def crawl(crawler):
out = crawler.get_output(language='mi')
crawl_udhr(crawler, out, filename='udhr_mri.txt')
_scrape_maoritelevision(crawler, out)
_scrape_paiperatapu(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='sk')
crawl_udhr(crawler, out, filename='udhr_slk.txt')
_crawl_pravda_sk(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='ar')
crawl_udhr(crawler, out, filename='udhr_arb.txt')
crawl_deutsche_welle(crawler, out, prefix='/ar/')
crawl_sputnik_news(crawler, out, host='arabic.sputniknews.com')
crawl_bbc_news(crawler, out, urlprefix='/arabic/')
def crawl(crawler):
out = crawler.get_output(language='yo')
crawl_udhr(crawler, out, filename='udhr_yor.txt')
crawl_voice_of_nigeria(crawler, out, urlprefix='/yoruba/')
crawl_bibleis(crawler, out, bible='YORUBS')
def crawl(crawler):
out = crawler.get_output(language='fuv')
crawl_udhr(crawler, out, filename='udhr_fuv.txt')
crawl_voice_of_nigeria(crawler, out, urlprefix='/fulfulde/')
crawl_bibleis(crawler, out, bible='FUVTBL')
def crawl(crawler):
out = crawler.get_output(language='cs')
crawl_udhr(crawler, out, filename='udhr_ces.txt')
crawl_sputnik_news(crawler, out, host='cz.sputniknews.com')
def crawl(crawler):
out = crawler.get_output(language='es')
crawl_udhr(crawler, out, filename='udhr_spa.txt')
crawl_bbc_news(crawler, out, urlprefix='/mundo/')
crawl_deutsche_welle(crawler, out, prefix='/es/')
def crawl(crawler):
out = crawler.get_output(language='el')
crawl_udhr(crawler, out, filename='udhr_ell_monotonic.txt')
crawl_deutsche_welle(crawler, out, prefix='/el/')
def crawl(crawler):
out = crawler.get_output(language='it')
crawl_udhr(crawler, out, filename='udhr_ita.txt')
crawl_sputnik_news(crawler, out, host='it.sputniknews.com')
_crawl_iltirreno_gelocal_it(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='ig')
crawl_udhr(crawler, out, filename='udhr_ibo.txt')
crawl_voice_of_nigeria(crawler, out, urlprefix='/igbo/')
def crawl(crawler):
out = crawler.get_output(language='vi')
crawl_udhr(crawler, out, filename='udhr_vie.txt')
crawl_bbc_news(crawler, out, urlprefix='/vietnamese/')
crawler.crawl_voice_of_america(out, host='voatiengviet.com')
def crawl(crawler):
unicode_out = crawler.get_output(language='mnw')
crawl_udhr(crawler, unicode_out, filename='udhr_mnw.txt')
crawl_mon_news(crawler, unicode_out)
def crawl(crawler):
out = crawler.get_output(language='ku')
crawl_udhr(crawler, out, filename='udhr_kmr.txt')
crawl_sputnik_news(crawler, out, host='krd.sputniknews.com')
def crawl(crawler):
out = crawler.get_output(language='os')
crawl_udhr(crawler, out, filename='udhr_oss.txt')
_crawl_raestdzinad_ru(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='mt')
crawl_udhr(crawler, out, filename='udhr_mlt.txt')
crawl_newsbook_mt(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='bm')
crawl_udhr(crawler, out, filename='udhr_bam.txt')
crawler.crawl_voice_of_america(out, host='voabambara.com')
def crawl(crawler):
out = crawler.get_output(language='lt')
crawl_udhr(crawler, out, filename='udhr_lit.txt')
_crawl_kauno_diena_lt(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='sw')
crawl_udhr(crawler, out, filename='udhr_swh.txt')
crawl_bbc_news(crawler, out, urlprefix='/swahili/')
crawl_deutsche_welle(crawler, out, prefix='/sw/')
def crawl(crawler):
out = crawler.get_output(language='nan')
crawl_udhr(crawler, out, filename='udhr_nan.txt')
def crawl(crawler):
out = crawler.get_output(language='vec')
crawl_udhr(crawler, out, filename='udhr_vec.txt')
crawl_larenadomila_it(crawler)
crawl_quatrociacoe_it(crawler)
crawl_wikisource_trieste_vernacola(crawler)
def crawl(crawler):
out = crawler.get_output(language='chr')
crawl_udhr(crawler, out, filename='udhr_chr_uppercase.txt')
crawler.crawl_churchio(out, bible_id='chr-cherokee')
def crawl(crawler):
out = crawler.get_output(language='ru')
crawl_udhr(crawler, out, filename='udhr_rus.txt')
crawl_deutsche_welle(crawler, out, prefix='/ru/')
def crawl(crawler):
out = crawler.get_output(language='mk')
crawl_udhr(crawler, out, filename='udhr_mkd.txt')
crawl_deutsche_welle(crawler, out, prefix='/mk/')
def crawl(crawler):
out = crawler.get_output(language='pt-PT')
crawl_udhr(crawler, out, filename='udhr_por_PT.txt')
_crawl_observador_pt(crawler, out)
_crawl_visao_sapo_pt(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='fi')
crawl_udhr(crawler, out, filename='udhr_fin.txt')
crawler.crawl_sverigesradio(out, program_id=185)
def crawl(crawler):
out = crawler.get_output(language='dz')
crawl_udhr(crawler, out, filename='udhr_dzo.txt')
crawl_kuensel(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='ps')
crawl_udhr(crawler, out, filename='udhr_pbu.txt')
crawl_deutsche_welle(crawler, out, prefix='/ps/', need_percent_in_url=True)
def crawl(crawler):
out = crawler.get_output(language='yue')
crawl_udhr(crawler, out, filename='udhr_yue.txt')
crawler.crawl_voice_of_america(out, host='www.voacantonese.com')
crawl_radio_free_asia(crawler, out, edition='cantonese', start_year=1998)
crawl_bibleis(crawler, out, bible='YUHUNV')
def crawl(crawler):
out = crawler.get_output(language='bg')
crawl_udhr(crawler, out, filename='udhr_bul.txt')
crawl_deutsche_welle(crawler, out, prefix='/bg/')
# There's audio for one part of Matthew under BLGAMB that matches this text
crawl_bibleis(crawler, out, 'BULB40')
def crawl(crawler):
out = crawler.get_output(language='my')
crawl_udhr(crawler, out, filename='udhr_mya.txt')
crawl_bbc_news(crawler, out, urlprefix='/burmese/')
