def get_client():
gc = client.GoodreadsClient(
os.getenv('GOODREADS_CLIENT_ID'),
os.getenv('GOODREADS_CLIENT_SECRET'),
)
# gc.authenticate()
return gc
def main():
logging.debug("Creating good reads client.")
grclient = client.GoodreadsClient(config['GOODREADKEYS']['KEY'], config['GOODREADKEYS']['SECRET'])
grcollector = collectdata.GoodreadsCollect(grclient, config['DATA_DIR_PATH']['PATH'])
end_after = int(config['TIMEPARAM']['END_TIME'])
wait_time = int(config['TIMEPARAM']['WAIT_TIME'])
logging.debug(f"Execution started at {datetime.now()}")
end_time = datetime.now() + timedelta(seconds=end_after)
logging.debug(f"Execution will end at : {end_time}")
while(datetime.now() < end_time):
logging.debug("Fetching data...........")
try:
grcollector.fetch_data()
except Exception as e:
logging.exception("Some exception occured : ", e)
continue
logging.debug(f"Waiting for {config['TIMEPARAM']['WAIT_TIME']} seconds")
time.sleep(wait_time)
logging.debug("Execution ended.")
def __init__(self):
#sets up good reads client and elastic search,
#should not really need goodreads client
self.gc = client.GoodreadsClient(
"NGr7Zl6XG9nTeNClLz9xA",
"WILsiGKkWTEoKh4M7z11TF0P2ukSRcJ2OEFJMngDgY")
self.es = Elasticsearch([{'host': 'localhost', 'port': 9200}])
def index(request):
api_key = key['api_key']
api_secret = key['api_secret']
gc = client.GoodreadsClient(api_key, api_secret)
first_book = gc.book(1)
second_book = gc.book(2)
third_book = gc.book(3)
fourth_book = gc.book(4)
fifth_book = gc.book(5)
sixth_book = gc.book(6)
seventh_book = gc.book(7)
eigth_book = gc.book(8)
ninth_book = gc.book(9)
books = []
print(gc)
context = {
'first_book': first_book,
'second_book': second_book,
'third_book': third_book,
'fourth_book': fourth_book,
'fifth_book': first_book,
'sixth_book': sixth_book,
'seventh_book': seventh_book,
'eigth_book': eigth_book,
'ninth_book': ninth_book,
}
return render(request, 'good_reads_api/index.html', context)
def get_gr_page(author):
gc = client.GoodreadsClient(goodreads_key, goodreads_secret)
book_ids = gc.search_books(author, search_field='author')
# order seems to be driven by likelihood of quotes so
book_ids = book_ids[:3]
#print(book_ids)
#n = randrange(len(book_ids))
#book_id = book_ids[n]
while 1:
book_id = choice(book_ids)
#print(f"{book_id=}")
try:
page = urllib.request.urlopen(gr_url + book_id).read()
except Exception as e:
print(f"Exception retrieving from goodreads: {e}")
return None
soup = BeautifulSoup(page, "lxml")
if soup.find("div", class_="quoteText"):
return soup
book_ids.remove(book_id)
if not book_ids:
return None
def get_basic_book_info(isbn):
gc = client.GoodreadsClient(Info.key, Info.secret)
book = gc.book(None, isbn)
title = book.title
author = book.authors[0]
publisher = book.publisher
img_url = book.image_url
book_link = book.link
book_info = [title, author, publisher, img_url, book_link]
return book_info
def initiate_goodreads_lient():
global gc
#read api connection details from ini file.
