推理链专家
e492965ba1
覆盖全部11个数据源的可复用 scraper 模块 tools/scrapers.py： - gov.cn: 国务院政策文件库（HTML 解析） - xinhuanet (news.cn): 新华社受权发布（HTML 解析） - scio (pbc镜像): 国新办新闻发布会文字实录 - pbc: 央行货币政策/公告 - mof: 财政部政策 - ndrc: 发改委产业政策 - csrc: 证监会公告（HTML 解析） - mofcom: 商务部政策（JSON API） - people: 人民日报社论（HTML 解析） - cctv: 央视新闻联播（JSONP API） - ce: 经济日报政策解读 更新 SKILL.md 引用新工具，统一入口 scrape_list()/scrape_article()。 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai>
633 lines
22 KiB
Python
633 lines
22 KiB
Python
"""
|
||
政策雷达 - 政府网站抓取工具集
|
||
每个函数返回标准化格式: {"title": str, "date": str, "url": str, "content": str}
|
||
列表函数返回: [{"title": str, "date": str, "url": str}, ...]
|
||
"""
|
||
|
||
import re
|
||
import json
|
||
import urllib.request
|
||
import urllib.error
|
||
import ssl
|
||
from html import unescape
|
||
|
||
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||
TIMEOUT = 15
|
||
|
||
# 忽略 SSL 证书验证（部分政府站点使用自签名证书）
|
||
_SSL_CTX = ssl.create_default_context()
|
||
_SSL_CTX.check_hostname = False
|
||
_SSL_CTX.verify_mode = ssl.CERT_NONE
|
||
|
||
|
||
def _fetch(url, headers=None):
|
||
"""通用 HTTP GET，返回解码后的 HTML 文本"""
|
||
hdrs = {"User-Agent": USER_AGENT}
|
||
if headers:
|
||
hdrs.update(headers)
|
||
req = urllib.request.Request(url, headers=hdrs)
|
||
with urllib.request.urlopen(req, timeout=TIMEOUT, context=_SSL_CTX) as resp:
|
||
raw = resp.read()
|
||
for enc in ("utf-8", "gbk", "gb2312"):
|
||
try:
|
||
return raw.decode(enc)
|
||
except UnicodeDecodeError:
|
||
continue
|
||
return raw.decode("utf-8", errors="replace")
|
||
|
||
|
||
def _extract_paragraphs(html):
|
||
"""从 HTML 中提取正文段落（通用）"""
|
||
paragraphs = re.findall(r"<p[^>]*>(.*?)</p>", html, re.DOTALL)
|
||
result = []
|
||
for p in paragraphs:
|
||
text = re.sub(r"<[^>]+>", "", p).strip()
|
||
text = unescape(text)
|
||
if text and len(text) > 10:
|
||
result.append(text)
|
||
return result
|
||
|
||
|
||
# ============================================================
|
||
# 优先级 1: 中央政府门户
|
||
# ============================================================
|
||
|
||
def gov_search(keyword, page=1):
|
||
"""
|
||
中国政府网 - 搜索 API（可搜索新闻发布会等）
|
||
URL: https://sousuo.www.gov.cn/search-gov/data?t=zhengcelibrary&q=...
|
||
返回 JSON，包含 title/url/summary
|
||
注意: 索引有 1-2 周延迟，最新内容可能尚未收录
|
||
"""
|
||
import urllib.parse
|
||
q = urllib.parse.quote(keyword)
|
||
api_url = (
|
||
f"https://sousuo.www.gov.cn/search-gov/data?t=zhengcelibrary"
|
||
f"&q={q}&p={page}&n=20&timetype=timeqb&mintime=&maxtime="
|
||
)
|
||
html = _fetch(api_url)
|
||
try:
|
||
data = json.loads(html)
|
||
except json.JSONDecodeError:
|
||
return []
|
||
results = []
|
||
search_result = data.get("searchVO", {}).get("catMap", {}).get("zhengcelibrary", {})
|
||
items = search_result.get("listVO", []) if isinstance(search_result, dict) else []
|
||
for item in items:
|
||
title = re.sub(r"<[^>]+>", "", item.get("title", "")).strip()
|
||
url = item.get("url", "")
|
||
date = item.get("pubtime", "")[:10] if item.get("pubtime") else ""
|
||
if title and url:
|
||
results.append({"title": title, "date": date, "url": url})
|
||
return results
|
||
|
||
|
||
def gov_zhengce_list():
|
||
"""
|
||
中国政府网 - 国务院政策文件库
|
||
URL: https://www.gov.cn/zhengce/
|
||
结构: 服务端渲染，<li><a href="...">标题</a><span>日期</span></li>
|
||
"""
|
||
html = _fetch("https://www.gov.cn/zhengce/")
|
||
items = re.findall(
|
||
r'<li>\s*<a href="([^"]+)"[^>]*>\s*([^<]+)\s*</a>\s*<span>\s*([\d-]+)\s*</span>',
|
||
html,
|
||
)
|
||
results = []
|
||
for url, title, date in items:
|
||
title = title.strip()
|
||
if not title:
|
||
continue
|
||
if url.startswith("./"):
|
||
url = "https://www.gov.cn/zhengce/" + url[2:]
|
||
results.append({"title": title, "date": date, "url": url})
|
||
return results
|
||
|
||
|
||
def gov_article(url):
|
||
"""
|
||
中国政府网 - 政策文章正文
|
||
正文在 <div class="pages_content"> 内的 <p> 标签中
|
||
"""
|
||
html = _fetch(url)
|
||
# 提取标题
|
||
title_match = re.search(r'<title>([^<]+)</title>', html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
# 提取发布日期
|
||
date_match = re.search(r"发布时间[：:]\s*([\d年\-./]+)", html)
|
||
date = date_match.group(1).strip() if date_match else ""
|
||
# 提取正文
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": date,
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def scio_press_list():
|
||
"""
|
||
国新办 - 新闻发布会文字实录
|
||
注意: scio.gov.cn 有反爬保护，此处使用 PBC 站点作为镜像
|
||
PBC 的 "国新办举行新闻发布会" 系列完整保留了国新办原文
|
||
URL: https://www.pbc.gov.cn/goutongjiaoliu/113456/113469/index.html
|
||
"""
|
||
html = _fetch(
|
||
"https://www.pbc.gov.cn/goutongjiaoliu/113456/113469/index.html"
|
||
)
|
||
items = re.findall(
|
||
r'<a[^>]*href="(/goutongjiaoliu/[^"]+)"[^>]*>([^<]{10,})</a>',
|
||
html,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for href, title in items:
|
||
title = title.strip()
|
||
if title and href not in seen and "国新办" in title:
|
||
seen.add(href)
|
||
results.append(
|
||
{
|
||
"title": title,
|
||
"date": "",
|
||
"url": "https://www.pbc.gov.cn" + href,
|
||
}
|
||
)
|
||
return results
|
||
|
||
|
||
def xinhuanet_list():
|
||
"""
|
||
新华社 - 受权发布/时政
|
||
注意: 使用 www.news.cn（新域名），旧 xinhuanet.com 只有 2021 年旧数据
|
||
URL: https://www.news.cn/
|
||
结构: 服务端渲染，标题在 <div class="tit"><a href="URL">标题</a></div>
|
||
文章链接格式: /{channel}/{YYYYMMDD}/{32-hex}/c.html
|
||
"""
|
||
html = _fetch("https://www.news.cn/")
|
||
pattern = r'<div class="tit"[^>]*><a[^>]*href=[\'"](https?://www\.news\.cn/[^"\']+/20\d{6}/[a-f0-9]{32}/c\.html)[\'"][^>]*>([^<]+)</a>'
