def translate_db(disease_db_en, language_code='vi'):
translated_disease_db = dict()
common.init_disease_db(translated_disease_db)
all_diseases = list(disease_db_en[common.ALL_DISEASES_VIEW].values())
for i in range(0, len(all_diseases)):
original_disease = all_diseases[i]
common.get_logger().info(''.join(['Translating the ', str(i),
'th/', str(len(all_diseases)), ' disease "',
original_disease.name, '"...']))
translated_disease = translate_a_disease(original_disease,
language_code)
translated_disease_db[common.ALL_DISEASES_VIEW][\
translated_disease.name] = translated_disease
return disease_db_translated
def scrape_all_disease_contents(disease_db):
is_still_need_to_scrape = True
while is_still_need_to_scrape:
is_still_need_to_scrape = scrape_all_disease_contents_once(disease_db)
if __name__ == "__main__":
common.setup_logger_warning()
common.get_logger().warning("Start scraping!")
# @todo: use INFO log level, disable logs from the 'request' package
#logging.getLogger("requests").propagate = False
#logging.getLogger("requests").setLevel(logging.WARNING)
start_time = time.clock()
disease_db = dict()
common.init_disease_db(disease_db)
scrape_all_disease_metadata(disease_db)
common.get_logger().warning(''.join(["No. of diseases to scrape: ",
str(len(disease_db[common.ALL_DISEASES_VIEW]))]))
scrape_all_disease_contents(disease_db)
end_time = time.clock()
common.get_logger().warning(''.join(["Total Scraping Time:",
str(end_time - start_time), "s"]))
common.dump_disease_db(disease_db, common.DISEASE_DB_FILE_EN)
common.get_logger().warning("Finished scraping!")