def delete_lab(slug):
'''
Deletes a lab specified by the slug parameter
Args:
slug: string specifying the slug of the lab
'''
print('DELETING A SPECIFIC LAB')
client = contentful_management.Client(
labs_constants.CONTENTFUL_MANAGEMENT_TOKEN)
entry = None
try:
print('Finding the lab %s...' % slug)
entry = client.entries(
labs_constants.CONTENTFUL_SPACE_ID,
labs_constants.CONTENTFUL_ENVIRONMENT).find(slug)
except contentful_management.errors.NotFoundError:
print('Entry not found for slug %s, STOPPING delete step')
return
else:
print('Found existing entry for slug %s, deleting...' % slug)
entry.unpublish()
entry.delete()
print('FINISHED delete for slug %s' % slug)
def _get_contentful_client():
api_token = _get_config()['management_api_token']
client = getattr(sys.modules[__name__], '_contentful_client')
if client is None:
client = contentful_management.Client(api_token)
setattr(sys.modules[__name__], '_contentful_client', client)
return client
def __init__(self):
'''
Must be called with a department already set.
'''
self.client = contentful_management.Client(secure.MANAGEMENT_API_TOKEN)
self.entries_client = self.client.entries(secure.SPACE_ID,
secure.ENVIRONMENT_ID)
self.content_types_client = self.client.content_types(
secure.SPACE_ID, secure.ENVIRONMENT_ID)
return None
def main(SPACE_ID, CF_ENV, PAT):
cma = contentful_management.Client(PAT)
content_types = cma.content_types(SPACE_ID, CF_ENV).all()
if len(content_types.items) < 1:
sys.exit('There\'s no content types in this space.')
file_name = f'{SPACE_ID}_content_model_{datetime.date.today()}.xlsx'
writer = pd.ExcelWriter(file_name)
for content_type in content_types:
ct = content_type.to_json()
name = clean_name(ct['name'])
fields = ct['fields']
df = pd.DataFrame(fields)
df.to_excel(writer, name, index=False)
writer.save()
def create_app(settings_override=None):
app = factory.create_app(__name__, __path__, settings_override)
contentful_delivery_client = contentful.Client(
os.environ['CONTENTFUL_SPACE_ID'],
os.environ['CONTENTFUL_DELIVERY_ACCESS_TOKEN'])
contentful_management_client = contentful_management.Client(
os.environ['CONTENTFUL_MANAGEMENT_ACCESS_TOKEN'])
nltk.download('punkt')
nltk.download('stopwords')
@app.route('/v1')
def abstract_docs():
return render_template('abstract.html')
@app.route('/v1', methods=['POST'])
def abstract():
if os.environ['FLASK_ENV'] == 'production':
data = request.get_json()
content_raw = data['fields']['content']['en-GB']
entry_id = data['sys']['id']
else:
entry_id = 'jZwuzvJy0g4OICOQU4y2S'
entry = contentful_delivery_client.entry(entry_id)
content_raw = entry.content
number_of_sents = 4
"""
Determine contentful resource
"""
environment_id = 'master'
entry = contentful_management_client.entries(
os.environ['CONTENTFUL_SPACE_ID'], environment_id).find(entry_id)
print('entry', entry)
"""
Remove markdown markup
"""
content_in_html = markdown(content_raw)
content_soup = BeautifulSoup(content_in_html, features='html.parser')
"""
Remove code snippets while leaving inline code snippets in place
"""
[
s.extract() for s in content_soup('code')
if len(s.prettify().splitlines()) > 3
]
"""
Remove headings and subheadings
"""
headings = [s.extract() for s in content_soup('h1')]
headings.extend([s.extract() for s in content_soup('h2')])
headings.extend([s.extract() for s in content_soup('h3')])
headings.extend([s.extract() for s in content_soup('h4')])
headings.extend([s.extract() for s in content_soup('h5')])
headings.extend([s.extract() for s in content_soup('h6')])
headings_in_text = " ".join([h.get_text() for h in headings])
"""
Remove newline characters
"""
for s in content_soup.findAll(text=True):
if '\n' in s.string and len(s.string) == 1:
s.extract()
"""
Create bag of words
"""
content_in_text = content_soup.get_text()
sents = sent_tokenize(content_in_text)
if len(sents) < number_of_sents:
return 'Not enough sentences for abstract extraction.', 403
words_in_content = word_tokenize(content_in_text.lower())
words_in_content.extend(word_tokenize(headings_in_text.lower()))
_stopwords = set(
stopwords.words('english') + list(punctuation) + ["''", "``"])
words_in_content = [
word for word in words_in_content if word not in _stopwords
]
freq = FreqDist(words_in_content)
top_10 = nlargest(10, freq, key=freq.get)
"""
Rank sentences by importance
"""
ranking = defaultdict(int)
for i, sent in enumerate(sents):
for w in word_tokenize(sent.lower()):
if w in freq:
ranking[i] += freq[w]
"""
Extract abstract
"""
sents_idx = nlargest(number_of_sents, ranking, key=ranking.get)
abstract = " ".join([sents[j] for j in sorted(sents_idx)])
"""
Write abstract to contentful
"""
if not os.environ['FLASK_ENV'] == 'development':
entry_attributes = {
'content_type_id': 'post',
'fields': {
**entry.fields(),
**entry.fields_with_locales(), 'abstract': {
'en-GB': abstract
}
}
}
entry.update(entry_attributes)
return abstract
return app
def id_generate():
seed = random.getrandbits(32)
while True:
yield seed
seed += 1
id_entry = id_generate()
po = polib.pofile('main.po')
for entry in po:
client = contentful_management.Client(
'CFPAT-_QLbCxDyhpTnTR2FFvUSqrly5QCZxfHQzzNCDQdzroE')
entry_id = next(
id_entry) # Use `None` if you want the API to autogenerate the ID.
entry = client.entries('orl9epj4q4ul', 'master').create(
entry_id, {
'content_type_id': 'main',
"fields": {
"msgid": {
"en-US": entry.msgid
},
"msgstr": {
"en-US": entry.msgstr
}
}
def __init__(self, api_token, space_id):
client = contentful_management.Client(api_token)
self.environment = client.environments(space_id).find('master')
import contentful_management
import time
import os
from dotenv import load_dotenv
load_dotenv()
SPACE_ID = os.getenv("SPACE_ID")
DELIVERY_API_KEY = os.getenv("DELIVERY_API_KEY")
MANGEMENT_API_KEY = os.getenv("MANGEMENT_API_KEY")
TESTING_ENV = "circle_testing"
client = contentful_management.Client(MANGEMENT_API_KEY)
try:
environment = client.environments(SPACE_ID).find(TESTING_ENV)
print("Deleting previous environment {}".format(TESTING_ENV))
environment.delete()
except:
print("{} environment doesn't exist".format(TESTING_ENV))
print("Creating new Enivronment: {}".format(TESTING_ENV))
environment = client.environments(SPACE_ID).create(TESTING_ENV,
{"name": TESTING_ENV})
time.sleep(1)
environment.name = TESTING_ENV
print("Polling to detect creation of {}".format(TESTING_ENV))
while True:
try:
#print(f"Arguments count: {len(sys.argv)}")
if len(sys.argv) < 2:
print('missing arguments for origin and destination space')
quit()
elif len(sys.argv) < 3:
print('missing second argument for destination space')
quit()
# get spaces id from arguments
orig_space = sys.argv[1]
dest_space = sys.argv[2]
cma_key = 'YOUR_CMA_KEY'
#conect to cma
client = contentful_management.Client(cma_key)
# get all roles on dest space and add them to array
my_input = []
dest_roles = client.roles(dest_space).all()
for dest_role in dest_roles:
dest_role_name = getattr(dest_role, 'name', 'Name not found')
print(f"Role found on destination '{dest_space}': {dest_role_name}")
my_input.append(dest_role_name)
# on loop inserting roles, avoid already created roles
roles = client.roles(orig_space).all()
for role in roles:
role_name = getattr(role, 'name', 'Not a product')
if role_name not in my_input:
