def test_it_saves_a_unicode_csv_to_the_database(): sheets = extract.validate(extract.extract('fixture/mps_unicode.csv')) extract.save(sheets) data = scraperwiki.sql.select('* from swdata') row = data[460] assert_equals(row['MP Name'], 'Michelle Gildernew') assert_equals(row['Party'], u'Sinn Féin')
def test_it_saves_to_the_database(): sheets = extract.validate(extract.extract('fixture/simple.xlsx')) extract.save(sheets) data = scraperwiki.sql.select('* from Sheet1') row = data[2] assert_equals(row['Year'], 2012) assert_equals(row['Awesomeness'], 8)
def test_it_can_extract_an_html_csv(): sheets = extract.validate(extract.extract('fixture/twitter-archive.csv')) assert_equals(len(sheets), 1) row = sheets['swdata'][3] assert_equals( row['source'], '<a href="http://www.tweetdeck.com" rel="nofollow">TweetDeck</a>')
def test_it_can_extract_a_unicode_csv(): sheets = extract.validate(extract.extract('fixture/mps_unicode.csv')) assert_equals(len(sheets), 1) sheet = sheets['swdata'] assert_equals(len(sheet), 653) row = sheet[460] assert_equals(row['MP Name'], 'Michelle Gildernew') assert_equals(row['Party'], u'Sinn Féin')
def test_it_can_extract_a_simple_csv_file(): sheets = extract.validate(extract.extract('fixture/simple.csv')) assert_equals(type(sheets), OrderedDict) assert_equals(len(sheets), 1) sheet = sheets['swdata'] assert_equals(len(sheet), 4) row = sheet[2] assert_equals(row['Year'], 2012) assert_equals(row['Awesomeness'], 8)
def test_it_can_extract_an_html_csv(): sheets = extract.validate(extract.extract('fixture/twitter-archive.csv')) assert_equals(len(sheets), 1) row = sheets['swdata'][3] assert_equals(row['source'], '<a href="http://www.tweetdeck.com" rel="nofollow">TweetDeck</a>')
def test_it_can_extract_a_latin1_csv(): sheets = extract.validate(extract.extract('fixture/ENH-CCG-spend-2013.csv')) assert_equals(len(sheets), 1) row = sheets['swdata'][1] assert_equals(row['Purchase invoice number'], 11223)