def read_soup(page):
'''
Reads a web page and soupifies it
'''
# Read the page
url, html, cookie_jar = fetch_url( page )
# Parse the page
return bs4.BeautifulSoup( html )
def read_soup(page):
'''
Reads a web page and soupifies it
'''
# Read the page
html = fetch_url(page)[1]
# Parse the page
return bs4.BeautifulSoup(html)
def save_file(filename, url):
k = 1
while True:
try:
url, data_blob, cookies = fetch_url( url )
break
except urllib2.HTTPError:
logger.error('Could not read PDF: %s DOC: %s' % ( url, filename))
k += 1
if k == MAX_ATTEMPTS:
raise DREError('Couldn\'t get the PDF: %s' % url )
logger.debug('Sleeping 2 secs...')
time.sleep(2)
with open(filename, 'wb') as f:
f.write(data_blob)
f.close()
def read_bdp_file(self):
url, payload, cj = fetch_url( BDP_SOURCE_URL )
return csv.reader( StringIO.StringIO( payload ), delimiter=';')
def save_file(filename, url):
k = 1
data_blob=fetch_url(url)[1]
with open(filename, 'wb') as f:
f.write(data_blob)
f.close()