def search(query_string=None, cmd=None, search_engine='google',
max_download=5):
engine = get_engine(search_engine)
search_req = engine.get_search_request(query_string)
search_result = get(search_req)
if isinstance(search_result, DownloadError):
raise SearchError('Failed search on {} ({})'.format(
search_engine, search_result.status_code))
urls = engine.get_hits(search_result)
docs = iter_get([Request(u.url) for u in urls[:max_download]])
return extract_commands(docs, base_commands=cmd)
def test_extract_commands(self):
cmds = extract_commands(iter_html_docs(TEST_DATA_DIR))
self.assertEqual(set(cmds.commands.keys()), MERGED_COMMANDS)
cmds = extract_commands(iter_html_docs(TEST_DATA_DIR), 'xargs')
self.assertEqual(set(cmds.commands.keys()), set([
'find /tmp -name "*.tmp" | xargs rm',
u'find ./music -name "*.mp3" -print0 | xargs -0 ls',
'find . -name "*.sh" | xargs grep "ksh"',
'find /tmp -name "*.tmp" -print0 | xargs -0 rm',
'find . -name "*.sh" -print0 | xargs -0 -I {} mv {} ~/back.scripts',
u'find ./work -print | xargs grep "profit"']))
cmds = extract_commands(
get_html_doc(TEST_DATA_DIR, 'stackoverflow.com'), 'xargs')
self.assertEqual(cmds.commands, {})
doc = HtmlDocument('http://stackoverflow.com', b'')
doc.body = None
cmds = extract_commands(doc)
self.assertEqual(cmds.nr_docs, 0)
def search(query_string=None,
cmd=None,
search_engine='google',
max_download=5):
engine = get_engine(search_engine)
search_req = engine.get_search_request(query_string)
search_result = get(search_req)
if isinstance(search_result, DownloadError):
raise SearchError('Failed search on {} ({})'.format(
search_engine, search_result.status_code))
urls = engine.get_hits(search_result)
docs = iter_get([Request(u.url) for u in urls[:max_download]])
return extract_commands(docs, base_commands=cmd)
