def update(request):
books = Book.objects.all()
for book in books:
title = book.book_title.rstrip().lstrip().replace('\n', ' ').replace(
'\r', '')
description = book.book_description.rstrip().lstrip().replace(
'\n', ' ').replace('\r', '')
bookup = Book.objects.filter(id=book.id).update(
book_title=re.sub(" +", " ", title),
book_description=re.sub(" +", " ", description))
return HttpResponse("sesses")
def modifalang(request):
books = Book.objects.all()
for d in books:
df = re.sub("-+", " ", d.book_url)
if d.book_url == "":
dat = Book.objects.filter(id=d.id).update(
keyboard=d.book_url[:15],
book_url=d.book_url[:60].replace(" ", "-"))
return HttpResponse("not change")
def changebook(request, book):
s = ""
books = Book.objects.filter(book_url=book)
for d in books:
df = re.sub("-+", " ", d.book_url)
if df == " " or d.book_url == "-" or d.book_url.rstrip().lstrip(
) == "":
trans1 = ''
data = ""
if trans1.text == "":
dat = Book.objects.filter(id=d.id).update(
keyboard=d.book_title[:15],
book_url=d.book_title[:60].replace(" ", "-"))
else:
dat = Book.objects.filter(id=d.id).update(
keyboard=data[:15], book_url=data[:60].replace(" ", "-"))
return HttpResponse("not change")
def changelang(request):
s = ""
books = Book.objects.all().order_by('-id')
for d in books:
df = re.sub("-+", " ", d.book_url)
if df == " " or d.book_url == "-" or d.book_url.rstrip().lstrip(
) == "":
data = ""
trans1 = ""
if trans1 == "":
dat = Book.objects.filter(id=d.id).update(
keyboard=d.book_title[:15],
book_url=d.book_title[:60].replace(" ", "-"))
else:
dat = Book.objects.filter(id=d.id).update(
keyboard=data[:15], book_url=data[:60].replace(" ", "-"))
print(data[:15])
return HttpResponse("not change")
def hindistory(request, url):
bdf = Book.objects.all()
if bdf.count() < 40000:
return HttpResponse("puh")
data = ""
response = requests.get(url)
if response.status_code == 200:
soup = BeautifulSoup(response.text)
d = soup.find("div", attrs={'id': "main-row"})
if d:
titles = d.find(
'h2',
attrs={'class': 'title-target text-left d-none d-sm-block'})
title = titles.text
print(title)
content = d.find("div",
attrs="content-container avoid-text-copy story")
url = re.sub("^a-zA-Z\u0900-\u097F+", '', title)
keysearch = '%20'.join(title.split()[:3])
datad = requests.get(
"http://google.com/complete/search?output=toolbar&q=" +
keysearch)
soupd = BeautifulSoup(datad.text)
ds = soupd.findAll('suggestion')
data = ""
string = []
for i in ds:
string.append(i['data'])
print(",".join(string[:5]))
catarray = []
arraycat = d.findAll(
"a", {
"class":
'badge badge-light badge-light-hover p-2 rounded-pill mr-1 mb-2 ga-track border border-danger'
})
for catd in arraycat:
cat_check = Category.objects.filter(cat_title=catd.text)
if cat_check.count() < 1:
cats = Category(cat_title=catd.text)
cats.save()
catarray.append(cats.pk)
else:
catarray.append(cat_check.first().id)
books = Book.objects.filter(book_title=title)
description = soup.find("meta", attrs={'name': "description"})
books = Book.objects.filter(book_title=title)
img = soup.find("img",
attrs={"class": 'rounded shadow-lg d-block'})
catds = d.find('span', attrs={'class': 'col-sm-6 col-12'})
catmain = catds.find("a", attrs={'class': 'ga-track'})
for s in catmain.select('b'):
s.extract()
cts = Category.objects.filter(
cat_title=str(catmain.text.replace(':', "")))
if cts.count() < 1:
ctd = Category(cat_title=str(catmain.text.replace(':', "")))
ctd.save()
catarray.append(ctd.id)
else:
catarray.append(cts[0].id)
print(img.get('src'))
if books.count() < 1 and d:
book = Book(book_title=title,
book_description=str(description['content']),
book_data=str(content),
book_arrcat=catarray,
book_rates=2,
publisher=1,
keyboard=",".join(string[:5]),
book_publish=True,
book_upload_date=timezone.now(),
book_url=url.replace("\n", "").replace(" ", "-"),
book_catid=1,
book_commit_id=1)
if img:
check_img = requests.get(img.get('src'))
if check_img.status_code == 200:
try:
book.get_remote_image(img.get('src'))
print(img.get('src'))
except:
print("error data")
else:
print("error data")
book.save()
return data
def wordpressjson(url, web):
response = requests.get(url)
if response.ok:
# response = requests.get(url)
jas = json.loads(response.text)
caatid = []
for js in jas:
title = js['title']['rendered']
content = js['content']['rendered']
parsed_html = BeautifulSoup(content)
for f in parsed_html.select('img'):
f.extract()
for f in parsed_html.select('a'):
f.extract()
for f in parsed_html.select('script'):
f.extract()
description = parsed_html.text[:400]
cat = js['categories']
for ca in cat:
caty = requests.get("https://" + web +
"/wp-json/wp/v2/categories/" + str((ca)))
# print(caty.text)
if caty.status_code == 200:
jsc = json.loads(caty.text)
catname = jsc['name']
cats = Category.objects.filter(cat_title=catname)
if cats.count() < 1:
catsave = Category(cat_title=catname)
catsave.save()
caatid.append(catsave.id)
else:
caatid.append(cats[0].id)
featured_media = requests.get("https://" + web +
"/wp-json/wp/v2/media/" +
str(js['featured_media']))
#featured_media = requests.get(js["_links"]['wp:featuredmedia'][0]['href'])
#print(featured_media.text)
img_json = json.loads(featured_media.text)
# print(img)
# img = js['featuredimage']
books = Book.objects.filter(book_title=title)
keybord = re.sub(r"[^A-Za-z0-9 ]+", '', title)
slug = js['slug']
fgh = re.sub(
' +', ' ',
slug.rstrip().lstrip().replace('\n', ' ').replace('\r', ''))
focaskey = re.sub(r"[^A-Za-z0-9 ]+", '', fgh)
urlsd = focaskey.replace(" ", "-").rstrip("-").lstrip("-")
# keysearch = '%20'.join(title.split()[:2])
# datad = requests.get("http://google.com/complete/search?output=toolbar&q=" + keysearch)
# soupd = BeautifulSoup(datad.text)
# d = soupd.findAll('suggestion')
# data = ""
# string = []
# for i in d:
# string.append(i['data'])
#
# print(",".join(string[:5]))
if books.count() < 1 and js['status'] == "publish":
book = Book(book_title=title,
book_description=description,
book_data=str(parsed_html),
book_arrcat=caatid,
book_rates=2,
publisher=1,
keyboard="",
book_publish=True,
book_upload_date=timezone.now(),
book_url=urlsd,
book_catid=1,
book_commit_id=1)
try:
img = img_json['guid']['rendered']
book.get_remote_image(img)
except KeyError:
print("no img")
book.save()