def as_image(source, output):
key = self.credentials['credentials']['grabzit_key']
secret = self.credentials['credentials']['grabzit_secret']
grabzIt = GrabzItClient.GrabzItClient(key, secret)
options = GrabzItImageOptions.GrabzItImageOptions()
options.browserHeight = -1
options.width = -1
options.height = -1
options.format = 'png'
options.quality = 100
grabzIt.FileToImage(source, options)
grabzIt.SaveTo(output) # (!) synchonous call to Grabzit API
def convert_url_img(url):
filename1 = datetime.now().strftime("%Y%m%d-%H%M%S")
path = 'tmp\img\{}.png'.format(filename1)
try:
grabzIt = GrabzItClient.GrabzItClient(
"YmI5YzRiY2U1NzI3NDNkMTk5OGJjNDRkNjNkNmUxNGE=",
"RT8/Pz8/egY/Pz8/Vz8/OD8/Cz8RRj8/Pz8/PyEOMz8=")
options = GrabzItImageOptions.GrabzItImageOptions()
options.format = "png"
options.browserHeight = -1
options.height = -1
options.width = -1
grabzIt.URLToImage(url, options)
grabzIt.SaveTo(path)
except Error as why:
print('grabzIt Error: {}\n'.format(why))
raise
return path
def convert_url_pdf(url):
filename1 = datetime.now().strftime("%Y%m%d-%H%M%S")
path = "tmp\pdf\{}.pdf".format(filename1)
try:
grabzIt = GrabzItClient.GrabzItClient(
"YmI5YzRiY2U1NzI3NDNkMTk5OGJjNDRkNjNkNmUxNGE=",
"RT8/Pz8/egY/Pz8/Vz8/OD8/Cz8RRj8/Pz8/PyEOMz8=")
options = GrabzItPDFOptions.GrabzItPDFOptions()
grabzIt.URLToPDF(url, options)
grabzIt.SaveTo(path)
grabzIt.SaveTo(path)
except pdfcrowd.Error as why:
# report the error
sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
# rethrow or handle the exception
raise
return path
def get_problem_by_id(self,
subject, id,
img=None, path_to_img=None, path_to_tmp_html=''):
"""
Получение информации о задаче по ее идентификатору
:param subject: Наименование предмета
:type subject: str
:param id: Идентификатор задачи
:type subject: str
:param img: Принимает одно из двух значений: pyppeteer или grabzit;
В результате будет использована одна из библиотек для генерации изображения с задачей.
Если не передавать этот аргумент, изображение генерироваться не будет
:type img: str
:param path_to_img: Путь до изображения, куда сохранить сохранить задание.
:type path_to_img: str
:param path_to_html: Можно указать директорию, куда будут сохраняться временные html-файлы заданий при использовании pyppeteer
:type path_to_html: str
:param grabzit_auth: При использовании GrabzIT укажите данные для аутентификации: {"AppKey":"...", "AppSecret":"..."}
:type grabzit_auth: dict
"""
doujin_page = requests.get(
f'{self._SUBJECT_BASE_URL[subject]}/problem?id={id}')
soup = BeautifulSoup(doujin_page.content, 'html.parser')
probBlock = soup.find('div', {'class': 'prob_maindiv'})
if probBlock is None:
return None
for i in probBlock.find_all('img'):
if not 'sdamgia.ru' in i['src']:
i['src'] = self._SUBJECT_BASE_URL[subject] + i['src']
URL = f'{self._SUBJECT_BASE_URL[subject]}/problem?id={id}'
TOPIC_ID = ' '.join(probBlock.find(
'span', {'class': 'prob_nums'}).text.split()[1:][:-2])
ID = id
CONDITION, SOLUTION, ANSWER, ANALOGS = {}, {}, '', []
try:
CONDITION = {'text': probBlock.find_all('div', {'class': 'pbody'})[0].text,
'images': [i['src'] for i in probBlock.find_all('div', {'class': 'pbody'})[0].find_all('img')]
}
except IndexError:
pass
try:
SOLUTION = {'text': probBlock.find_all('div', {'class': 'pbody'})[1].text,
'images': [i['src'] for i in probBlock.find_all('div', {'class': 'pbody'})[1].find_all('img')]
}
except IndexError:
pass
except AttributeError:
pass
try:
ANSWER = probBlock.find(
'div', {'class': 'answer'}).text.replace('Ответ: ', '')
except IndexError:
pass
except AttributeError:
pass
try:
ANALOGS = [i.text for i in probBlock.find(
'div', {'class': 'minor'}).find_all('a')]
if 'Все' in ANALOGS:
ANALOGS.remove('Все')
except IndexError:
pass
except AttributeError:
pass
if not img is None:
for i in probBlock.find_all('div', {'class': 'minor'}): # delete the information parts of problem
i.decompose()
probBlock.find_all('div')[-1].decompose()
# Pyppeteer
if img == 'pyppeteer':
import asyncio
from pyppeteer import launch
open(f'{path_to_tmp_html}{id}.html', 'w', encoding='utf-8').write(str(probBlock))
async def main():
browser = await launch()
page = await browser.newPage()
await page.goto('file:' + path.abspath(f'{path_to_tmp_html}{id}.html'))
