对外py编写
This commit is contained in:
@@ -1,140 +0,0 @@
|
||||
# 学习强国重要新闻爬虫使用说明
|
||||
|
||||
## 功能概述
|
||||
|
||||
在 `XxqgCrawler` 类中新增了 `crawl_important` 方法，用于爬取学习强国"重要新闻"栏目的文章内容。
|
||||
|
||||
## 实现原理
|
||||
|
||||
该方法结合了旧版 `myQiangguo` 爬虫和新版 Selenium 爬虫的优势：
|
||||
|
||||
1. **获取文章列表**：参考旧版爬虫方式，使用 `requests` 库直接请求 JSON 接口获取文章列表
|
||||
- JSON接口地址: `https://www.xuexi.cn/lgdata/1jscb6pu1n2.json?_st=26095725`
|
||||
- 返回包含文章URL、标题、来源等基础信息的列表
|
||||
|
||||
2. **解析文章详情**：使用现有的 `parse_news_detail` 方法（基于 Selenium）解析每篇文章的详细内容
|
||||
- 提取标题、发布时间、来源
|
||||
- 提取正文内容（文字、图片、视频）
|
||||
- 保存完整的文章结构
|
||||
|
||||
## 使用方法
|
||||
|
||||
### 基本用法
|
||||
|
||||
```python
|
||||
from crawler.xxqg.XxqgCrawler import XxqgCrawler
|
||||
|
||||
# 初始化爬虫
|
||||
crawler = XxqgCrawler()
|
||||
|
||||
# 爬取重要新闻（默认最多60篇）
|
||||
result = crawler.crawl_important()
|
||||
|
||||
# 检查结果
|
||||
if result.success:
|
||||
print(f"成功爬取 {len(result.dataList)} 篇新闻")
|
||||
for news in result.dataList:
|
||||
print(f"标题: {news.title}")
|
||||
print(f"来源: {news.source}")
|
||||
print(f"发布时间: {news.publishTime}")
|
||||
else:
|
||||
print(f"爬取失败: {result.message}")
|
||||
|
||||
# 关闭浏览器
|
||||
crawler.driver.quit()
|
||||
```
|
||||
|
||||
### 自定义爬取数量
|
||||
|
||||
```python
|
||||
# 只爬取前10篇文章
|
||||
result = crawler.crawl_important(max_count=10)
|
||||
```
|
||||
|
||||
### 运行测试脚本
|
||||
|
||||
```bash
|
||||
cd f:\Project\schoolNews\schoolNewsCrawler\crawler\xxqg
|
||||
python test_important_crawler.py
|
||||
```
|
||||
|
||||
## 输出结果
|
||||
|
||||
爬取完成后，结果会自动保存到 `Xxqg_important_news.json` 文件中，包含以下信息：
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"title": "文章标题",
|
||||
"url": "文章URL",
|
||||
"source": "来源",
|
||||
"publishTime": "发布时间",
|
||||
"contentRows": [
|
||||
{
|
||||
"type": "text",
|
||||
"content": "段落文本"
|
||||
},
|
||||
{
|
||||
"type": "img",
|
||||
"content": "<img src='图片URL' />"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## 参数说明
|
||||
|
||||
### `crawl_important(max_count=60)`
|
||||
|
||||
- **max_count**: 最多爬取的文章数量，默认60篇
|
||||
- **返回值**: `ResultDomain` 对象
|
||||
- `success`: 是否成功
|
||||
- `code`: 状态码（0表示成功，1表示失败）
|
||||
- `message`: 提示信息
|
||||
- `dataList`: 新闻列表（`List[NewsItem]`）
|
||||
|
||||
## 注意事项
|
||||
|
||||
1. **浏览器初始化**：首次运行时会自动打开 Chrome 浏览器并访问学习强国主页获取 Cookie
|
||||
2. **验证码处理**：如果遇到验证码，程序会暂停30秒让用户手动完成验证
|
||||
3. **爬取速度**：每篇文章之间会有1-2秒的随机延迟，避免请求过快被封禁
|
||||
4. **资源清理**：使用完毕后记得调用 `crawler.driver.quit()` 关闭浏览器
|
||||
|
||||
## 与旧版爬虫的对比
|
||||
|
||||
### 旧版爬虫 (myQiangguo)
|
||||
- 使用 `requests` + `BeautifulSoup` 解析静态HTML
|
||||
- 依赖于特定的 `data+MD5.js` 接口格式
|
||||
- 需要处理不同格式的URL（.html和.json）
|
||||
|
||||
### 新版爬虫 (XxqgCrawler)
|
||||
- 结合 `requests` 获取列表 + `Selenium` 解析详情
|
||||
- 能够处理动态加载的内容
|
||||
- 统一的接口和返回格式
|
||||
- 更好的错误处理和日志记录
|
||||
|
||||
## 扩展功能
|
||||
|
||||
如果需要爬取其他栏目，可以参考 `crawl_important` 方法的实现，修改对应的 JSON 接口URL即可。
|
||||
|
||||
常见栏目的JSON接口：
|
||||
- 重要新闻: `https://www.xuexi.cn/lgdata/1jscb6pu1n2.json?_st=26095725`
|
||||
- 重要活动: `https://www.xuexi.cn/lgdata/1jpuhp6fn73.json?_st=26095746`