config = configparser.ConfigParser()
#os.path.dirname(os.path.realpath(__file__))
config.read(os.path.curdir + r'\goodreads.ini')
print(str(config.sections()))
api_key = config.get('access_info', 'api_key')
api_secret = config.get('access_info', 'api_secret')
gc = client.GoodreadsClient(api_key, api_secret)
return gc
def main():
args = parse_args()
# Setup stdout
encoding = locale.getpreferredencoding()
writer = getwriter(encoding)
sys.stdout = writer(sys.stdout)
args.query = to_unicode(args.query)
goodreads_key = api_key
goodreads_secret = api_secret
grc = client.GoodreadsClient(goodreads_key, goodreads_secret)
books = get_books(grc, args)
AR_sorted = sorted(books, key=lambda b: float(b.average_rating))
NTR_sorted = sorted(books, key=lambda b: float(b.text_reviews_count))
max_AR = float(AR_sorted[-1].average_rating)
max_NTR = float(NTR_sorted[-1].text_reviews_count)
Books = []
totaux = []
for book in books:
d = {
star_label: int(star_number)
for star_label, star_number in (
tuple(rating.split(':'))
for rating in book.rating_dist.split('|'))
}
totaux.append(float(d.pop('total', 'inf')))
TR_sorted = sorted(totaux)
max_TR = TR_sorted[-1]
for book in books:
b = Book(book, max_AR, max_NTR, max_TR)
Books.append(b)
if not os.path.isdir("results"):
os.mkdir("results")
result_file = os.path.join("results", "results.txt")
with open(result_file, "w") as f:
old, sys.stdout = sys.stdout, f
print(
"List of results, sorted by higher fitness:\n<Book title> : <Book fitness>"
)
print("-" * 56)
for book in sorted(Books, key=lambda b: b.fitnessScore, reverse=True):
print(book)
sys.stdout = old # restore stdout
print(
"Find your results in the 'results.txt' file of the root directory of the script"
)
def get_books_from_gr_api(query, api_key, api_secret): gc = client.GoodreadsClient(api_key, api_secret) new_books = [] for i in range(1,10): try: new_books += gc.search_books(q=query, page=i, search_field='all') except: continue new_books = [ book.gid for book in new_books ] new_books = list( set(new_books) ) return new_books
def main():
"""
Main function of the test module
"""
# setting up the API keys from local keys.py file
goodreads_key = os.environ['GOODREADS_KEY']
goodreads_secret = os.environ['GOODREADS_SECRET']
# creating a client for book search and information retrieval
gc = client.GoodreadsClient(goodreads_key, goodreads_secret)
current_path = os.getcwd()
file = open(os.path.join(current_path, "output", "log.json"), "w")
gutenberg_titles = []
# Getting the title of the first 3000 books on Project Gutenberg (EXTREMELY FAST)
for i in range(1, 10):
title = list(get_metadata('title', i))
if title:
# prepare the string for the file name
filename = ''.join(
e for e in title[0] if e.isalnum() or e == ' ') + ".txt"
gutenberg_titles.append(filename[:-4])
text = strip_headers(load_etext(i)).strip()
with open(os.path.join(current_path, "output", filename),
"w") as output_file:
output_file.write(text)
titles = dict()
# Searching for the books on Goodreads, reading their metadata
for book_title in gutenberg_titles:
try:
lst = gc.search_books(book_title, search_field='title')
if not lst:
continue
else:
book = lst[0]
titles[book.title] = (
book_title + ".txt", str(book.popular_shelves),
str(book.similar_books), str(book.authors),
dict(dict(book.work)['original_publication_year'])['#text'])
except (request.GoodreadsRequestException, KeyError, TypeError):
continue
json.dump(titles, file, indent=4)
file.close()
def recommend_book(feeling, FastText_model, book_kmeans, feelings_knn, glove):
'''function to get a list of 5 books that are most relevant to the user's query