await page.screenshot({'path': path_to_img, 'fullPage': 'true'})
await browser.close()
asyncio.get_event_loop().run_until_complete(main())
remove(path.abspath(f'{path_to_tmp_html}{id}.html'))
# Grabz.it
elif img == 'grabzit':
from GrabzIt import GrabzItClient, GrabzItImageOptions
grabzIt = GrabzItClient.GrabzItClient(self.grabzit_auth['AppKey'], self.grabzit_auth['AppSecret'])
options = GrabzItImageOptions.GrabzItImageOptions()
options.browserWidth = 800
options.browserHeight = -1
grabzIt.HTMLToImage(str(probBlock), options=options)
grabzIt.SaveTo(path_to_img)
# HTML2Image
elif img == 'html2img':
from html2image import Html2Image
if self.html2img_chrome_path == 'chrome': hti = Html2Image()
else: hti = Html2Image(chrome_path=self.html2img_chrome_path, custom_flags=['--no-sandbox'])
hti.screenshot(html_str=str(probBlock), save_as=path_to_img)
return {'id': ID, 'topic': TOPIC_ID, 'condition': CONDITION, 'solution': SOLUTION, 'answer': ANSWER,
'analogs': ANALOGS, 'url': URL}
#Number of Employees
e = soup.find_all(
'a',
class_=
'component--field-formatter field-type-enum link-accent ng-star-inserted'
)
l = str(e[0]).strip().split('>')
ne.append(l[1][:-3])
#Founders
fn = soup.find_all('a', class_='link-accent ng-star-inserted')
founder.append(Founder(fn))
#Links
grabzIt = GrabzItClient.GrabzItClient(
"ZDg2NmM1MDVjYTI3NGFkM2FmOTZjMzc4MGE5YTI3MzU=",
"bj9UTR8VED8/PxsFUT81PyB4Pz8/d29tSz8UVj8ccU0=")
for link in soup.find_all('a', href=True):
lk = link.get('href')
txt2 = str(lk)
#Website
wa = web()
wo.append(wa[0])
wo1.append(wa[1])
#Facebook
fa = FLT('facebook')
fbo.append(fa[0])
fbo1.append(fa[1])
URL = "https://www.kiva.org/lend?queryString=" + str(n) + "&status=all"
chromedriver = "/Users/arjunsoin/Desktop/chromedriver"
browser = webdriver.Chrome(chromedriver)
browser.get(URL)
html = browser.page_source
soup = BeautifulSoup(html,"lxml")
s = 91929 ## placeholder html that is rewritten on each iteration
fl = '%s.html' % s ## replace with url
di = os.getcwd()
final = di + "/" + fl
with open(final, "w") as file:
file.write(str(soup))
options = GrabzItImageOptions.GrabzItImageOptions()
options.width = -1
options.height = -1
options.browserHeight = -1
grabzIt = GrabzItClient.GrabzItClient("NmViOGJhNjk0YjRiNGU4OTlhNDFiNjk2MDliOTY2MDM=", "KzA/ID8LVz8/P3F+X2M/Pz8/RT9VPz8mPz8/Pz8/Pyc=")
grabzIt.FileToImage(final, options)
filepath = di + '/result.jpg'
grabzIt.SaveTo(filepath)
im = Image.open(filepath)
outfile = str(n) + "_tile.jpg"
region=im.crop((40, 350, 330, 651))
region.save(outfile, "JPEG")
except ImportError:
from ConfigParser import SafeConfigParser
message = ""
if os.environ['REQUEST_METHOD'] == 'POST':
form = cgi.FieldStorage()
if form.getvalue("delete") == "1":
r = glob.glob('results/*')
for i in r:
os.remove(i)
else:
try:
parser = SafeConfigParser()
parser.read("config.ini")
grabzIt = GrabzItClient.GrabzItClient(
parser.get("GrabzIt", "applicationKey"),
parser.get("GrabzIt", "applicationSecret"))
isHtml = form.getvalue("convert") == "html"
if form.getvalue("format") == "pdf":
if (isHtml == True):
grabzIt.HTMLToPDF(form.getvalue("html"))
else:
grabzIt.URLToPDF(form.getvalue("url"))
elif form.getvalue("format") == "gif":
grabzIt.URLToAnimation(form.getvalue("url"))
else:
if (isHtml == True):
grabzIt.HTMLToImage(form.getvalue("html"))
else:
grabzIt.URLToImage(form.getvalue("url"))
form = cgi.FieldStorage()
message = form.getvalue("message")
customId = form.getvalue("customid")
id = form.getvalue("id")
filename = form.getvalue("filename")
format = form.getvalue("format")
targeterror = form.getvalue("targeterror")
parser = SafeConfigParser()
parser.read('config.ini')
#Custom id can be used to store user ids or whatever is needed for the later processing of the
#resulting screenshot
grabzIt = GrabzItClient.GrabzItClient(
parser.get('GrabzIt', 'applicationKey'),
parser.get('GrabzIt', 'applicationSecret'))
result = grabzIt.GetResult(id)
if result != None:
#Ensure that the application has the correct rights for this directory.
fo = open(
os.path.dirname(os.path.abspath(__file__)) + os.path.sep + "results" +
os.sep + filename, "wb")
fo.write(result)
fo.close()
print("Content-type: text/html\n\n")