import contentful_management
import re
from pathlib import Path
key_dir = Path(__file__).resolve().parent.parent.joinpath('KEYS')
KEY = key_dir.joinpath('contentful.txt').read_text()
# set up Contentful environment and get list of content types as starting point
client = contentful_management.Client(KEY)
space = client.spaces().all()[2].id
ENV = client.environments(space).find('master')
all_types = ENV.content_types().all()
types = [t.id for t in all_types]
#%%
# Sublists of categorised content types
pages = ['adviceCollection', 'adviceCollectionAdviser', 'adviceList']
units = [
'adviceUnit', 'adviceUnitAdviser', 'callout', 'calloutAdviser',
'circumstantialUnit', 'circumstantialUnitAdviser'
]
dynamic = [
'banner', 'table', 'adviserWarning', 'amount', 'backgroundText',
'callCosts', 'contactDetails', 'contentPattern', 'legislationLink'
]
tools = ['tool', 'resultPage', 'question', 'answer']
def _sys_field(self, cid):
'''
param cid: contentful id
'''
return {'sys': {'type': 'Link', 'linkType': 'Entry', 'id': cid}}
def to_camel_case(self, string):
components = string.replace('-', '_').split('_')
return components[0] + ''.join(x.title() for x in components[1:])
if __name__ == "__main__":
from pprint import pprint
# Example using the Contentful client
client = contentful_management.Client(secure.MANAGEMENT_API_TOKEN)
sid = secure.SPACE_ID
eid = secure.ENVIRONMENT_ID
content_type = client.content_types(sid, eid).find('instructor')
# Translation of metadata to a Contentful entry
T = Translate()
pprint(
T.autoInstructor({
'name': 'Daniel Seaton',
'title': 'Dr.',
'bio': 'New at ODL.',
'department_clink_id': '1c5BaHz1xsxiNogsMkMQPr'
}))
from dotenv import load_dotenv
import os
import contentful
import contentful_management
load_dotenv()
cc = contentful.Client(os.getenv("CONTENTFUL_SPACE_ID"),
os.getenv("CONTENTFUL_ACCESS_TOKEN"))
cm = contentful_management.Client(os.getenv("CONTENTFUL_PAT"))
def write_guest(name, description=None):
entry = cm.entries(os.getenv("CONTENTFUL_SPACE_ID"),
os.getenv("CONTENTFUL_ENVIRONMENT")).create(
None, {
"content_type_id": "guest",
"fields": {
"name": {
"en-US": name
},
"description": {
"en-US": description
}
}
})
return entry
def write_episode(title,
number=None,
"id": id,
"name": name,
"slug": slug,
"description": desc
})
return product_types
dotenv.load_dotenv()
SPACE_ID = os.getenv("SPACE_ID")
ACCESS_TOKEN = os.getenv("ACCESS_TOKEN_MGMT")
ENVIRONMENT = "master"
client = contentful_management.Client(ACCESS_TOKEN)
content_type = client.content_types(SPACE_ID, ENVIRONMENT).find("productType")
entries = content_type.entries().all({'limit': '1000'})
existing_product_types = []
for entry in entries:
existing_product_types.append(str(entry.fields("de")["id"]))
print(
f"{len(existing_product_types)} product types found: {','.join(existing_product_types)}"
)
product_types = load_product_types()
for product_type in product_types:
if product_type["id"] not in existing_product_types:
import json
import os
import re
import shutil
import labs_constants
import boto3
from botocore.exceptions import NoCredentialsError
import frontmatter
import contentful_management
client = contentful_management.Client(
labs_constants.CONTENTFUL_MANAGEMENT_TOKEN)
SLUG_BLACKLIST = []
def get_slugs():
'''
Gets the list of slugs, which are the directory names of
each directory under the labs/ directory
Returns:
List of strings representing slugs
'''
slugs = []
# r=root, d=directories, f = files
for r, d, f in os.walk(labs_constants.LABS_PATH):
slugs = [folder for folder in d]
def main(folder, drive_path):
"""A personal Photo Manager for Contentful and Google Drive.
