A CLI to interact with the QCon London 2022 website

qcon-london-2022.py

#!/usr/bin/python3
import cmd, re, sys, traceback
from dataclasses import dataclass
from typing import List

import requests
from bs4 import BeautifulSoup

# This is part of Suhail's talk on the Developer Enablement
# track at QCon London 2022

class QConShell(cmd.Cmd):
    prompt = '\nQCon London 🇬🇧  2022 > '

    def __init__(self):
        super(QConShell, self).__init__()
        self.postcmd(None, None)

    def postcmd(self, stop, line):
        if self.lastcmd == "exit":
            return True

    def do_schedule(self, args):
        req = requests.get("https://qconlondon.com/schedule/london2022/apr/tabular")
        for item in parse_schedule(req.content):
            print(f"{item.date_time} | {item.talk_title} - {item.author} ({item.room})")

    def do_tracks(self, args):
        req = requests.get("https://qconlondon.com/#program")
        for item in parse_tracks(req.content):
            print(f"{item.day} | {item.track_title} - {item.host} ({item.bio})")

    def do_speakers(self, args):
        req = requests.get("https://qconlondon.com/speakers/london2022/apr")
        for item in sorted(parse_speakers(req.content), key=lambda x: x.name):
            print(f"{item.name} ({item.bio})")

    def do_exit(self, _):
        raise KeyboardInterrupt()



@dataclass
class ScheduleItem:
    talk_title: str
    author: str
    date_time: str
    room: str

# I hereby apologise to all the Pythonistas and BeautifulSoup gurus
# for my sloppy parsing code, it got the job done for the demo :)

def parse_schedule(contents):
    soup = BeautifulSoup(contents, features="html.parser")
    output = []
    for row in soup.findAll('tr', class_='presentations-row'):
        for item in row.findAll('td', class_='presentation'):
            talk_title = clean_string(item.findAll('a', class_='presentation-title')[0].string)
            author = clean_string(item.findAll('div', class_='session-speakers')[0].getText())
            date_time = clean_string(item['data-start'])
            room = clean_string(item.findAll('span', class_='location')[0].string)
            output.append(ScheduleItem(talk_title, author, date_time, room))
    return output


@dataclass
class TrackItem:
    track_title: str
    host: str
    bio: str
    day: str    


def parse_tracks(contents):
    soup = BeautifulSoup(contents, features="html.parser")
    output = []
    for item in soup.findAll('div', class_='border-l-4'):
        title = clean_string(item.findAll('a', class_='text-black')[0].string)
        host = clean_string(item.findAll('a', class_='text-black')[1].findAll('span')[0].string)
        bio = clean_string(item.findAll('a', class_='text-black')[1].findAll('span')[1].string)
        date = clean_string(item.findAll('p', class_='track-date')[0].string)
        output.append(TrackItem(title, host, bio, date))
    return output


@dataclass
class SpeakerItem:
    name: str
    bio: str


def parse_speakers(contents):
    soup = BeautifulSoup(contents, features="html.parser")
    output = []
    for item in soup.findAll('section', class_='max-w-screen-xl')[0].findAll('div', class_='xl:p-6'):
        name = clean_string(item.findAll('h4')[0].string)
        bio = clean_string(item.findAll('p')[0].string)
        output.append(SpeakerItem(name, bio))
    return output


def clean_string(input):
    out = input.strip()
    return re.sub(r"\s+", " ", out)


if __name__ == '__main__':
    print(f"Welcome to the Developer Enablement Track at QCon London 2022")
    shell = QConShell()
    while True:
        try:
            shell.cmdloop()
        except KeyboardInterrupt:
            sys.exit()
        except:
            traceback.print_exc()