一些中药（植物）有关的数据库

ETCM1.0/2.0

YaTCM

TCMSP

TCMdatabase

＊HIT 2.0

TCMSID

symmap2.0

TCMID

＊本草组鉴HERB

 wget? 

 

尝试爬虫下载？

尝试1-requests

import os
import requests
from bs4 import BeautifulSoup
import time


# 创建保存文件的目录
save_dir = "/home/databank_70t/chenyuanjie/outdoor_data/20241125_test_down_from_web
"
os.makedirs(save_dir, exist_ok=True)


# 需要爬取的编号范围
start_id = 1  # 起始编号
end_id = 2   # 结束编号（根据需要调整）


base_url = "http://herb.ac.cn/Detail/?v=HERB{:06d}&label=Herb"


for herb_id in range(start_id, end_id + 1):
    herb_number = f"HERB{herb_id:06d}"  # 格式化为 HERB000001
    url = base_url.format(herb_id)
    print(f"Processing {herb_number}: {url}")
    
    try:
        # 请求页面内容
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        
        # 定位页面中最后一个“Download”按钮
        all_download_buttons = soup.find_all('a', text="Download")
        if all_download_buttons:
            # 获取最后一个按钮
            download_button = all_download_buttons[-1]
            download_url = download_button['href']
            print(f"Found download link: {download_url}")
            
            # 下载文件内容
            file_response = requests.get(download_url)
            file_response.raise_for_status()
            
            # 保存文件
            file_path = os.path.join(save_dir, f"{herb_number}.txt")  # 文件命名
            with open(file_path, 'wb') as file:
                file.write(file_response.content)
            print(f"Downloaded and saved: {file_path}")
        else:
            print(f"No download link found for {herb_number}")
    except Exception as e:
        print(f"Failed to process {herb_number}: {e}")
    
    # 防止请求过快，避免被网站封禁
    time.sleep(1)

尝试2-selenium

from selenium import webdriver
from selenium.webdriver.firefox.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import os
import time
import glob
# 配置下载目录
download_directory = "/home/databank_70t/chenyuanjie/outdoor_data/20241125_test_down_from_web"  # 修改为你想保存文件的路径
if not os.path.exists(download_directory):
    os.makedirs(download_directory)
# 配置 Selenium
options = webdriver.FirefoxOptions()
options.set_preference("browser.download.folderList", 2)  # 使用自定义下载目录
options.set_preference("browser.download.dir", os.path.abspath(download_directory))
options.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/xlsx")  # 指定文件类型，防止弹窗
options.headless = True  # 无头模式，适合无图形界面环境
# 配置 Geckodriver 的路径
service = Service(executable_path='/home/databank_70t/chenyuanjie/apps/geckodriver')
# 启动 WebDriver
driver = webdriver.Firefox(service=service, options=options)
# 等待下载函数
def wait_for_download(directory, timeout=30):
    elapsed = 0
    while elapsed < timeout:
        files = glob.glob(f"{directory}/*.part")
        if not files:  # 没有部分下载文件，表示下载完成
            return True
        time.sleep(1)
        elapsed += 1
    raise TimeoutError("Download did not complete in time")
# HERB ID 范围
start_id = 1
end_id = 3
# 循环下载每个 HERB ID 的文件
for herb_id in range(start_id, end_id + 1):
    herb_str = f"HERB{herb_id:06d}"  # 格式化为 HERB000001, HERB000002...
    url = f"http://herb.ac.cn/Detail?v={herb_str}&label=Herb"
    try:
        # 打开对应的页面
        driver.get(url)


        # 找到 "Download" 按钮并点击
        download_button = WebDriverWait(driver, 10).until(
            EC.element_to_be_clickable((By.XPATH, '//button[text()="Download"]'))
        )
        download_button.click()


        # 等待文件下载完成
        wait_for_download(download_directory)


        # 重命名文件
        downloaded_files = os.listdir(download_directory)
        for file in downloaded_files:
            if file.endswith(".xlsx"):
                old_path = os.path.join(download_directory, file)
                new_path = os.path.join(download_directory, f"{herb_str}.xlsx")
                os.rename(old_path, new_path)
                print(f"Downloaded and renamed: {new_path}")
                break
    except Exception as e:
        print(f"Error processing {herb_str}: {e}")
# 关闭 WebDriver
driver.quit()

crul-

联系作者？无果-可能是由于这是关键数据吧

尝试先筛选条件，然后自己下载

TCMBank-中山大学

cnpd

HERB2.0也上线了，但是和1.0一样不提供中药和化合物的对应关系表

其他：

TCMNPAS：网络方剂学与网络药理学综合分析平台