DrissionPage 提取器
|
||||
extractor = ZhihuDrissionExtractor(
|
||||
headless=self.config.get('headless', True),
|
||||
timeout=self.config.get('timeout', 30),
|
||||
config=self.config
|
||||
)
|
||||
|
||||
extractor = ZhihuPlaywrightExtractor()
|
||||
data = extractor.extract(content.url)
|
||||
|
||||
if data and data.get('content'):
|
||||
if data and data.get('content_markdown'):
|
||||
# 更新元数据
|
||||
if data.get('title'):
|
||||
content.title = data['title']
|
||||
@@ -66,18 +77,15 @@ class ZhihuSource(BaseSource):
|
||||
content.author = data['author']
|
||||
|
||||
# 返回 Markdown 内容
|
||||
return data['content']
|
||||
return data['content_markdown']
|
||||
|
||||
except ImportError as e:
|
||||
# Playwright 未安装
|
||||
import logging
|
||||
logger = logging.getLogger(__name__)
|
||||
logger.warning(f"Playwright 未安装，使用 HTTP 方案: {e}")
|
||||
logger.error(f"DrissionPage 导入失败: {e}")
|
||||
except Exception as e:
|
||||
# Playwright 提取失败
|
||||
import logging
|
||||
logger = logging.getLogger(__name__)
|
||||
logger.error(f"Playwright 提取失败: {e}")
|
||||
logger.error(f"DrissionPage 提取失败: {e}")
|
||||
|
||||
# 降级到原有 HTTP 方案（保留现有逻辑）
|
||||
return self._fetch_with_http(content.url)
|
||||
return None
|
||||
|
||||
@@ -0,0 +1,491 @@
|
||||
"""
|
||||
知乎 DrissionPage 内容提取器
|
||||
使用 DrissionPage 浏览器自动化工具抓取知乎内容
|
||||
"""
|
||||
|
||||
import re
|
||||
import json
|
||||
import sys
|
||||
import os
|
||||
from typing import Dict, Optional, Any, List
|
||||
from pathlib import Path
|
||||
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 DrissionBrowser:
|
||||
"""DrissionPage 浏览器管理器"""
|
||||
|
||||
def __init__(self, headless: bool = True, timeout: int = 30):
|
||||
self.headless = headless
|
||||
self.timeout = timeout
|
||||
self.page = None
|
||||
|
||||
def start(self):
|
||||
"""启动浏览器"""
|
||||
from DrissionPage import ChromiumOptions, ChromiumPage
|
||||
|
||||
options = ChromiumOptions()
|
||||
if self.headless:
|
||||
options.headless()
|
||||
options.set_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 = ChromiumPage(options)
|
||||
self.page.set.timeouts(base=self.timeout)
|
||||
|
||||
def close(self):
|
||||
"""关闭浏览器"""
|
||||
if self.page:
|
||||
self.page.quit()
|
||||
self.page = None
|
||||
|
||||
def goto(self, url: str):
|
||||
"""导航到指定 URL"""
|
||||
self.page.get(url)
|
||||
|
||||
def wait_for_selector(self, selector: str, timeout: int = None):
|
||||
"""等待选择器出现"""
|
||||
timeout = timeout or self.timeout
|
||||
self.page.wait.ele_displayed(selector, timeout=timeout)
|
||||
|
||||
def query_selector(self, selector: str):
|
||||
"""查询选择器"""
|
||||
return self.page.ele(selector)
|
||||
|
||||
def query_selector_all(self, selector: str):
|
||||
"""查询所有匹配的选择器"""
|
||||
return self.page.eles(selector)
|
||||
|
||||
def evaluate(self, script: str):
|
||||
"""执行 JavaScript 代码"""
|
||||
return self.page.run_js(script)
|
||||
|
||||
def get_page_title(self):
|
||||
"""获取页面标题"""
|
||||
if self.page:
|
||||
return self.page.title
|
||||
return ''
|
||||
|
||||
def get_page_content(self):
|
||||
"""获取页面 HTML 内容"""
|
||||
if self.page:
|
||||
return self.page.html
|
||||
return ''
|
||||
|
||||
def screenshot(self, path: str):
|
||||
"""截图"""
|
||||
if self.page:
|
||||
self.page.get_screenshot(path=path)
|
||||
|
||||
|
||||
class ZhihuDrissionExtractor:
|
||||
"""知乎 DrissionPage 提取器"""
|
||||
|
||||
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, config: Optional[Dict] = None):
|
||||
"""
|
||||
初始化提取器
|
||||
|
||||
Args:
|
||||
headless: 是否使用无头浏览器（默认 True）
|
||||
timeout: 超时时间（秒，默认 30）
|
||||
config: 配置字典，用于加载 Cookie
|
||||
"""
|
||||
self.headless = headless
|
||||
self.timeout = timeout
|
||||
self.config = config or {}
|
||||
# 支持从 config 中获取 headless 和 timeout
|
||||
if self.config.get('headless') is not None:
|
||||
self.headless = self.config.get('headless')
|
||||
if self.config.get('timeout') is not None:
|
||||
self.timeout = self.config.get('timeout')
|
||||
|
||||
self.browser = DrissionBrowser(headless=self.headless, timeout=self.timeout)