|
||
items = re.findall(pattern, html)
|
||
results = []
|
||
seen = set()
|
||
for url, title in items:
|
||
title = title.strip()
|
||
if title and url not in seen:
|
||
seen.add(url)
|
||
date_match = re.search(r"/(20\d{6})/", url)
|
||
date = ""
|
||
if date_match:
|
||
d = date_match.group(1)
|
||
date = f"{d[:4]}-{d[4:6]}-{d[6:8]}"
|
||
results.append({"title": title, "date": date, "url": url})
|
||
return results
|
||
|
||
|
||
def xinhuanet_article(url):
|
||
"""
|
||
新华社 - 文章正文
|
||
标题: <h1><span class="title">...</span></h1>
|
||
正文: <div id="detailContent"> 内的 <p> 标签
|
||
"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r'<h1[^>]*>.*?<span class="title"[^>]*>([^<]+)</span>', html, re.DOTALL)
|
||
if not title_match:
|
||
title_match = re.search(r'<title>([^<]+)</title>', html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
# 提取正文
|
||
content_match = re.search(r'id="detailContent"[^>]*>(.*?)</div>\s*(?:<div|</)', html, re.DOTALL)
|
||
if content_match:
|
||
content_html = content_match.group(1)
|
||
content_paras = _extract_paragraphs(content_html)
|
||
else:
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
# ============================================================
|
||
# 优先级 2: 部委官网
|
||
# ============================================================
|
||
|
||
def pbc_list():
|
||
"""
|
||
中国人民银行 - 货币政策/公告/沟通
|
||
URL: https://www.pbc.gov.cn/goutongjiaoliu/113456/113469/index.html
|
||
结构: 服务端渲染，<a href="/goutongjiaoliu/...">标题</a>
|
||
"""
|
||
html = _fetch(
|
||
"https://www.pbc.gov.cn/goutongjiaoliu/113456/113469/index.html"
|
||
)
|
||
items = re.findall(
|
||
r'<a[^>]*href="(/goutongjiaoliu/[^"]+)"[^>]*>([^<]{10,})</a>',
|
||
html,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for href, title in items:
|
||
title = title.strip()
|
||
if title and href not in seen and len(title) > 5:
|
||
seen.add(href)
|
||
# 从 URL 提取日期 (格式: 2026071518015458230)
|
||
date_match = re.search(r"/(20\d{6})\d{11}/", href)
|
||
date = ""
|
||
if date_match:
|
||
d = date_match.group(1)
|
||
date = f"{d[:4]}-{d[4:6]}-{d[6:8]}"
|
||
results.append(
|
||
{
|
||
"title": title,
|
||
"date": date,
|
||
"url": "https://www.pbc.gov.cn" + href,
|
||
}
|
||
)
|
||
return results
|
||
|
||
|
||
def pbc_article(url):
|
||
"""中国人民银行 - 文章正文（正文在 <p> 标签中）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def mof_list():
|
||
"""
|
||
财政部 - 财政新闻/政策
|
||
URL: https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/
|
||
结构: 服务端渲染，<a href="t202607...">标题</a> + 日期
|
||
"""
|
||
html = _fetch("https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/")
|
||
items = re.findall(
|
||
r'href="([^"]*t2026[^"]+\.htm)"[^>]*>\s*([^<]{10,80})\s*</a>\s*(?:.*?(\d{4}[-/]\d{2}[-/]\d{2}))?',
|
||
html,
|
||
re.DOTALL,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for url, title, date in items:
|
||
title = title.strip()
|
||
if title and url not in seen:
|
||
seen.add(url)
|
||
if url.startswith("./") or url.startswith("t20"):
|
||
url = "https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/" + url.replace("./", "")
|
||
results.append({"title": title, "date": date or "", "url": url})
|
||
return results
|
||
|
||
|
||
def mof_article(url):
|
||
