请求与解析.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = requests.session()\n",
    "r = s.get(\"https://github.com/events\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from lxml import html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "root = html.fromstring(r.content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['GitHub Events · GitHub']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "root.xpath(\"//title/text()\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Events']"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "root.xpath(\"//h1/text()\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['/join?source=header',\n",
       " '/features',\n",
       " '/features/code-review/',\n",
       " '/features/project-management/',\n",
       " '/features/integrations',\n",
       " '/features/actions',\n",
       " '/features/package-registry',\n",
       " '/features#team-management',\n",
       " '/features#social-coding',\n",
       " '/features#documentation',\n",
       " '/features#code-hosting',\n",
       " '/customer-stories',\n",
       " '/security',\n",
       " '/enterprise',\n",
       " '/explore',\n",
       " '/topics',\n",
       " '/collections',\n",
       " '/trending',\n",
       " '/marketplace',\n",
       " '/pricing',\n",
       " '/pricing#feature-comparison',\n",
       " '/nonprofit',\n",
       " '/login?return_to=%2Fevents',\n",
       " '/join?source=header',\n",
       " '/explore',\n",
       " '/topics',\n",
       " '/collections',\n",
       " '/events',\n",
       " '/',\n",
       " '/features',\n",
       " '/security',\n",
       " '/enterprise',\n",
       " '/customer-stories',\n",
       " '/pricing',\n",
       " '/about/careers',\n",
       " '/about/press',\n",
       " '/site/terms',\n",
       " '/site/privacy']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 取属性，使用@符号，比如“@href”\n",
    "root.xpath(\"//a[starts-with(@href, '/')]/@href\")"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}