|
||||
self.markdown_converter = MarkdownConverter()
|
||||
self.cookie_file = os.path.join(
|
||||
os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
|
||||
'data', 'cookies', 'zhihu.json'
|
||||
)
|
||||
|
||||
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.text if hasattr(element, 'text') else ''
|
||||
|
||||
def _extract_html_content(self, element) -> str:
|
||||
"""提取元素的 HTML 内容"""
|
||||
if element is None:
|
||||
return ''
|
||||
return element.html if hasattr(element, 'html') else ''
|
||||
|
||||
def _extract_attribute(self, selector: str, attribute: str) -> str:
|
||||
"""提取元素的属性"""
|
||||
try:
|
||||
element = self.browser.query_selector(selector)
|
||||
if element:
|
||||
return element.attr(attribute) or ''
|
||||
except Exception as e:
|
||||
print(f"提取属性时出错（选择器: {selector}, 属性: {attribute}）: {e}")
|
||||
return ''
|
||||
|
||||
def _load_cookies(self) -> List[Dict]:
|
||||
"""
|
||||
加载 Cookie，优先级：配置 > 环境 > 文件
|
||||
|
||||
Returns:
|
||||
Cookie 列表
|
||||
"""
|
||||
cookies = []
|
||||
|
||||
# 1. 尝试从配置加载（优先级最高）
|
||||
if self.config.get('zhihu.cookie_str'):
|
||||
try:
|
||||
cookies = json.loads(self.config.get('zhihu.cookie_str'))
|
||||
print(f"从配置加载 Cookie，共 {len(cookies)} 个")
|
||||
except json.JSONDecodeError as e:
|
||||
print(f"配置中的 Cookie JSON 格式错误: {e}")
|
||||
|
||||
# 2. 尝试从环境变量加载（优先级中等）
|
||||
elif os.getenv('ZHIHU_COOKIE'):
|
||||
try:
|
||||
cookies = json.loads(os.getenv('ZHIHU_COOKIE'))
|
||||
print(f"从环境变量加载 Cookie，共 {len(cookies)} 个")
|
||||
except json.JSONDecodeError as e:
|
||||
print(f"环境变量中的 Cookie JSON 格式错误: {e}")
|
||||
|
||||
# 3. 尝试从文件加载（优先级最低）
|
||||
else:
|
||||
cookie_file = self.config.get('zhihu.cookie_file', self.cookie_file)
|
||||
if cookie_file and Path(cookie_file).exists():
|
||||
try:
|
||||
with open(cookie_file, 'r', encoding='utf-8') as f:
|
||||
cookies = json.load(f)
|
||||
print(f"从文件加载 Cookie ({cookie_file})，共 {len(cookies)} 个")
|
||||
except (json.JSONDecodeError, FileNotFoundError, IOError) as e:
|
||||
print(f"从文件加载 Cookie 失败: {e}")
|
||||
else:
|
||||
print("未找到 Cookie 配置，将使用未登录状态访问知乎")
|
||||
|
||||
return cookies
|
||||
|
||||
def _apply_cookies(self, cookies: List[Dict]):
|
||||
"""
|
||||
应用 Cookie 到浏览器页面
|
||||
|
||||
Args:
|
||||
cookies: Cookie 列表
|
||||
"""
|
||||
if not cookies:
|
||||
return
|
||||
|
||||
try:
|
||||
for cookie in cookies:
|
||||
if self.browser and self.browser.page:
|
||||
self.browser.page.set.cookies.add(cookie)
|
||||
print(f"成功应用 {len(cookies)} 个 Cookie")
|
||||
except Exception as e:
|
||||
print(f"应用 Cookie 时出错: {e}")
|
||||
|
||||
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.get_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.screenshot(os.path.join(debug_dir, 'zhihu_drission_screenshot.png'))
|
||||
with open(os.path.join(debug_dir, 'zhihu_drission_page.html'), 'w', encoding='utf-8') as f:
|
||||
f.write(self.browser.get_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.attr('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.attr('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,
|
||||
'url': str,
|
||||
'content_id': str,
|
||||
}
|
||||
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}")
|
||||
|
||||
# 加载 Cookie
|
||||
cookies = self._load_cookies()
|
||||
if cookies:
|
||||
print(f"加载了 {len(cookies)} 个 Cookie")
|
||||
|
||||
print(f"启动浏览器...")
|
||||
|
||||
# 启动浏览器
|
||||
self.browser.start()
|
||||
|
||||
# 应用 Cookie
|
||||
if cookies and self.browser.page:
|
||||
self._apply_cookies(cookies)
|
||||
|
||||
print(f"访问页面: {url}")
|
||||
# 访问页面
|
||||
self.browser.goto(url)
|
||||
|
||||
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, config=None) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
便捷函数：提取知乎内容
|
||||
|
||||
Args:
|
||||
url: 知乎 URL
|
||||
config: 配置字典
|
||||
|
||||
Returns:
|
||||
提取的内容字典
|
||||
"""
|
||||
with ZhihuDrissionExtractor(config=config) as extractor:
|
||||
return extractor.extract(url)
|
||||
Reference in New Issue
Block a user