def set_up_docx_inline(url):
from io import BytesIO
from requests import get as requestsget
response = requestsget(url)
img = BytesIO(response.content)
return img
def scrape_fr_google(self, symbol, correct_url):
print_debug_stmt('scrape_fr_google')
print_debug_stmt('correct_url')
print_debug_stmt(correct_url)
resp = requestsget(correct_url)
print_debug_stmt('resp.status_code')
print_debug_stmt(resp.status_code)
if str(resp.status_code) == '200':
parser = fromstring(resp.text)
raw_html = parser.cssselect('#ires > ol div.g:nth-child(1)')[0]
# dive must somehow relatable to finance (that his box is realy about the finance)
if 'Google Finance' in raw_html.text_content():
# semantic match #1 FOLLOW-UP (begin)
span1st = raw_html.cssselect('h3 span')[0]
print_debug_stmt('span1st')
print_debug_stmt(span1st)
print_debug_stmt('str(span1st.text_content())')
print_debug_stmt(str(span1st.text_content()))
company_name = span1st.text_content().lstrip('- ')
print_debug_stmt('company_name')
print_debug_stmt(company_name)
tbl1st = raw_html.cssselect('table')[0]
td1st = tbl1st.cssselect('td')[0]
b1st = tbl1st.cssselect('b')[0]
# at last, got the selector correct and price extracted
last_trade_price = b1st.text_content()
span2nd = tbl1st.cssselect('span')[1]
last_trade_time = span2nd.text_content()
year_atthemoment = date.today().strftime('%Y')
last_trade_time = last_trade_time + ' ' + str(year_atthemoment)
# this line most match, in position and in content (semantically) w
# the columns header stored in global constants (COL_NAMES) -- right
# data must go to the right column
temptupl = (symbol, company_name, 'google', last_trade_time,
last_trade_price)
# semantic match #1 FOLLOW-UP (end)
temprowlist = []
temprowlist.append(temptupl)
tempdf = DataFrame(temprowlist, columns=COL_NAMES)
return tempdf
else:
raise ScrapeFailedException()
else:
raise ScrapeFailedException()
def attachment_to_email(attachment_res):
from io import BytesIO
from email.mime.base import MIMEBase
from email.encoders import encode_base64
from requests import get as requestsget
temp_bytes = BytesIO(requestsget(attachment_res['DOWNLOAD_URL']).content)
p = MIMEBase('application', 'octet-stream')
p.set_payload(temp_bytes.read())
encode_base64(p)
filename = attachment_res['NAME']
p.add_header('Content-Disposition', 'attachment; filename= %s' % filename)
return p
def set_up_MIME_IMAGE(url, file_format):
from io import BytesIO
from requests import get as requestsget
from PIL import Image
from email.mime.image import MIMEImage
stream_bytes = BytesIO()
response = requestsget(url)
img = Image.open(BytesIO(response.content))
img.save(stream_bytes, file_format)
stream_bytes.seek(0)
img_obj = stream_bytes.read()
return MIMEImage(img_obj)
def validateExternal(email):
response = requestsget(apiurl.format(key=key, email=email))
if response.status_code != 200:
return None, "{}: Status invalido. Contacte al administrador".format(
response.status_code)
return response.json(), None