"""财政部 - 文章正文"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
date_match = re.search(r"发布日期[：:]\s*([\d年\-./]+)", html)
|
||
date = date_match.group(1).strip() if date_match else ""
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": date,
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def ndrc_list(page=1):
|
||
"""
|
||
发改委 - 产业政策/规划
|
||
URL: https://www.ndrc.gov.cn/xxgk/
|
||
结构: 服务端渲染，<ul class="u-list"><li><a>标题</a><span>日期(YYYY/MM/DD)</span></li></ul>
|
||
分页: index_{page-1}.html
|
||
"""
|
||
if page == 1:
|
||
list_url = "https://www.ndrc.gov.cn/xxgk/"
|
||
else:
|
||
list_url = f"https://www.ndrc.gov.cn/xxgk/index_{page - 1}.html"
|
||
html = _fetch(list_url)
|
||
items = re.findall(
|
||
r'<a[^>]*href="([^"]+)"[^>]*>\s*([^<]{10,})\s*</a>\s*<span>\s*([\d/]+)\s*</span>',
|
||
html,
|
||
)
|
||
results = []
|
||
for url, title, date in items:
|
||
title = title.strip()
|
||
if not title:
|
||
continue
|
||
if url.startswith("./"):
|
||
url = "https://www.ndrc.gov.cn" + url[1:]
|
||
results.append({"title": title, "date": date, "url": url})
|
||
return results
|
||
|
||
|
||
def ndrc_article(url):
|
||
"""发改委 - 文章正文（正文在 div.TRS_Editor 内）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
editor_match = re.search(r'class="TRS_Editor"[^>]*>(.*?)</div>\s*<', html, re.DOTALL)
|
||
if editor_match:
|
||
content_paras = _extract_paragraphs(editor_match.group(1))
|
||
else:
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def csrc_list(page=1):
|
||
"""
|
||
证监会 - 主席讲话/政策公告
|
||
URL: https://www.csrc.gov.cn/csrc/c100028/
|
||
结构: HTML 页面（API 返回空结果，需用 common/searchList 获取 HTML）
|
||
HTML URL: /common/searchList/{channelid}?_isAgg=true&_isJson=true&_pageSize=18&_template=index&page={N}
|
||
"""
|
||
channel_id = "c100028"
|
||
url = f"https://www.csrc.gov.cn/common/searchList/{channel_id}?_isAgg=true&_isJson=true&_pageSize=18&_template=index&page={page}"
|
||
html = _fetch(url)
|
||
items = re.findall(
|
||
r'<a[^>]*href="(/csrc/c100028/c\d+/content\.shtml)"[^>]*>([^<]{10,})</a>',
|
||
html,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for path, title in items:
|
||
title = title.strip()
|
||
if title and path not in seen:
|
||
seen.add(path)
|
||
results.append(
|
||
{
|
||
"title": title,
|
||
"date": "",
|
||
"url": "https://www.csrc.gov.cn" + path,
|
||
}
|
||
)
|
||
return results
|
||
|
||
|
||
def csrc_article(url):
|
||
"""证监会 - 文章正文"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def mofcom_list():
|
||
"""
|
||
商务部 - 外贸/消费政策
|
||
URL: https://www.mofcom.gov.cn/
|
||
结构: 政策列表页使用 JSON API
|
||
API: /api-gateway/jpaas-publish-server/front/page/build/unit
|
||
"""
|
||
html = _fetch("https://www.mofcom.gov.cn/")
|
||
# 首页新闻是 SSR
|
||
items = re.findall(
|
||
r'<a[^>]*href="([^"]+)"[^>]*>\s*([^<]{10,80})\s*</a>',
|
||
html,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for url, title in items:
|
||
title = title.strip()
|
||
if title and url not in seen and len(title) > 8:
|
||
seen.add(url)
|
||
if url.startswith("/"):
|
||
url = "https://www.mofcom.gov.cn" + url
|
||
results.append({"title": title, "date": "", "url": url})
|
||
return results
|
||
|
||
|
||
def mofcom_article(url):
|
||
"""商务部 - 文章正文（正文在 div.wms-con 内）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
