1.1 使用Biopython查找与任一药物和某种疾病相关文献并输出文献总数
from Bio import Entrez
# 设置 Entrez 的邮箱,作为唯一标识符
Entrez.email = "beixun2023@outlook.com"
# 使用 Entrez 搜索 PubMed
handle = Entrez.esearch(db="pubmed", term="asthma AND albuterol", retmax=50)
record = Entrez.read(handle)
handle.close()
# 获取找到的文章总数
article_count = record['Count']
# 打印文章总数
print(f"文献总数: {article_count}")
## 文献总数: 6681
# 从找到的文章中获取前三篇的PMID
pmids = record['IdList']
print(f"前三篇文献的PMID:{pmids[:3]}")
## 前三篇文献的PMID:['38713039', '38703974', '38702638']
1.2 利用selenium打开文献页面保存
from selenium import webdriver
import time
# 创建WebDriver实例
driver = webdriver.Edge()
for pmid in pmids[:3]:
url = f"https://pubmed.ncbi.nlm.nih.gov/{pmid}/"
driver.get(url)
time.sleep(5) # 确保页面加载完毕
html_content = driver.page_source
with open(f"./class01_html/{pmid}.html", 'w', encoding='utf-8') as file:
file.write(html_content)
## 130127
## 107108
## 170362
driver.quit()
![保存的html文件](https://img-blog.csdnimg.cn/direct/df8354c626334523802a3921441b5c2a.png)
1.3 使用paperscraper下载文献
from paperscraper.pdf import save_pdf
import os
# 定义一个计数器,跟踪成功下载的次数
success_count = 0
# 遍历检索到的文献
for pmid in pmids[:10]:
# 如果成功下载次数达到三次,退出循环
if success_count >= 3:
break
# 获取文献信息
summary_handle = Entrez.esummary(db="pubmed", id=pmid)
summary_record = Entrez.read(summary_handle)
doi = summary_record[0]["DOI"]
print(pmid, ":", doi)
# 利用paperscraper下载文献
paper_data = {"doi": doi}
save_pdf(paper_data, filepath=f"./class01_paper/{pmid}.pdf")
# 检查下载成功还是失败
if os.path.exists(f"./class01_paper/{pmid}.pdf"):
print(f"./class01_paper/{pmid}文献下载成功")
# 成功下载一次,计数器加一
success_count += 1
else:
print(f"{pmid}文献下载失败")
continue
## 38713039 : 10.26442/00403660.2024.03.202631
## 38713039文献下载失败
## 38703974 : 10.1016/j.resp.2024.104271
## 38703974文献下载失败
## 38702638 : 10.1186/s12887-024-04749-4
## ./class01_paper/38702638文献下载成功
## 38698565 : 10.1177/17534666241232264
## 38698565文献下载失败
## 38693043 : 10.1016/j.jped.2024.03.012
## 38693043文献下载失败
## 38684750 : 10.1038/s41598-024-59588-1
## ./class01_paper/38684750文献下载成功
## 38684652 : 10.1038/s41533-024-00363-0
## ./class01_paper/38684652文献下载成功
![下载的pdf文献](https://img-blog.csdnimg.cn/direct/1b3b16100871431bba78079916e2f463.png)