{ "cells": [ { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "# Corporate Intelligence" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## API Research\n", "\n", "### BundesAPI" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "*Down to due maintenance work from 24.03. - 26.03.*\n", "\n", "Basically a Bundesanzeiger Scraping Wrapper" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "dict_keys(['Aufsichtsrat', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2020 bis zum 31.12.2020', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2019 bis zum 31.12.2019', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2018 bis zum 31.12.2018', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2017 bis zum 31.12.2017', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2016 bis zum 31.12.2016', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2015 bis zum 31.12.2015', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2014 bis zum 31.12.2014', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2013 bis zum 31.12.2013', 'Jahresabschluss zum Geschäftsjahr vom 01.01.2012 bis zum 31.12.2012', 'Jahresabschluss zum Geschäftsjahr vom 01.10.2010 bis zum 30.06.2011', 'Jahresabschluss zum Geschäftsjahr vom 01.07.2011 bis zum 31.12.2011', 'Jahresbericht zum 31.3.2006', 'Jahresbericht 30.11.2022'])\n" ] } ], "source": [ "from deutschland.bundesanzeiger import Bundesanzeiger\n", "ba = Bundesanzeiger()\n", "# search term\n", "data = ba.get_reports(\"Atos IT-Dienstleistung & Beratung GmbH\")\n", "# returns a dictionary with all reports found as fulltext reports\n", "print(data.keys())" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'date': datetime.datetime(2017, 7, 17, 0, 0), 'name': 'Aufsichtsrat', 'company': 'Atos IT-Dienstleistung und Beratung GmbH', 'report': '\\n\\n\\n\\n\\xa0\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nAtos IT-Dienstleistung und Beratung GmbH\\nGelsenkirchen\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nWechsel im Aufsichtsrat der Atos IT-Dienstleistung und Beratung GmbH, Gelsenkirchen\\nBekanntmachung gemäß § 8 DrittelbG\\nHerr Harald Olivier ist aus dem Aufsichtsrat der Gesellschaft ausgeschieden.\\nDurch Beschluss des Amtsgerichts Gelsenkirchen vom 26.06.2017 ist\\n\\n\\n―\\n\\n\\nFrau Martina Dick\\n Stellvertretende Betriebsratsvorsitzende der Gesellschaft\\n\\n\\n\\nzum Mitglied des Aufsichtsrats als Vertreterin der Arbeitnehmer bestellt worden.\\n\\xa0\\n\\nGelsenkirchen, im Juli 2017\\nAtos IT-Dienstleistung und Beratung GmbH\\nDie Geschäftsführung\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n'}\n" ] } ], "source": [ "# Note: There can be multiple \"Aufsichtsrat\" entries per Company, the API however does only return one because the keys are overwritten\n", "print(data['Aufsichtsrat'])" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "None\n" ] } ], "source": [ "from deutschland.handelsregister import Handelsregister\n", "hr = Handelsregister()\n", "\n", "results = hr.search(keywords=\"BLUECHILLED Verwaltungs GmbH\")\n", "print(results)" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "### Offene Register" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "Hint: Visualize schema with tools such a [DBeaver](https://dbeaver.io/)\n", "\n", "Note: Not up-to-date" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# SQLite export\n", "import sqlite3\n", "con = sqlite3.connect(\"../data/openregister.db\")" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "cur = con.cursor()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[('name',),\n", " ('registrations',),\n", " ('officer',),\n", " ('company',),\n", " ('company_fts',),\n", " ('company_fts_data',),\n", " ('company_fts_idx',),\n", " ('company_fts_docsize',),\n", " ('company_fts_config',),\n", " ('officer_fts',),\n", " ('officer_fts_data',),\n", " ('officer_fts_idx',),\n", " ('officer_fts_docsize',),\n", " ('officer_fts_config',),\n", " ('name_fts',),\n", " ('name_fts_data',),\n", " ('name_fts_idx',),\n", " ('name_fts_docsize',),\n", " ('name_fts_config',)]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "schema = cur.execute(\"SELECT name FROM sqlite_master WHERE type='table';\")\n", "schema.fetchall()\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idcompany_numbercurrent_statusjurisdiction_codenameregistered_addressretrieved_atregister_flag_ADregister_flag_CDregister_flag_DK...native_company_numberregistered_officeregistrarregister_artregister_nummerformer_registrarregister_flag_register_flag_Note:_registerNummerSuffixregister_flag_Status information
