From d5592be0ccdae16e219a1054a2de4776483ed50f Mon Sep 17 00:00:00 2001 From: theo1 Date: Sat, 30 May 2020 16:46:19 +0200 Subject: [PATCH] First commit of a python parser --- .gitignore | 2 + README.md | 16 +++ index.html | 27 +++++ parser.py | 37 ++++++ requirements.txt | 3 + waoff-calendar.ics | 273 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 358 insertions(+) create mode 100644 .gitignore create mode 100644 README.md create mode 100644 index.html create mode 100644 parser.py create mode 100644 requirements.txt create mode 100644 waoff-calendar.ics diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..e5fc6d2 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +# ignore local venv +waoffvenv/ diff --git a/README.md b/README.md new file mode 100644 index 0000000..7af54db --- /dev/null +++ b/README.md @@ -0,0 +1,16 @@ +# We Are One : A Global Film Festival parser + +## What does it do ? + +_This short scripts parses an HTML page from the official WAOFF schedule webpage (http://www.weareoneglobalfestival.com/schedule) and parses it to create an iCalendar-formatted file, that you can directly import in your calendar app._ + +**Note** : the webpage is JS-based, which means you can't just `wget` it to extract the HTML page. You'll need to browse to the schedule page you want, go to the console, and type : +```js +console.log(document.getElementsByTagName('html')[0].innerHTML); +``` +, then copy-paste it to and html file locally, that you'll browse with the script. + +## TODO +- [ ] fix the start time problem in the ICS file +- [ ] handle timezone (the time on the website is EST) +- [ ] interactive choice of HTML page and name of calendar diff --git a/index.html b/index.html new file mode 100644 index 0000000..5f0fc7a --- /dev/null +++ b/index.html @@ -0,0 +1,27 @@ +<--- Sample HTML page from http://www.weareoneglobalfestival.com/schedule ---> + +Festival Schedule | We Are One: A Global Film Festival
COMING TO YOUTUBE MAY 29 -JUNE 7, 2020
We Are One Festival White logo
FILTER EVENTS
BROWSESCHEDULEFAQ
TYPE OF FILM
GENRE


MayJune

29303101020304050607


360 VR
Alteration
Starts at 07:00 AM EST on May 29
Program
Annecy Shorts for Families
Starts at 07:00 AM EST on May 29
Short Film
Bilby
Starts at 07:00 AM EST on May 29
Short Film
Bird Karma
Starts at 07:00 AM EST on May 29
360 VR
Bloodless
Starts at 07:00 AM EST on May 29
360 VR
Crow: The Legend
Starts at 07:00 AM EST on May 29
360 VR
Daughters of Chibok
Starts at 07:00 AM EST on May 29
360 VR
Extravaganza
Starts at 07:00 AM EST on May 29
360 VR
Ghost Fleet VR
Starts at 07:00 AM EST on May 29
360 VR
Isle of the Dead
Starts at 07:00 AM EST on May 29
360 VR
Ivory Burn
Starts at 07:00 AM EST on May 29
Web Series
Jaws — Assembling a Top-Tier Team (feat. TierZoo)
Starts at 07:00 AM EST on May 29
Short Film
Marooned
Starts at 07:00 AM EST on May 29
360 VR
Minotaur
Starts at 07:00 AM EST on May 29
360 VR
My Africa
Starts at 07:00 AM EST on May 29
360 VR
On/Off
Starts at 07:00 AM EST on May 29
360 VR
Passenger
Starts at 07:00 AM EST on May 29
Web Series
Sébastien Tellier on Paris’ rooftop | A Take Away Show
Starts at 07:00 AM EST on May 29
360 VR
Step To The Line
Starts at 07:00 AM EST on May 29
Web Series
The Stories That Prepared Us
Starts at 07:00 AM EST on May 29
360 VR
Traveling While Black
Starts at 07:00 AM EST on May 29
360 VR
The Waiting Room
Starts at 07:00 AM EST on May 29
Short Film
And Then The Bear
Starts at 08:00 AM EST on May 29
Short Film
The Distance Between Us And The Sky
Starts at 08:00 AM EST on May 29
Program
The Short Film Selection in Competition at the 72nd Festival de Cannes: Program 2
Starts at 08:00 AM EST on May 29
Short Film
White Echo
Starts at 08:00 AM EST on May 29
Panel
Cinema Cafe with Jackie Chan
Starts at 09:30 AM EST on May 29
Television
Losing Alice
Starts at 10:45 AM EST on May 29
Feature Film
Electric Swan
Starts at 01:00 PM EST on May 29
Feature Film
Crazy World
Starts at 02:00 PM EST on May 29
Feature Film
Rudeboy: The Story of Trojan Records
Starts at 03:30 PM EST on May 29
Short Film
Cru - Raw
Starts at 05:15 PM EST on May 29
Short Film
Egg
Starts at 05:15 PM EST on May 29
Short Film
The Light Side
Starts at 05:15 PM EST on May 29
Short Film
Motorcycle Drive By
Starts at 05:15 PM EST on May 29
Short Film
No More Wings
Starts at 05:15 PM EST on May 29
Short Film
TOTO
Starts at 05:15 PM EST on May 29
Program
Tribeca 2020 Shorts Program
Starts at 05:15 PM EST on May 29
Short Film
When I Write It
Starts at 05:15 PM EST on May 29
Short Film
Circus Person
Starts at 07:05 PM EST on May 29
We Are One

An unprecedented 10-day digital film festival exclusively on YouTube curated by the following film festivals

Annecy International Animation Film FestivalBerlin International Film FestivalBFI London Film FestivalCannes Film FestivalGuadalajara International Film FestivalJerusalem Film FestivalKarlovy Vary International Film FestivalLocarno Film FestivalInternational Film Festival & Awards Macao (IFFAM)Marrakech International Film FestivalMumbai Film FestivalNew York Film FestivalRotterdam International Film FestivalSan Sebastian International Film FestivalSarajevo Film FestivalSundance Film FestivalSydney Film FestivalToronto International Film FestivalTokyo International Film FestivalTribeca Film FestivalVenice Film Festival

© 2020 We Are One: Global Film Festival

+debugger eval code:1:9 + diff --git a/parser.py b/parser.py new file mode 100644 index 0000000..2c02978 --- /dev/null +++ b/parser.py @@ -0,0 +1,37 @@ +from datetime import datetime +from bs4 import BeautifulSoup +from icalendar import Calendar, Event +import pytz + +file = open('index.html', 'r') +page = file.read() +cal = Calendar() + +def handleFilm(p) : + title = p.find('a', {'class':'Film_title'}) + print(title.string) + runtime = p.find('div', {'class':'Film_runtime'}) + time = p.find('span', {'class': 'start_time'}) + # Starts at 05:15 PM EST on May 29 + time_formatted = datetime.strptime(time.string, "Starts at %I:%M %p EST on %B %d") + time_formatted = time_formatted.replace(year=2020) + tz_time = pytz.timezone('US/Eastern') + tz_time.localize(time_formatted) + print(time_formatted) + print("Europe : " + str(tz_time)) + summary = p.find('div', {'class' : 'Film_summary'}) + + event = Event() + event.add('description', summary.string) + event.add('summary', title.string) + event.add('dtstart', time_formatted) + + cal.add_component(event) + +soup = BeautifulSoup(page) +for p in soup.find_all('div', {'class': 'Film'}): + handleFilm(p) + +f = open("waoff-calendar.ics", 'wb') +f.write(cal.to_ical()) +f.close() diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..3df2ba3 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +beautifulsoup4 +icalendar +pytz diff --git a/waoff-calendar.ics b/waoff-calendar.ics new file mode 100644 index 0000000..a587f25 --- /dev/null +++ b/waoff-calendar.ics @@ -0,0 +1,273 @@ +BEGIN:VCALENDAR +BEGIN:VEVENT +SUMMARY:Alteration +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:When Alexandro volunteered for a dream experiment\, he never i + magined that he would be subjected to a form of Artificial Intelligence wh + o aims to digitize his subconscious. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Annecy Shorts for Families +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:None +END:VEVENT +BEGIN:VEVENT +SUMMARY:Bilby +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This sweet short from DreamWorks Animation Studios finds a lon + esome bilby tangled up with a helpless baby bird in the deadly desert of A + ustralia. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Bird Karma +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:A crafty\, long-legged bird chases a mesmerizing fish through + a foggy pond in this sprightly short\, produced by DreamWorks Animation St + udios. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Bloodless +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:Portraying the final moments of a sex worker murdered by a US + soldier in South Korea\, this piece brings historical atrocities to light + through a concrete personal experience. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Crow: The Legend +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:The carefree animals imagine spring is endless. But when the v + ery first winter arrives\, can Crow (John Legend) make the ultimate sacrif + ice to save his friends?\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Daughters of Chibok +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This VR experience deals with the aftermath of the kidnapping + of 276 schoolgirls in 2014 in Nigeria\, and explores topical global issues + of gender rights and the right to education.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Extravaganza +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:A busy executive (Paul Scheer) tests a VR headset that promise + s to be the future of entertainment...but is actually anything but forward + thinking. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Ghost Fleet VR +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This harrowing look at slavery in the Thai fishing industry is + told through the experience of one man's harrowing ordeal to escape a pri + son of water after 10 years at sea.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Isle of the Dead +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:A timeless voyage from an everyday apartment toward our final + destination\, guided by Charon\, ferryman of the Underworld. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Ivory Burn +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This film bears witness to the burning of over 100 tons of ele + phant tusks and rhinoceros horn: a symbolic and visceral clarion call to t + he poaching and illegal trade syndicates. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Jaws — Assembling a Top-Tier Team (feat. TierZoo) +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This video essay by YouTube creators of Lessons From The Scree + nplay analyzes the classic blockbuster Jaws to examine how a screenwriter + can craft a dynamic team of characters. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Marooned +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:In this stylized DreamWorks Animation Studios short set in the + not-too-distant future\, a cantankerous and selfish robot is put to the t + est while stranded on an abandoned lunar outpost.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Minotaur +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:A mythical passage through the archetypal hero’s journey. Th + rough abstractions\, we experience their corresponding emotional states: c + alm\, love\, joy\, surprise\, fear\, anger/hate\, and death/rebirth\, lead + ing again to calm. +END:VEVENT +BEGIN:VEVENT +SUMMARY:My Africa +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This mixed-reality experience transports viewers to an elephan + t sanctuary in Kenya\, where a community is reknitting the bonds that have + long enabled people and wildlife to coexist.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:On/Off +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:Behind the closed doors of an intensive care unit\, ON/OFF loo + ks at how difficult it is for healthcare professionals to confront and “ + manage” death on a daily basis. \n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Passenger +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:This abstracted and dreamlike experience places you in the bac + kseat of a taxi\, and recreates the geographic and visual dislocation of f + inding a new home in a foreign land.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Sébastien Tellier on Paris’ rooftop | A Take Away Show +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:French artist Sébastien Tellier serenades Paris from one of i + ts highest point of view: the roof of Le Théâtre du Châtelet\, in the h + eart of the city +END:VEVENT +BEGIN:VEVENT +SUMMARY:Step To The Line +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:Shot entirely in a maximum security prison\, this piece shows + how release from incarceration can be just as jarring as intake and how pa + rallel lives diverge when someone serves time.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:The Stories That Prepared Us +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:A telling of the story of Coronavirus through moments in criti + cally-acclaimed film and television. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Traveling While Black +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:Confronting the way we understand and talk about race in Ameri + ca\, Traveling While Black immerses the viewer in the long history of rest + ricted movement for Black Americans. \n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:The Waiting Room +DTSTART;VALUE=DATE-TIME:20200529T070000 +DESCRIPTION:An unflinching record of Victoria Mapplebeck’s journey from + breast cancer diagnosis to recovery\, The Waiting Room considers what we c + an or can’t control when our bodies fail us. \n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:And Then The Bear +DTSTART;VALUE=DATE-TIME:20200529T080000 +DESCRIPTION:Houses will burn. Men and women will tremble. But the children + will come together and howl as they dance on the ashes like wild bears in + this vivid animation. +END:VEVENT +BEGIN:VEVENT +SUMMARY:The Distance Between Us And The Sky +DTSTART;VALUE=DATE-TIME:20200529T080000 +DESCRIPTION:In this Short Film Palme d’Or winner\, two strangers (Ioko I + oannis Kotidis\, Nikos Zeginogolu) meet one night at a gas station. One is + there to refuel\; the other is stranded. +END:VEVENT +BEGIN:VEVENT +SUMMARY:The Short Film Selection in Competition at the 72nd Festival de Ca + nnes: Program 2 +DTSTART;VALUE=DATE-TIME:20200529T080000 +DESCRIPTION:None +END:VEVENT +BEGIN:VEVENT +SUMMARY:White Echo +DTSTART;VALUE=DATE-TIME:20200529T080000 +DESCRIPTION:Chloë Sevigny’s ethereal séance-story sees a young woman\, + Carla (Kate Lyn Sheil)\, explore and wield her inner power while on vacat + ion with friends. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Cinema Cafe with Jackie Chan +DTSTART;VALUE=DATE-TIME:20200529T093000 +DESCRIPTION:Recorded live from the Sundance Film Festival\, each Cinema Ca + fé invigorates the culture of conversation. Our informal chats round up s + pecial guests for thought-provoking discussions between Festival filmmaker + s and journalists. Cinema Cafe with Jac... +END:VEVENT +BEGIN:VEVENT +SUMMARY:Losing Alice +DTSTART;VALUE=DATE-TIME:20200529T104500 +DESCRIPTION:Fascination spirals into Faustian bargain after an ambitious f + emale film director meets—and obsesses over—a younger femme-fatale scr + eenwriter. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Electric Swan +DTSTART;VALUE=DATE-TIME:20200529T130000 +DESCRIPTION:An apartment building in Buenos Aires begins to tremble and pr + ovokes an otherworldly nausea throughout the city in this magical realist + skewering of its class divisions.\n\n +END:VEVENT +BEGIN:VEVENT +SUMMARY:Crazy World +DTSTART;VALUE=DATE-TIME:20200529T140000 +DESCRIPTION:Pint-sized kung fu masters face off with the evil Tiger Mafia + in this action flick from Uganda's no-budget\, gonzo super-studio\, Wakali + wood. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Rudeboy: The Story of Trojan Records +DTSTART;VALUE=DATE-TIME:20200529T153000 +DESCRIPTION:Featuring Jamaican reggae and ska legends like Lee “Scratch + ” Perry and Marcia Griffiths\, Rudeboy chronicles a multicultural revolu + tion on the dancefloors of late ’60s and early ’70s Britain. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Cru - Raw +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:A young chef (Jeanne Werne) must learn that in this kitchen\, + a lot of blood\, sweat\, and tears go into making every dish. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Egg +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:An action-packed romance and Americana western adventure about + an egg's epic Hollywood journey from farm to table. +END:VEVENT +BEGIN:VEVENT +SUMMARY:The Light Side +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:An aging Sith Lord must come to grips with his past and discov + er why humility may be the greatest force in the galaxy. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Motorcycle Drive By +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:Third Eye Blind cannot finish their new album in time for a ma + ssive tour. Their fans still show\, breaking attendance records\, and high + lighting the importance of the band's deep cuts. +END:VEVENT +BEGIN:VEVENT +SUMMARY:No More Wings +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:At a divergent point in their lives\, two lifelong friends (Iv + anno Jeremiah\, Parys Jordon) meet at their favorite South London fried ch + icken shop. +END:VEVENT +BEGIN:VEVENT +SUMMARY:TOTO +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:Rosa Forlano\, a 90 year old Nonna\, falls in love with a robo + t while teaching it how to make spaghetti. Unfortunately\, her family reci + pe is erased by a software update. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Tribeca 2020 Shorts Program +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:None +END:VEVENT +BEGIN:VEVENT +SUMMARY:When I Write It +DTSTART;VALUE=DATE-TIME:20200529T171500 +DESCRIPTION:Two Oakland teens (Leila Mottley\, Ajai Kasim) explore what it + means to be young\, Black and committed to making art in their rapidly ch + anging city. +END:VEVENT +BEGIN:VEVENT +SUMMARY:Circus Person +DTSTART;VALUE=DATE-TIME:20200529T190500 +DESCRIPTION:Left by her fiancé for another woman\, a grieving painter (Br + itt Lower) joins a one-ring circus to reclaim her forgotten wildness. +END:VEVENT +END:VCALENDAR