youmaniwa-blog_061019

textmining_youmaniwa_blog.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 記事の連続取得"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "前回のデータが残っていたら削除"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "if os.path.exists('raw_entry-contents.txt'):\n",
    "    print(\"以前実行したファイルが残っています\")\n",
    "    q_delete = input('削除しますか?(y/n) >> ')\n",
    "    if q_delete == 'y':\n",
    "        os.remove('raw_entry-contents.txt')\n",
    "        os.remove('prcsd_entry-contents.txt')\n",
    "else:\n",
    "    pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "HTTPリクエストを送りHTMLを抽出"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import re\n",
    "\n",
    "raw_urls = []\n",
    "urls = []\n",
    "with open('archive_url.txt','r') as f_in:\n",
    "    for url in f_in.readlines():\n",
    "        raw_urls.append(url)\n",
    "\n",
    "for i in raw_urls:\n",
    "    urls.append(i.replace('\\n',''))\n",
    "\n",
    "for url in urls:\n",
    "    r = requests.get(url)\n",
    "    r_text = r.content\n",
    "    \n",
    "    if r.status_code == 200:\n",
    "        soup = BeautifulSoup(r_text, 'lxml')\n",
    "        soup_entry = soup.find_all(class_='entry-content')\n",
    "    \n",
    "    with open('raw_entry-contents.txt','a', encoding = 'utf-8') as f_out:\n",
    "        for t in soup_entry:\n",
    "            f_out.write('{}\\n\\n---\\n\\n'.format(str(t.get_text)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "HTMLタグの除去"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "with open('raw_entry-contents.txt','r', encoding = 'utf-8') as cs_in:\n",
    "    raw_content = cs_in.read()\n",
    "\n",
    "with open('prcsd_entry-contents.txt','a', encoding = 'utf-8') as cs_out:\n",
    "    cs_out.write((re.sub('<.+?>',' ',raw_content)))"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}