content_match = re.search(r'class="wms-con"[^>]*>(.*?)</div>\s*<', html, re.DOTALL)
|
||
if content_match:
|
||
content_paras = _extract_paragraphs(content_match.group(1))
|
||
else:
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
# ============================================================
|
||
# 优先级 3: 权威媒体转载
|
||
# ============================================================
|
||
|
||
def people_editorial_list():
|
||
"""
|
||
人民日报 - 社论/观点
|
||
URL: http://opinion.people.com.cn/GB/8213/49160/index.html
|
||
结构: 主页面有多个子栏目，每个子栏目页面有 <li> 文章列表
|
||
文章URL格式: /n1/2026/0623/c223228-40745676.html (相对) 或完整URL
|
||
"""
|
||
base = "http://opinion.people.com.cn/GB/8213/49160/"
|
||
html = _fetch(base + "index.html")
|
||
# 获取所有子栏目链接（完整URL）
|
||
sub_urls = re.findall(r'href="(http://opinion\.people\.com\.cn/GB/8213/49160/\d+/index\.html)"', html)
|
||
sub_urls = list(dict.fromkeys(sub_urls))
|
||
results = []
|
||
seen = set()
|
||
for sub in sub_urls:
|
||
try:
|
||
sub_html = _fetch(sub)
|
||
# 解析 <li> 项目（注意：人民网的链接使用单引号 href='...'）
|
||
lis = re.findall(r"<li[^>]*>(.*?)</li>", sub_html, re.DOTALL)
|
||
for li in lis:
|
||
# 匹配单引号或双引号的 href
|
||
m = re.search(r"href=['\"](/n1/\d{4}/\d{4}/c[\d-]+\.html)['\"][^>]*>([^<]{10,})</a>", li)
|
||
if m:
|
||
url_path, title = m.groups()
|
||
title = title.strip()
|
||
url = "http://opinion.people.com.cn" + url_path
|
||
if title and url not in seen:
|
||
seen.add(url)
|
||
date_match = re.search(r"/n1/(20\d{2})/(\d{4})/", url)
|
||
date = ""
|
||
if date_match:
|
||
year, md = date_match.groups()
|
||
date = f"{year}-{md[:2]}-{md[2:]}"
|
||
results.append({"title": title, "date": date, "url": url})
|
||
except Exception:
|
||
continue
|
||
return results
|
||
|
||
|
||
def people_article(url):
|
||
"""人民日报 - 文章正文（正文在 <p> 标签中，class=rm_txt_zw 的容器内）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
# 正文在 p 标签中
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def cctv_list(page=1):
|
||
"""
|
||
央视新闻 - 新闻联播文字版
|
||
URL: https://news.cctv.com/lbj/
|
||
结构: JSONP API
|
||
API: https://news.cctv.com/2019/07/gaiban/cmsdatainterface/page/china_{page}.jsonp?callback=china
|
||
注意: 需要设置 Referer 头
|
||
"""
|
||
api_url = f"https://news.cctv.com/2019/07/gaiban/cmsdatainterface/page/china_{page}.jsonp?callback=china"
|
||
raw = _fetch(api_url, headers={"Referer": "https://news.cctv.com/"})
|
||
# 解析 JSONP: china({...})
|
||
json_match = re.search(r"[^(]+\((\{.*\})\)", raw, re.DOTALL)
|
||
if not json_match:
|
||
return []
|
||
try:
|
||
data = json.loads(json_match.group(1))
|
||
except json.JSONDecodeError:
|
||
return []
|
||
items = data.get("data", {}).get("list", []) if isinstance(data.get("data"), dict) else []
|
||
results = []
|
||
for item in items:
|
||
title = item.get("title", "").strip()
|
||
url = item.get("url", item.get("link", ""))
|
||
date = item.get("focus_date", item.get("date", ""))
|
||
if title and url:
|
||
results.append(
|
||
{
|
||
"title": title,
|
||
"date": str(date)[:10],
|
||
"url": url,
|
||
}
|
||
)
|
||
return results
|
||
|
||
|
||
def cctv_article(url):
|
||
"""央视新闻 - 文章正文（正文在 div.content_area 内）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
content_match = re.search(r'class="content_area"[^>]*>(.*?)</div>\s*<', html, re.DOTALL)
