extracting XML titles

titles.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import xml.etree.ElementTree as ET"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "research-article\n",
      "A Functional Analysis of the Spacer of V(D)J Recombination Signal Sequences\n"
     ]
    }
   ],
   "source": [
    "filepath2=\"journal.pbio.0000001.xml\" \n",
    "tree2 = ET.parse(filepath2)\n",
    "root2 = tree2.getroot()\n",
    "title2=root2.find(\".//article-title\")\n",
    "type2=root2.get(\"article-type\")\n",
    "print(type2)\n",
    "print(title2.text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "genus-species\n",
      "research-article\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "#file = open(\"all_titles.txt\",\"w\", encoding='utf-8')  \n",
    "filepath1=\"journal.pbio.0000013.xml\"\n",
    "tree = ET.parse(filepath1)\n",
    "root = tree.getroot()\n",
    "y=root.find(\".//named-content\")\n",
    "z=y.get(\"content-type\")\n",
    "print(z)\n",
    "title=root.find(\".//article-title\")\n",
    "type=root.get(\"article-type\")\n",
    "print(type)\n",
    "print(title.text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://stackoverflow.com/questions/25218358/how-do-i-access-text-between-tags-with-xml-etree-elementtree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Drosophila', ' Free-Running Rhythms Require Intercellular Communication']"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text_parts = list(title.itertext())\n",
    "text_parts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Drosophila Free-Running Rhythms Require Intercellular Communication'"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\".join(title.itertext())"
   ]
  }
 ],
 "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}