01K1101R_HRB150148currently registereddeolly UG (haftungsbeschränkt)Waidmannstraße 1, 22769 Hamburg.2018-11-09T18:03:03Z111...Hamburg HRB 150148HamburgHamburgHRB150148NoneNoneNoneNoneNone
12R1101_HRB81092currently registereddeBLUECHILLED Verwaltungs GmbHOststr.2018-07-25T11:14:02Z111...Düsseldorf HRB 81092DüsseldorfDüsseldorfHRB81092NoneNoneNoneNoneNone
23H1101_H1101_HRB18423currently registereddeMittelständische Beteiligungsgesellschaft Brem...Langenstraße 2-4, 28195 Bremen.2018-06-24T21:12:00Z111...Bremen früher Bremen HRB 18423BremenBremenHRB18423BremenNoneNoneNoneNone
34R1101_HRB45109currently registereddeAlbert Barufe GmbHHans-Sachs-Straße 11, 40721 Hilden.2018-07-25T11:15:01Z111...Düsseldorf HRB 45109HildenDüsseldorfHRB45109NoneNoneNoneNoneNone
45R1101_HRB37996currently registereddeITERGO Informationstechnologie GmbHERGO-Platz 1, 40477 Düsseldorf.2018-07-25T12:32:08Z111...Düsseldorf HRB 37996DüsseldorfDüsseldorfHRB37996NoneNoneNoneNoneNone
\n", "

5 rows × 25 columns

\n", "
" ], "text/plain": [ " id company_number current_status jurisdiction_code \\\n", "0 1 K1101R_HRB150148 currently registered de \n", "1 2 R1101_HRB81092 currently registered de \n", "2 3 H1101_H1101_HRB18423 currently registered de \n", "3 4 R1101_HRB45109 currently registered de \n", "4 5 R1101_HRB37996 currently registered de \n", "\n", " name \\\n", "0 olly UG (haftungsbeschränkt) \n", "1 BLUECHILLED Verwaltungs GmbH \n", "2 Mittelständische Beteiligungsgesellschaft Brem... \n", "3 Albert Barufe GmbH \n", "4 ITERGO Informationstechnologie GmbH \n", "\n", " registered_address retrieved_at \\\n", "0 Waidmannstraße 1, 22769 Hamburg. 2018-11-09T18:03:03Z \n", "1 Oststr. 2018-07-25T11:14:02Z \n", "2 Langenstraße 2-4, 28195 Bremen. 2018-06-24T21:12:00Z \n", "3 Hans-Sachs-Straße 11, 40721 Hilden. 2018-07-25T11:15:01Z \n", "4 ERGO-Platz 1, 40477 Düsseldorf. 2018-07-25T12:32:08Z \n", "\n", " register_flag_AD register_flag_CD register_flag_DK ... \\\n", "0 1 1 1 ... \n", "1 1 1 1 ... \n", "2 1 1 1 ... \n", "3 1 1 1 ... \n", "4 1 1 1 ... \n", "\n", " native_company_number registered_office registrar \\\n", "0 Hamburg HRB 150148 Hamburg Hamburg \n", "1 Düsseldorf HRB 81092 Düsseldorf Düsseldorf \n", "2 Bremen früher Bremen HRB 18423 Bremen Bremen \n", "3 Düsseldorf HRB 45109 Hilden Düsseldorf \n", "4 Düsseldorf HRB 37996 Düsseldorf Düsseldorf \n", "\n", " register_art register_nummer former_registrar register_flag_ \\\n", "0 HRB 150148 None None \n", "1 HRB 81092 None None \n", "2 HRB 18423 Bremen None \n", "3 HRB 45109 None None \n", "4 HRB 37996 None None \n", "\n", " register_flag_Note: _registerNummerSuffix register_flag_Status information \n", "0 None None None \n", "1 None None None \n", "2 None None None \n", "3 None None None \n", "4 None None None \n", "\n", "[5 rows x 25 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "df = pd.read_sql_query(\"SELECT * FROM company LIMIT 100\", con)\n", "df.head()" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "### Open Corporates" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "import requests\n", "\n", "BASE_URL = \"https://api.opencorporates.com\"" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "401" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "response = requests.get(f\"{BASE_URL}/companies/search\")\n", "response.status_code" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "![](../images/open_corporates_pricing.png)" ] } ], "metadata": { "kernelspec": { "display_name": "venv", "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": "3.10.7" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }