-
-
Save gajus/68f9da3b27a51a58db990ae67e9acdae to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import _ from 'lodash'; | |
import surgeon from 'surgeon'; | |
import { | |
extractMatch, | |
extractDate, | |
extractTime, | |
mapSelector, | |
request | |
} from '@applaudience/showtime-scraper-tools'; | |
export const source = { | |
country: 'fr', | |
name: 'mk2', | |
nid: 'mk2', | |
url: 'http://www.mk2.com/' | |
}; | |
export const scrapeVenues = async () => { | |
const document = await request('get', 'http://www.mk2.com/', 'html'); | |
const x = surgeon(document); | |
const venues = x({ | |
properties: { | |
name: '::text()', | |
nid: '::attribute(href)::match("/salles/mk2-(.+)")', | |
url: '::attribute(href)' | |
}, | |
selector: '#footer p:contains(Les salles MK2) + .item-list a[href^="/salles/"] {1,}' | |
}); | |
return venues.map((venue) => { | |
return { | |
guide: { | |
url: 'http://www.mk2.com/salles/mk2-' + venue.url | |
}, | |
result: { | |
name: venue.name, | |
nid: venue.nid, | |
url: 'http://www.mk2.com/salles/mk2-' + venue.url | |
} | |
}; | |
}); | |
}; | |
export const scrapeMovies = async (guide) => { | |
const document = await request('get', guide.url, 'html'); | |
const x = surgeon(document); | |
const movies = x({ | |
properties: { | |
name: '.fiche-film-title', | |
url: 'a[href^="/films/"]::attribute(href)' | |
}, | |
selector: '#seances .l-mk2-tables .l-session-table .fiche-film-info::has(.fiche-film-title) {0,}', | |
uniqueBy: 'url' | |
}); | |
return movies.map((movie) => { | |
return { | |
guide: { | |
showtimeUrl: guide.url, | |
movieUrl: movie.url | |
}, | |
result: { | |
name: movie.name | |
} | |
} | |
}); | |
}; | |
const scrapeLanguageAttributes = (version) => { | |
switch (version) { | |
case 'VO': | |
return { | |
audio: { | |
language: 'original' | |
} | |
}; | |
case 'VF': | |
return { | |
audio: { | |
language: 'fr' | |
} | |
}; | |
default: | |
return {}; | |
} | |
}; | |
export const scrapeShowtimes = async (guide) => { | |
const document = await request('get', guide.showtimeUrl, 'html'); | |
const x = surgeon(document, { | |
formatters: { | |
extractDate, | |
extractTime | |
}, | |
parameters: { | |
movieUrl: guide.movieUrl | |
} | |
}); | |
const dates = x({ | |
has: 'a[href="${movieUrl}"]', | |
properties: { | |
date: '.table-header .l-schedule-days::attribute(id)::extractDate(YYYYMMDD)', | |
events: { | |
properties: { | |
time: '::text()::extractTime(HH[h]mm)', | |
url: '::attribute(href)', | |
version: '::text()::match("(VOST|VO|VF)")' | |
}, | |
selector: '.item-list a[href^="/reservation"]' | |
} | |
}, | |
selector: '#seances .l-mk2-tables .l-session-table' | |
}); | |
return _.flatten(dates.map((date) => { | |
return date.events.map((event) => { | |
return { | |
time: date.date + ' ' + event.time, | |
url: 'http://www.mk2.com' + event.url, | |
...scrapeLanguageAttributes(event.version) | |
}; | |
}); | |
})); | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment