create function lib

cxyim · Feb 7, 2019 · 00e700b · 00e700b
1 parent c13d5ab
commit 00e700b
Show file tree

Hide file tree

Showing 6 changed files with 1,093 additions and 16 deletions.
diff --git a/log/author_url_set_log.txt b/log/author_url_set_log.txt
diff --git a/old_code/.ipynb_checkpoints/get_doc_biblio-checkpoint.ipynb b/old_code/.ipynb_checkpoints/get_doc_biblio-checkpoint.ipynb
@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "from pprint import pprint as fprint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'requests' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-1-222e90fcddd6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mdoc_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"http://www.cnki.com.cn/Article/CJFDTOTAL-TSQB201807022.htm\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdoc_url\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0mbs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBeautifulSoup\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'requests' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "doc_url = \"http://www.cnki.com.cn/Article/CJFDTOTAL-TSQB201807022.htm\"\n",
+    "r = requests.get(doc_url)\n",
+    "bs = BeautifulSoup(r.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "《图书情报工作》\n",
+      "纳米出版及其应用研究进展\n",
+      "['牛丽慧', '欧石燕']\n",
+      "[目的 /意义]随着学术期刊文献的大量增长,在传统科学文献出版模式下,科研人员需要花费大量时间从文献中查找、获取和解读所需信息。为了促进科学信息的传播与交流,面向科学文献内容的细粒度语义出版成为一种新趋势。本文介绍语义出版中的一种代表性出版模式\"纳米出版(nanopublication)\",并剖析纳米出版在不同学科领域中应用的可能性及应用特点。[方法 /过程]首先对纳米出版模型进行了介绍,然后通过文献调研对纳米出版的应用现状进行了述评,最后以实例说明纳米出版在不同学科领域中的应用特点。[结果 /结论]研究结果表明:(1)纳米出版目前主要应用于生物医学领域,在计算机和人文科学有少量应用,在其他领域几乎没有什么应用;(2)纳米出版可以扩展到其他学科领域进行应用,但是需要根据学科特征构建符合学科领域特点的纳米出版物。\n",
+      "南京大学信息管理学院\n",
+      "['纳米出版', '语义出版', '知识表示']\n",
+      "2018\n"
+     ]
+    }
+   ],
+   "source": [
+    "#journal\n",
+    "journal = bs.find(\"b\").text.strip()\n",
+    "print(journal)\n",
+    "\n",
+    "#title\n",
+    "title = bs.find(\"h1\").text.strip()\n",
+    "print(title)\n",
+    "\n",
+    "#ahthor\n",
+    "res = bs.find(\"div\",{\"style\":\"text-align:center; width:740px; height:30px;\"})\n",
+    "# print(res)\n",
+    "author_list = list()\n",
+    "for item in res.find_all(\"a\"):\n",
+    "    author_list.append(item.string.strip())\n",
+    "print(author_list)\n",
+    "\n",
+    "#abstract\n",
+    "abstract = bs.find(\"div\",{\"style\":\"text-align:left;word-break:break-all\"}).font.next_sibling.string.strip()\n",
+    "print(abstract)\n",
+    "\n",
+    "#address\n",
+    "address = bs.find(\"div\",{\"style\":\"text-align:left;\"}).a.string.strip()\n",
+    "print(address)\n",
+    "\n",
+    "#keywords\n",
+    "keyword_list = bs.find(\"meta\",{\"name\":\"keywords\"})[\"content\"].split()\n",
+    "print(keyword_list)\n",
+    "\n",
+    "#year\n",
+    "year = bs.find(\"font\",{\"color\":\"#0080ff\"}).string.strip()[:4]\n",
+    "print(year)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "write() takes exactly one argument (0 given)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-6-48fe4239b792>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      6\u001b[0m \u001b[0mres_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"T1 \"\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[0mres_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"JF \"\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mjournal\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m \u001b[0mres_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      9\u001b[0m \u001b[0mres_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mTypeError\u001b[0m: write() takes exactly one argument (0 given)"
+     ]
+    }
+   ],
+   "source": [
+    "file_name = \"download_\"+doc_url[31:-4]+\".txt\"\n",
+    "res_file = open(file_name,\"w\",encoding=\"utf-8\")\n",
+    "for i,author in enumerate(author_list):\n",
+    "    res_file.write(\"A\"+str(i+1)+\" \"+author+\"\\n\")\n",
+    "res_file.write(\"AD \"+address+\"\\n\")\n",
+    "res_file.write(\"T1 \"+title+\"\\n\")\n",
+    "res_file.write(\"JF \"+journal+\"\\n\")\n",
+    "res_file.write(\"YR \"+year+\"\\n\")\n",
+    "res_file.write(\"K1 \"+\";\".join(keyword_list)+\"\\n\")\n",
+    "res_file.write(\"AB \"+abstract+\"\\n\")\n",
+    "res_file.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/old_code/get_doc_biblio.ipynb b/old_code/get_doc_biblio.ipynb
@@ -13,9 +13,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'requests' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-1-222e90fcddd6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mdoc_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"http://www.cnki.com.cn/Article/CJFDTOTAL-TSQB201807022.htm\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdoc_url\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0mbs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBeautifulSoup\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'requests' is not defined"
+     ]
+    }
+   ],
    "source": [
     "doc_url = \"http://www.cnki.com.cn/Article/CJFDTOTAL-TSQB201807022.htm\"\n",
     "r = requests.get(doc_url)\n",