import requests
from bs4 import BeautifulSoup
import re
import os
import json
from datetime import datetime
# 目标URL
url = "https://listing.szse.cn/projectdynamic/ipo/detail/index.
html?id=1003423"
# 创建存储目录
if not os.path.exists('./ipo_documents'):
os.makedirs('./ipo_documents')
# 请求头
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (K
HTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
'Accept': 'text/
html,application/x
html+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
'Connection': 'keep-alive',
'Referer': 'https://listing.szse.cn/disclosure/ipo/index.
html'
}
def extract_document_links(
html_content):
"""从
HTML内容中提取文档链接"""
soup = BeautifulSoup(
html_content, '
html.parser')
# 查找所有包含文档的表格行
rows = soup.select('tr')
documents = []
current_category = None
for row in rows:
# 检查
是否是类别行（包含<th>
标签）
if row.find('th'):
current_category = row.get_text(strip=True)
continue
# 检查
是否是文档行
if row.find('td'):
tds = row.find_all('td')
# 确保有足够的列
if len(tds) > 1:
doc_name = tds[0].get_text(strip=True)
# 处理日期和链接列
date_links = []
for td in tds[1:]:
# 查找所有链接
for link in td.find_all('a', href=True):
date_text = link.get_text(strip=True)
file_url = link['href']
# 清理URL中的空格和特殊字符
file_url = re.sub(r'\s+', '', file_url)
file_url = file_url.replace('”', '').replace('"', '')
# 跳过无效URL
if file_url.startswith('http'):
date_links.append({
'date': date_text,
'url': file_url
})
# 添
加到文档列表
if doc_name and date_links:
for dl in date_links:
documents.append({
'category': current_category,
'document_name': doc_name,
'publish_date': dl['date'],
'file_url': dl['url']
})
return documents
def main():
print(f"开始爬取IPO项目详情页: {url}")
try:
# 发送HTTP请求
response = requests.get(url, headers=headers)
response.raise_for_status() # 检查请求
是否成功
# 解析文档链接
documents = extract_document_links(response.text)
if documents:
# 创建结果文件名
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
output_file = f"./ipo_documents/project_1003423_{timestamp}.json"
# 保存结果到JSON文件
with open(output_file, 'w', encoding='utf-8') as f:
json.dump(documents, f, ensure_ascii=False, indent=2)
print(f"\n爬取完成! 共找到 {len(documents)} 个文档链接")
print(f"结果已保存到: {output_file}")
# 打印前3个结果示例
print("\n文档链接示例:")
for i, doc in enumerate(documents[:3]):
print(f"{i + 1}. {doc['category']} - {doc['document_name']}")
print(f" 发布日期: {doc['publish_date']}")
print(f" 文件URL: {doc['file_url']}\n")
else:
print("未找到任何文档链接")
except requests.exceptions.RequestException as e:
print(f"请求失败: {str(e)}")
except Exception as e:
print(f"发生错误: {str(e)}")
if __name__ == '__main__':
main() 修改代码，帮我提取出下列
html中的pdf链接
加到代码中，让运行后的代码下载出pdf文件进行存放。<td>招股说明书</td)
▼<td class="text-center
target="_
blank'
”href="httns://reDortdocs.static.sZse.cn/UpFi1es/rasinfodisc1/202306/RAS 202306 EFF55B536A0445029A7FC26A9AFDC151.Ddf" style="display:block;">2023-06-27</a
<a
target="_b1ank"href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202312/RAS 202312 31160583E7E90B12654185BD6F9CCCA47976D6.pdf"
href= style="display:block;">2023-12-31</a
<a
target=
"_
blank href="https://reDortdocs.static.szse.cn/UpFi1es/rasinfodisc1/202403/RAS 202403 1518253651462FDD5744BFBF999BDCA530BBD1.Ddf" style="display:block;">2024-03-15</a
<a
target="_b1ank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202407/RAS 202407 2521201348F597A7C0408EAA0147A41BBA30E8.pdf"
sty1e="display:b1ock;">2024-07-25</a
/a
target=
"
blank' href="httDs://reDortdocs.statiC.SZse.Cn/UpFi1es/rasinf9disc1/202409/RAS 202409 111700A6910513E1C7459DBC9F23DA12258A8E.Ddf” style="display:block;">2024-09-11</a
/2
target="
blank" href=
"https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202503/RAS_202503_2021351592FBC4C28B461CB055581BCF516C3E.pdf ”sty1e="disp1ay:b1ock;">2025-03-20</a
</td
▼<td class="text-center
a
target=”_b1ank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202506/RAS 202506 1021050A714A3ED75944E597BBAED9456B6037.pdf"
style="display:block;">2025-06-10</a
</td
▼<td class="text-center")
target="_
blank" href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202507/RAS 202507 041725E36EB4D843004F0997B334B64E5003BA. pdf” sty1e="disp1ay:b1ock;">2025-07-04</a
</td
</tr>
(tr
<td>发行保荐书</td>
▼<td class="text-center")
target=”
blank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202306/RAS 202306 58E303FEE6224DA2BC2F9E3E6AFA0AD7.pdf”style="display:block:">2023-06-27</a)
<a
target="_
blank"href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202312/RAS 202312 311605D9B366F45DDF48309F197AA265B20214.pdf”style="display:block;">2023-12-31</a
<a
target=”_
blank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202403/RAS 202403 151825E9082653339C4865B0AACF747572A8C6.pdf”
sty1e="disp1ay:b1ock:">2024-03-15</a
<a
target="_
blank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202407/RAS_202407 252120477EFCFD25BF4D50B92F00170E5260C0.pdf"
style="disp1ay:b1ock;">2024-07-25</a
/8
target="_
blank"
"href="https://reP0rtdocs.static.Szse.cn/UpFi1es/rasinfodisc1/202409/RAS 202409 1117006A832FC0F83C4E028E66B7FF1A096760.pdf"
sty1e="display:block;">2024-09-11</a
<a
target="_b1ank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202503/RAS 202503 202135865CD83D4D6E49F1809648ACAAD8E5E7.pdf"
target= style="display:block;">2025-03-20</a
</td)
▼<td class="text-center"
target=”_
blank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202506/RAS 202506 102105190C786D6F404C0DA93711F9C5B62411.pdf”style="disp1ay:b1ock:">2025-06-10</a
</td)
▼<td class="text-center"
target="_b1ank”href="https://reportdocs.static.szse.cn/UpFiles/rasinfodisc1/202507/RAS_202507 041725EA0CD092A7754891A7BA76821E20494E.pdf”style="disp1ay:b1ock;">2025-07-04</a
</td
</tr)
<trhttps://listing.szse.cn/projectdynamic/ipo/detail/index.
html?id=1003423 ，帮我爬取网址中的披露文件的链接等相关信息，帮我写出具体的python代码。
扫一扫
1335
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
