[python]批量下载pubmed文献 使用sci-hub和noteexpress

pubmed上下载好题录,导入NE

然后自定义样式,导出txt
第一行需要自己空一行出来


python代码:

import requests
from bs4 import BeautifulSoup
import os

DOI = []
f = open("C:/Users/docto/Desktop/doi1.txt", "r", encoding="utf-8")
for line in f.readlines():
    line = line[:-1]  #去掉换行符
    DOI.append(line)
DOI = DOI[1:]  #从第二行开始  第一行是空格
#print(DOI)

path = "C:/Users/docto/Desktop/sci_hub文献下载_doi1"   #输出文件夹所在地
if os.path.exists(path) == False:    #如果没有这个文件夹,那就创建一个
	os.mkdir(path)

head = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'
        }

i = 0
for doi in DOI:
    i = i + 1
    print("n" + "[" + str(i) + "]")
    doi = doi.split("-doi:")  #将这一行字段分成两部分 doi[1],和doi[2]  "-doi"会消失在字段里
    url = "https://www.sci-hub.ren/" + doi[1]
    #print("  trying:  "+url)
    filename = path +"/"+ doi[0] + ".pdf"
    if os.path.exists(filename) == False: #判断是否存在这个文件了
        try:
            r = requests.get(url, headers = head)
            r.raise_for_status()
            r.encoding = r.apparent_encoding
            soup = BeautifulSoup(r.text, "html.parser")
            download_url = soup.iframe.attrs["src"]
            print("  Downloading:" + doi[0])
            download_r = requests.get(download_url, headers = head)
            download_r.raise_for_status()
            f = open(path +"/"+ doi[0] + ".pdf", "wb")
            f.write(download_r.content)
            print(" √" )
        except:    #跳过出错
            print("  XXX Cannot download:  " + doi[1] + "n  " + doi[0] + "n  " + url)
    else:
        print("  Pdf already exists: " + doi[0])