From c47f3c1760c4889fed2c321c8d6fabc457010817 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Sat, 11 Jul 2020 12:02:55 +0200 Subject: [PATCH] Updated version and documentation --- CHANGELOG.rst | 3 +++ README.rst | 11 +++++++++-- setup.py | 2 +- 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.rst b/CHANGELOG.rst index 66ee5dc..792e513 100644 --- a/CHANGELOG.rst +++ b/CHANGELOG.rst @@ -3,6 +3,9 @@ Changelog This changelog contains a list of versions with their respective high-level changes. +v0.4.0: + - added public scraping support + - added geckodriver path for internal scraping v0.3.7: - changed login link v0.3.6: diff --git a/README.rst b/README.rst index b9d7d45..c8f04ed 100644 --- a/README.rst +++ b/README.rst @@ -6,9 +6,10 @@ ALLRIS Scraper .. image:: https://img.shields.io/pypi/pyversions/twomartens.allrisscraper.svg :alt: Python 3.7 and 3.8 .. image:: https://img.shields.io/pypi/v/twomartens.allrisscraper.svg - :alt: version 0.3.5 + :alt: version 0.4.0 -This scraper requires your username and password and performs the following tasks for you: +This scraper offers both public and private scraping. The latter requires your username and password and performs the +following tasks for you: - login - download of all agendas and motions related to upcoming meetings of committees and plenary sessions @@ -18,6 +19,9 @@ This scraper requires your username and password and performs the following task **IMPORTANT:** All districts are supported but official committee abbreviations will only work for Eimsbüttel as of now. +The public scraper ought to be used with care as it accesses all accessible pages of an entire month. Currently, +June 2020 is hardcoded and it can only be used in a GUI environment. + Requirements ------------ @@ -51,6 +55,8 @@ Configuration pdflocation = /path/to/storage/of/PDFs/ ; location of the firefox binary firefoxBinary = /Pfad/zur/firefox.exe + ; location of the geckodriver binary + geckodriver = /Pfad/zum/geckodriver Usage after initial setup ------------------------- @@ -62,3 +68,4 @@ In the specified location for download you will find the following structure: - ``YYYY-MM-DD_Abbreviation of committee or plenary session/`` (one directory for each meeting) - files inside the directory: ``Einladung.pdf`` (contains invitation), ``Mappe.pdf`` (contains all motions in one document), and ``Tagesordnung.pdf`` (agenda) +the diff --git a/setup.py b/setup.py index 55d0b58..031fc5e 100644 --- a/setup.py +++ b/setup.py @@ -30,7 +30,7 @@ setup( author="Jim Martens", author_email="github@2martens.de", url="https://git.2martens.de/2martens/allris-scraper", - version="0.3.7", + version="0.4.0", namespace_packages=["twomartens"], packages=find_packages('src', exclude=["*.tests", "*.tests.*", "tests.*", "tests"]), package_dir={'': 'src'},