|
||||
- 重要会议: `https://www.xuexi.cn/lgdata/19vhj0omh73.json?_st=26095747`
|
||||
- 重要讲话: `https://www.xuexi.cn/lgdata/132gdqo7l73.json?_st=26095749`
|
||||
|
||||
## 技术架构
|
||||
|
||||
```
|
||||
crawl_important()
|
||||
├── requests 获取JSON列表
|
||||
│ └── 解析文章URL和基础信息
|
||||
├── 遍历URL列表
|
||||
│ ├── parse_news_detail() (Selenium)
|
||||
│ │ ├── 访问文章页面
|
||||
│ │ ├── 提取标题、时间、来源
|
||||
│ │ └── 解析内容（文字、图片、视频）
|
||||
│ └── 补充缺失的字段
|
||||
└── 保存结果到JSON文件
|
||||
```
|
||||
130
schoolNewsCrawler/crawler/xxqg/XxqgColumn.py
Normal file
130
schoolNewsCrawler/crawler/xxqg/XxqgColumn.py
Normal file
@@ -0,0 +1,130 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
学习强国栏目爬虫命令行工具
|
||||
用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
import time
|
||||
# Add project root directory to path to import crawler
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
|
||||
from crawler.xxqg.XxqgCrawler import XxqgCrawler
|
||||
from loguru import logger
|
||||
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
parser = argparse.ArgumentParser(
|
||||
description='学习强国新闻栏目爬虫工具',
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog="""
|
||||
"""
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--column', '-c',
|
||||
type=str,
|
||||
required=True,
|
||||
help='栏目名称 important：重要新闻， xuexishiping：学习时评，zonghexinwen：综合新闻，zhongxuanbu：中宣部'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--yesterday', '-y',
|
||||
type=str,
|
||||
default="True",
|
||||
help='是否抓取昨天的数据 (默认: True)'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--start', '-s',
|
||||
type=str,
|
||||
default=None,
|
||||
help='开始日期 (格式: YYYY-MM-DD)'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--end', '-e',
|
||||
type=str,
|
||||
default=None,
|
||||
help='结束日期 (格式: YYYY-MM-DD)'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--output', '-o',
|
||||
type=str,
|
||||
help='输出文件路径'
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# 获取参数
|
||||
column = args.column
|
||||
yesterday = str(args.yesterday)
|
||||
if yesterday.upper() == "FALSE":
|
||||
yesterday = False
|
||||
elif yesterday.upper() == "TRUE":
|
||||
yesterday = True
|
||||
else:
|
||||
parser.error("--yesterday 参数必须是 True 或 False")
|
||||
|
||||
start = args.start
|
||||
end = args.end
|
||||
output_file = args.output
|
||||
|
||||
logger.info("使用直接参数模式")
|
||||
|
||||
# column 必须存在
|
||||
if not column or not column.strip():
|
||||
parser.error("栏目不能为空！")
|
||||
try:
|
||||
logger.info(f"开始搜索: 栏目='{column}', 昨天={yesterday}, 开始日期={start}, 结束日期={end}")
|
||||
crawler = XxqgCrawler()
|
||||
url_config= crawler.config.urls[column]
|
||||
time.sleep(5)
|
||||
result = crawler.crawl_base(url_config, yesterday=yesterday, start=start, end=end)
|
||||
# print(result)
|
||||
output = {
|
||||
"code": result.code,
|
||||
"message": result.message,
|
||||
"success": result.success,
|
||||
"data": None,
|
||||
"dataList": [item.model_dump() for item in result.dataList] if result.dataList else []
|
||||
}
|
||||
# result = None
|
||||
# with open("F:\Project\schoolNews\schoolNewsCrawler\output\output.json", "r", encoding="utf-8") as f:
|
||||
# result = json.load(f)
|
||||
# print(result)
|
||||
# output = result
|
||||
|
||||
|
||||
if output_file:
|
||||
output_path = Path(output_file)
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(output, f, ensure_ascii=False, indent=2)
|
||||
logger.info(f"结果已保存到: {output_file}")
|
||||
|
||||
crawler.close()
|
||||
sys.exit(0 if result.success else 1)
|
||||
# print(json.dumps(output, ensure_ascii=False, indent=2))
|
||||
# sys.exit(0 if result["success"] else 1)
|
||||
except Exception as e:
|
||||
logger.error(f"执行失败: {str(e)}")
|
||||
error_output = {
|
||||
"code": 500,
|
||||
"message": f"执行失败: {str(e)}",
|
||||
"success": False,
|
||||
"data": None,
|
||||
"dataList": []
|
||||
}
|
||||
print(json.dumps(error_output, ensure_ascii=False, indent=2))
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -104,7 +104,7 @@ class XxqgCrawler(BaseCrawler):
|
||||
'sec-ch-ua-platform': '"Windows"'
|
||||
}
|
||||
),
|
||||
"zongheshiping": UrlConfig(
|
||||
"zonghexinwen": UrlConfig(
|
||||
url="https://www.xuexi.cn/7097477a9643eacffe4cc101e4906fdb/9a3668c13f6e303932b5e0e100fc248b.html",
|
||||
method="GET",
|
||||
params={
|
||||
@@ -359,7 +359,7 @@ class XxqgCrawler(BaseCrawler):
|
||||
"type": "text",
|
||||
"content": text_content
|
||||
})
|
||||
logger.debug(f"提取文字: {text_content[:50]}...")
|
||||
# logger.debug(f"提取文字: {text_content[:50]}...")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"处理内容元素失败: {str(e)}")
|
||||
@@ -369,7 +369,7 @@ class XxqgCrawler(BaseCrawler):
|
||||
|
||||
if is_page():
|
||||
pass
|
||||
logger.info(f"解析文章详情完成: {news_item.model_dump()}")
|
||||
logger.info(f"解析文章详情完成: {news_item.url}")
|
||||
return news_item
|
||||
|
||||
|
||||
@@ -577,7 +577,7 @@ class XxqgCrawler(BaseCrawler):
|
||||
# 解析meta请求响应获取channelId
|
||||
try:
|
||||
meta_data = json.loads(target_request.response.body)
|
||||
logger.info(f"Meta响应数据: {meta_data}")
|
||||
# logger.info(f"Meta响应数据: {meta_data}")
|
||||
|
||||
# 提取channelId
|
||||
if 'pageData' in meta_data and 'channel' in meta_data['pageData']:
|
||||
|
||||
106
schoolNewsCrawler/crawler/xxqg/XxqgSearch.py
Normal file
106
schoolNewsCrawler/crawler/xxqg/XxqgSearch.py
Normal file
@@ -0,0 +1,106 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
学习强国搜索爬虫命令行工具
|
||||
用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
import time
|
||||
# Add project root directory to path to import crawler
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
|
||||
from crawler.xxqg.XxqgCrawler import XxqgCrawler
|
||||
from loguru import logger
|
||||
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
parser = argparse.ArgumentParser(
|
||||
description='学习强国新闻搜索工具',
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog="""
|
||||
"""
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--query', '-q',
|
||||
type=str,
|
||||
required=True,
|
||||
help='搜索关键词'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--total', '-t',
|
||||
type=int,
|
||||
default=10,
|
||||
help='抓取数量 (默认: 10)'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--output', '-o',
|
||||
type=str,
|
||||
help='输出文件路径'
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# 获取参数
|
||||
key = args.query
|
||||
total = args.total
|
||||
output_file = args.output
|
||||
|
||||
logger.info("使用直接参数模式")
|
||||
|
||||
# 关键校验：key 必须存在
|
||||
if not key or not key.strip():
|
||||
parser.error("搜索关键词不能为空！")
|
||||
try:
|
||||
logger.info(f"开始搜索: 关键词='{key}', 数量={total}")
|
||||
crawler = XxqgCrawler()
|
||||
time.sleep(5)
|
||||
result = crawler.search(keyword=key.strip(), total=total)
|
||||
# print(result)
|
||||
output = {
|
||||
"code": result.code,
|
||||
"message": result.message,
|
||||
"success": result.success,
|
||||
"data": None,
|
||||
"dataList": [item.model_dump() for item in result.dataList] if result.dataList else []
|
||||
}
|
||||
# result = None
|
||||
# with open("F:\Project\schoolNews\schoolNewsCrawler\output\output.json", "r", encoding="utf-8") as f:
|
||||
# result = json.load(f)
|
||||
# print(result)
|
||||
# output = result
|
||||
|
||||
|
||||
if output_file:
|
||||
output_path = Path(output_file)
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(output, f, ensure_ascii=False, indent=2)
|
||||
logger.info(f"结果已保存到: {output_file}")
|
||||
|
||||
crawler.close()
|
||||
sys.exit(0 if result.success else 1)
|
||||
# print(json.dumps(output, ensure_ascii=False, indent=2))
|
||||
# sys.exit(0 if result["success"] else 1)
|
||||
except Exception as e:
|
||||
logger.error(f"执行失败: {str(e)}")
|
||||
error_output = {
|
||||
"code": 500,
|
||||
"message": f"执行失败: {str(e)}",
|
||||
"success": False,
|
||||
"data": None,
|
||||
"dataList": []
|
||||
}
|
||||
print(json.dumps(error_output, ensure_ascii=False, indent=2))
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,42 +0,0 @@
|
||||
"""
|
||||
测试学习强国重要新闻爬虫
|
||||
"""
|
||||
from XxqgCrawler import XxqgCrawler
|
||||
from loguru import logger
|
||||
|
||||
def test_crawl_important():
|
||||
"""测试爬取重要新闻"""
|
||||
try:
|
||||
# 初始化爬虫
|
||||
logger.info("初始化学习强国爬虫...")
|
||||
crawler = XxqgCrawler()
|
||||
|
||||
# 爬取重要新闻（默认最多60篇）
|
||||
logger.info("开始爬取重要新闻...")
|
||||
result = crawler.crawl_important(max_count=10) # 测试时只爬取10篇
|
||||
|
||||
# 检查结果
|
||||
if result.success:
|
||||
logger.info(f"爬取成功！{result.message}")
|
||||
logger.info(f"共爬取到 {len(result.dataList)} 篇新闻")
|
||||
|
||||
# 打印前3篇新闻标题
|
||||
for idx, news in enumerate(result.dataList[:3], 1):
|
||||
logger.info(f"{idx}. {news.title}")
|
||||
logger.info(f" 来源: {news.source}")
|
||||
logger.info(f" 发布时间: {news.publishTime}")
|
||||
logger.info(f" 内容行数: {len(news.contentRows)}")
|
||||
logger.info("")
|
||||
else:
|
||||
logger.error(f"爬取失败: {result.message}")
|
||||
|
||||
# 关闭浏览器
|
||||
if crawler.driver:
|
||||
crawler.driver.quit()
|
||||
logger.info("浏览器已关闭")
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"测试过程中发生错误: {str(e)}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_crawl_important()
|
||||
Reference in New Issue
Block a user