Creates a Root Google Drive folder, along with a year and individual folder for the album.
Asks the user if they want to upload to Contentful as well, and if so asks for a collection Title.
"""
contentful_upload = promptUser(
"Do you want to upload to Contentful? [Y/n]")
drive_upload = promptUser("Do you want to upload to Google Drive? [Y/n]")
if contentful_upload:
collection_title = input(
"Please provide a title for the Photo Collection:").strip()
photos = []
collection_date = None
print("===== Authenticating Contentful =====")
try:
client = contentful_management.Client(CONTENTFUL_MANAGEMENT_TOKEN)
portfolio_space = client.spaces().find(CONTENTFUL_SPACE_ID)
master_env = portfolio_space.environments().find('master')
except:
contentful_upload = False
print(
"!!!!! Authenticating Contentful Failed. Ensure the Management Token and Space ID are correct !!!!!"
)
if drive_upload:
service, folder_id = driveFolderSetup(folder)
print("===== Iterating Through Photos =====")
directory = os.fsencode(drive_path + DRIVE_YEAR + "/" + folder)
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith(".jpg"):
filepath = os.fsencode(drive_path + DRIVE_YEAR + "/" + folder +
"/" + filename)
if drive_upload:
photo_metadata = {'name': [filename], 'parents': [folder_id]}
photo_media = MediaFileUpload(filepath,
mimetype='image/jpeg',
resumable=True)
request = service.files().create(media_body=photo_media,
body=photo_metadata)
response = None
while response is None:
status, response = request.next_chunk()
if status:
print("Uploaded", int(status.progress() * 100))
print("Uploaded", filename, "to Google Drive")
if contentful_upload:
if not collection_date:
with open(os.fsdecode(filepath), 'rb') as image_file:
image = Image(image_file)
collection_date = datetime.datetime.strptime(
image.datetime_original,
'%Y:%m:%d %H:%M:%S').date()
try:
contentful_upload = portfolio_space.uploads().create(
os.fsdecode(filepath))
asset_attributes = {
'fields': {
'title': {
"en-US": filename
},
'file': {
'en-US': {
'fileName':
filename,
'contentType':
'image/jpeg',
'uploadFrom':
contentful_upload.to_link().to_json()
}
}
}
}
contentful_asset = master_env.assets().create(
None, asset_attributes) # None lets API generate ID
contentful_asset = contentful_asset.process(
) # Processing is an async task, so I need to wait to publish it
except:
print('!!!!! Error Uploading Contentful Asset:', filename)
else:
photos.append(contentful_asset)
print("Uploaded", filename, "to Contentful")
if contentful_upload:
print("===== Creating Contentful Photo Collection =====")
photoCollection_attributes = {
'content_type_id': 'photoCollection',
'fields': {
'title': {
'en-US': collection_title
},
'photos': {
'en-US': [item.to_link().to_json() for item in photos]
},
'collectionDate': {
'en-US': collection_date.isoformat()
},
'featuredImage': {
'en-US': photos[0].to_link().to_json()
}
}
}
try:
new_photoCollection = master_env.entries().create(
None, photoCollection_attributes
) # None lets API auto generate unique ID
except:
print('!!!!! Error Creating Contentful Photo Collection !!!!!')
print("===== Publishing Uploaded Contentful Images =====")
for photo in photos:
try:
master_env.assets().find(photo.id).publish()
except:
print('!!!!! Error Publishing Contentful Asset:',
photo.file.fileName)
print("===== Contentful Upload and Publish Complete! =====")