From 127797b296081ee7f6817616b338cf17fadffed7 Mon Sep 17 00:00:00 2001
From: bql <72600300+baiqinglun@users.noreply.github.com>
Date: Mon, 19 Feb 2024 16:44:54 +0800
Subject: [PATCH] =?UTF-8?q?=E7=AC=AC=E4=B8=80=E6=AC=A1=E6=8F=90=E4=BA=A4?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md | 29 ++++++++++++++++++++++
 doi.csv   |  3 +++
 main.py   | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 run.bat   |  3 +++
 4 files changed, 108 insertions(+)
 create mode 100644 README.md
 create mode 100644 doi.csv
 create mode 100644 main.py
 create mode 100644 run.bat

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..0697645
--- /dev/null
+++ b/README.md
@@ -0,0 +1,29 @@
+通过文献的doi使用多线程下载文献
+
+## 使用说明
+
+### 获取并更改headers
+
+进入网址 https://www.sci-hub.ee/ 后按F12进入开发选项，然后刷新网页
+
+![](https://test-123456-md-images.oss-cn-beijing.aliyuncs.com/img/20240219163328.png)
+
+然后填在headers内
+
+![](https://test-123456-md-images.oss-cn-beijing.aliyuncs.com/img/20240219163404.png)
+
+### 输入doi
+
+打开doi.csv文件，并输入doi号
+
+![](https://test-123456-md-images.oss-cn-beijing.aliyuncs.com/img/20240219163509.png)
+
+### 更改python安装目录
+
+![](https://test-123456-md-images.oss-cn-beijing.aliyuncs.com/img/20240219163613.png)
+
+### 运行下载
+
+点击run.bat开始下载
+
+![](https://test-123456-md-images.oss-cn-beijing.aliyuncs.com/img/20240219163716.png)
\ No newline at end of file
diff --git a/doi.csv b/doi.csv
new file mode 100644
index 0000000..0e51d40
--- /dev/null
+++ b/doi.csv
@@ -0,0 +1,3 @@
+doi
+10.1136/gut.2009.182170
+10.3390/Brainsci10110868
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..2c25dc9
--- /dev/null
+++ b/main.py
@@ -0,0 +1,73 @@
+import requests
+import re
+import os
+import urllib.request
+import pandas as pd
+import threading
+import time
+from tqdm import tqdm
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36',
+}
+
+def getPaperPdf(doi):
+    # 下载文献
+    sci_Hub_Url = "https://www.sci-hub.ee/"
+    paper_url = sci_Hub_Url + doi
+    pattern = '/.*?\.pdf'
+    content = requests.get(paper_url, headers=headers)
+    download_url = re.findall(pattern, content.text)
+    download_url[1] = "https:" + download_url[1]
+    path = r"paper"
+    if not os.path.exists(path):
+        os.makedirs(path)
+
+    req = urllib.request.Request(download_url[1], headers=headers)
+    u = urllib.request.urlopen(req, timeout=5)
+
+    # 获取文献名称
+    title_base_url = "https://api.crossref.org/works/"
+    url = title_base_url + doi
+    response = requests.get(url)
+    title = ""
+    if response.status_code == 200:
+        data = response.json()
+        title = data["message"]["title"][0]
+        title = title.replace(':', '')
+    else:
+        print("Failed to fetch title for DOI:", doi)
+
+    # 写入
+    file_name = title + ".pdf"
+    f = open(os.path.join(path, file_name), 'wb')
+    block_sz = 8192
+    while True:
+        buffer = u.read(block_sz)
+        if not buffer:
+            break
+        f.write(buffer)
+    f.close()
+    print("Successful to download" + " " + file_name)
+
+# 开启多线程
+def download_papers(df):
+    threads = []
+    for doi in df['doi']:
+        thread = threading.Thread(target=getPaperPdf, args=(doi,))
+        threads.append(thread)
+        thread.start()
+
+    # 等待所有线程完成
+    for thread in threads:
+        thread.join()
+
+if __name__ == '__main__':
+    print("下载中......................................")
+    start_time = time.time()  # 记录开始下载的时间戳
+    df = pd.read_csv('doi.csv')
+    download_papers(df)
+    end_time = time.time()  # 记录结束下载的时间戳
+    download_time = end_time - start_time  # 计算下载所花费的时间
+    print("总下载时间：",download_time)
+    print("下载完成")
\ No newline at end of file
diff --git a/run.bat b/run.bat
new file mode 100644
index 0000000..89ce9f0
--- /dev/null
+++ b/run.bat
@@ -0,0 +1,3 @@
+@echo off
+D:\anaconda3\python.exe .\main.py
+pause