def crawl(crawler):
out = crawler.get_output(language='my')
crawl_udhr(crawler, out, filename='udhr_mya.txt')
crawl_bbc_news(crawler, out, urlprefix='/burmese/')
zawgyi_out = crawler.get_output(language='my-t-d0-zawgyi')
crawl_than_lwin_times(crawler, zawgyi_out)
def crawl(crawler):
out = crawler.get_output(language='id')
crawler.crawl_abc_net_au(out, program_id='indonesian')
crawler.crawl_voice_of_america(out, host='voaindonesia.com')
crawl_bbc_news(crawler, out, urlprefix='/indonesia/')
crawl_deutsche_welle(crawler, out, prefix='/id/')
crawl_udhr(crawler, out, filename='udhr_ind.txt')
crawl_bibleis(crawler, out, bible='INDASV')
crawl_bibleis(crawler, out, bible='INDWBT')
crawl_bibleis(crawler, out, bible='INDSHV')
def crawl(crawler):
out = crawler.get_output(language='cy')
crawl_udhr(crawler, out, filename='udhr_cym.txt')
crawl_bbc_news(crawler, out, urlprefix='/cymrufyw/')
def crawl(crawler):
out = crawler.get_output(language='ja')
crawl_udhr(crawler, out, filename='udhr_jpn.txt')
crawl_bbc_news(crawler, out, urlprefix='/japanese/')
def crawl(crawler):
out = crawler.get_output(language='si')
crawl_udhr(crawler, out, filename='udhr_sin.txt')
crawl_bbc_news(crawler, out, urlprefix='/sinhala/')
def crawl(crawler):
out = crawler.get_output(language='ky')
crawl_udhr(crawler, out, filename='udhr_kir.txt')
crawl_bbc_news(crawler, out, urlprefix='/kyrgyz/')
crawl_azattyk_org(crawler, out)
def crawl(crawler):
out = crawler.get_output(language='gd')
crawl_udhr(crawler, out, filename='udhr_gla.txt')
_crawl_dasg(crawler, out)
crawl_bbc_news(crawler, out, urlprefix='/naidheachdan/')
def crawl(crawler):
out = crawler.get_output(language='pcm')
crawl_udhr(crawler, out, filename='udhr_pcm.txt')
crawl_bbc_news(crawler, out, urlprefix='/pidgin/')
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='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='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):
out = crawler.get_output(language='my')
crawl_udhr(crawler, out, filename='udhr_mya.txt')
crawl_bbc_news(crawler, out, urlprefix='/burmese/')
def crawl(crawler):
out = crawler.get_output(language='ur')
crawl_udhr(crawler, out, filename='udhr_urd.txt')
crawl_bbc_news(crawler, out, urlprefix='/urdu/')
def crawl(crawler):
out = crawler.get_output(language='ta')
crawl_udhr(crawler, out, filename='udhr_tam.txt')
crawl_bbc_news(crawler, out, urlprefix='/tamil/')
def crawl(crawler):
out = crawler.get_output(language='rw')
crawl_udhr(crawler, out, filename='udhr_kin.txt')
crawl_bbc_news(crawler, out, urlprefix='/gahuza/')
def crawl_modern_standard_arabic(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='so')
crawl_udhr(crawler, out, filename='udhr_som.txt')
crawl_bbc_news(crawler, out, urlprefix='/somali/')