def test__articles_dump_to_file(self):
titles = ['Ross_Ice_Shelf', 'Southern_Cross_Expedition', 'Ice_shelf']
webtools.articles_dump_to_file(titles, 'test.xml.tmp')
root = parse_tools.parse_xml('test.xml.tmp')
pages = root.findall(parse_tools.PAGE_TAG)
self.assertEqual(len(pages), len(titles))
def make_dump(wiki_dump, articles_titles, compress=False):
""" Download specified articles from Wikipedia site,
merges them into one file, compresses it as Wikipedia dump file
@param articles_titles: article's canonic name on Wikipedia web page
@param wiki_dump: output filename (if not specified default is used)
"""
_log.debug("-"*80)
_log.info('Executing makedump process on articles: {}'.format(articles_titles))
_log.info('Dump path: {}'.format(wiki_dump))
web_tools.articles_dump_to_file(articles_titles, wiki_dump, compress)
def make_dump(wiki_dump, articles_titles, compress=False):
""" Download specified articles from Wikipedia site,
merges them into one file, compresses it as Wikipedia dump file
@param articles_titles: article's canonic name on Wikipedia web page
@param wiki_dump: output filename (if not specified default is used)
"""
_log.debug("-" * 80)
_log.info(
'Executing makedump process on articles: {}'.format(articles_titles))
_log.info('Dump path: {}'.format(wiki_dump))
web_tools.articles_dump_to_file(articles_titles, wiki_dump, compress)
