def get_user_history_results(data):
user_history = {}
nodes = PyQuery(data)('tr')
def parse_row(index, node):
data = {}
row = PyQuery(node)
if index!=0:
data = {'title':row('td').eq(0).text(),
'city': row('td').eq(1).text(),
'date': row('td').eq(2).text(),
'place': row('td').eq(3).text(),
'time': row('td').eq(4).text(),
'results': row('td').eq(5)('a').attr("href")
}
user_history[index] = data
nodes.each(parse_row)
return user_history
row_header = PyQuery(row.find('td')[0]).text()
if not row_header:
# This is an intermediary header row to remind readers which column is which.
continue
target_cell_imgs = PyQuery(row.find('td')[column]).find('img[alt$=svg]')
if not target_cell_imgs:
continue
row_sign_filenames = []
target_cell_imgs.each(lambda: row_sign_filenames.append(
{
'type': 'sign filename',
'text': PyQuery(this).attr('alt').replace(' ', '_'),
}
))
filenames_to_remove = []
for filename in row_sign_filenames:
# Download the SVG(s).
try:
image_page = PyQuery('http://en.wikipedia.org/wiki/File:{}'.format(filename['text']))
svg_link = image_page.find('a.internal').filter(lambda: this.text_content().strip() == 'Original file')
svg_url = svg_link.attr('href')
if not svg_url:
print(
'Could not find URL for {table_header}: {row_header}: {filename}\n'.format(
table_header=table_header,