|
||
if content_match:
|
||
content_paras = _extract_paragraphs(content_match.group(1))
|
||
else:
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
def ce_list():
|
||
"""
|
||
经济日报 - 部委政策解读
|
||
URL: http://www.ce.cn/
|
||
结构: 服务端渲染，文章链接格式: /xwzx/gnsz/gdxw/202607/t20260721_xxxxxxx.shtml
|
||
政策相关文章在 /gnsz/ (国内时政) 和 /xwzx/ (新闻) 栏目下
|
||
"""
|
||
html = _fetch("http://www.ce.cn/")
|
||
items = re.findall(
|
||
r'<a[^>]*href="([^"]*t2026[^"]+\.shtml)"[^>]*>([^<]{10,})</a>',
|
||
html,
|
||
)
|
||
results = []
|
||
seen = set()
|
||
for url, title in items:
|
||
title = title.strip()
|
||
# 过滤政策相关文章（国内时政/新闻栏目）
|
||
if "/gnsz/" not in url and "/xwzx/" not in url and "/syj/" not in url:
|
||
continue
|
||
if title and url not in seen:
|
||
seen.add(url)
|
||
if url.startswith("/"):
|
||
url = "http://www.ce.cn" + url
|
||
# 从 URL 提取日期
|
||
date_match = re.search(r"/(20\d{6})/", url)
|
||
date = ""
|
||
if date_match:
|
||
d = date_match.group(1)
|
||
date = f"{d[:4]}-{d[4:6]}-{d[6:8]}"
|
||
results.append({"title": title, "date": date, "url": url})
|
||
return results
|
||
|
||
|
||
def ce_article(url):
|
||
"""经济日报 - 文章正文（正文在 div.content.clearfix 内）"""
|
||
html = _fetch(url)
|
||
title_match = re.search(r'id="NewsArticleTitle"[^>]*>([^<]+)', html)
|
||
if not title_match:
|
||
title_match = re.search(r"<title>([^<]+)</title>", html)
|
||
title = title_match.group(1).strip() if title_match else ""
|
||
content_match = re.search(r'class="content clearfix"[^>]*>(.*?)</div>\s*<', html, re.DOTALL)
|
||
if content_match:
|
||
content_paras = _extract_paragraphs(content_match.group(1))
|
||
else:
|
||
content_paras = _extract_paragraphs(html)
|
||
return {
|
||
"title": title,
|
||
"date": "",
|
||
"url": url,
|
||
"content": "\n\n".join(content_paras),
|
||
}
|
||
|
||
|
||
# ============================================================
|
||
# 统一入口
|
||
# ============================================================
|
||
|
||
SCRAPERS = {
|
||
"gov.cn": {"list": gov_zhengce_list, "article": gov_article, "name": "中国政府网"},
|
||
"xinhuanet": {"list": xinhuanet_list, "article": xinhuanet_article, "name": "新华社"},
|
||
"pbc": {"list": pbc_list, "article": pbc_article, "name": "中国人民银行"},
|
||
"mof": {"list": mof_list, "article": mof_article, "name": "财政部"},
|
||
"ndrc": {"list": ndrc_list, "article": ndrc_article, "name": "发改委"},
|
||
"csrc": {"list": csrc_list, "article": csrc_article, "name": "证监会"},
|
||
"mofcom": {"list": mofcom_list, "article": mofcom_article, "name": "商务部"},
|
||
"people": {"list": people_editorial_list, "article": people_article, "name": "人民日报"},
|
||
"cctv": {"list": cctv_list, "article": cctv_article, "name": "央视新闻"},
|
||
"ce": {"list": ce_list, "article": ce_article, "name": "经济日报"},
|
||
"scio": {"list": scio_press_list, "article": pbc_article, "name": "国新办(PBC镜像)"},
|
||
}
|
||
|
||
|
||
def scrape_list(site_key, **kwargs):
|
||
"""统一列表抓取入口"""
|
||
scraper = SCRAPERS.get(site_key)
|
||
if not scraper:
|
||
return []
|
||
return scraper["list"](**kwargs)
|
||
|
||
|
||
def scrape_article(site_key, url):
|
||
"""统一文章抓取入口"""
|
||
scraper = SCRAPERS.get(site_key)
|
||
if not scraper:
|
||
return {"title": "", "date": "", "url": url, "content": ""}
|
||
return scraper["article"](url)
|