input:
feeling: the user query string
FastText_model: the pre-trained FastText model on all book summaries from the Goodreads list 'Best Books Ever'
book_kmeans: the pre-trained k-means clustering model on the vector descriptions of all book summaries from the Goodreads list 'Best Books Ever'
feelings_knn: the pre-trained k-NN model on all cases
glove: the dictionary of pre-trained GloVe word embeddings
output:
a list of 5 books that are most relevant to the user's query
'''
# create the Goodreads API client
goodreads_key = 't6mIkabukH29jAey0381yA'
goodreads_secret = '6IWvvO5CNFIAqUragee2Bb5HkEOvxIYqSXeXdFSHvM'
good_client = client.GoodreadsClient(goodreads_key, goodreads_secret)
# get the book based on the query
cure_short = pd.read_csv('cure_short.csv')
# get the matching case and the book prescribed for the case
case_indices = feeling_to_case(feeling, feelings_knn, glove)
id = cure_short.iloc[case_indices]['goodreads_id'].item()
test_book = good_client.book(id)
test_book_description = test_book.description
test_book_vector = preprocess(test_book_description, FastText_model)
# get the cluster that the prescribed book belongs to
cluster_number = book_kmeans.predict(test_book_vector).item()
info_books = pd.read_json('best_books_clustered.json')
predicted_cluster = info_books[info_books['cluster'] == cluster_number]
predicted_cluster.reset_index(drop=True, inplace=True)
# fit a k-NN to the vector description of all the books inside the cluster
X = list(predicted_cluster['vector_description'])
X = np.array(X)
books_knn = NearestNeighbors(metric='cosine') # should try 'mahalanobis'
books_knn.fit(X)
# get a list of the most similar books to the prescribed book from the cluster
distance, indices = books_knn.kneighbors(test_book_vector, n_neighbors=5)
indices = indices.reshape(-1, )
recommendation_list = list(predicted_cluster.iloc[indices]['title'])
return recommendation_list
def getBookInfo(count=booksCount):
"""
returns a list of objects, books(going by id) --> all books that exist from #1 to count (inclusive
"""
gc = client.GoodreadsClient("JdH0YOXuBLIFXhXUGMNmA",
"XtIlhsavfhSICDEMLzWLRyKp509VNaeGbVUh7tJaQ")
gc.authenticate("JdH0YOXuBLIFXhXUGMNmA",
"XtIlhsavfhSICDEMLzWLRyKp509VNaeGbVUh7tJaQ")
bookList = []
for i in range(1, count + 1):
try:
bookList.append(gc.book(i)) # get id --> .gid
print('#' + bookList[-1].gid, bookList[-1].title)
except Exception:
print("book", i, "cannot be found?")
return bookList
def goodreads(isbn):
cl = client.GoodreadsClient("YwoRrbmvD1xQgyfIIOPQ", "INo8jC4JeAVOiXFckzQPKqYYeuq2wFLJyBKQmidDy0")
book = cl.book(isbn=isbn)
title = book.title
authors = book.authors
author = ''
for a in authors:
author += a.__repr__()
author += ", "
avg_rating = book.average_rating
rev_count = book.text_reviews_count
return jsonify({
"title": title
"author": author
"avg_rating": avg_rating
"rev_count": rev_count
})
def set_genre_goodreads(books):
CONSUMER_KEY = 'gsyDVEcZ3ZOFqDvXxrA'
CONSUMER_SECRET = 'U182SOVsGZRYY7IFJ7jqpltLyXkBvPwp9mUnLsWcek'
gr = client.GoodreadsClient(CONSUMER_KEY, CONSUMER_SECRET)
i = 0
chunk_size = 500
already_processed = books.dropna(subset=['Hashed-Genre'], how='any')
to_be_read = set(books.index) - set(already_processed.index)
for isbn in to_be_read:
print("Reading book ", i, " of ", len(to_be_read))
i += 1
try:
shelves = gr.book(isbn=isbn).popular_shelves
shelves = [str(x) for x in shelves]
except Exception:
print("Error in ISBN ", isbn)
continue
undesired_shelves = set([
'to-read', 'own', 'books-i-own', 'currently-reading',
'owned-books', 'default', 're-read', 'my-books', 'owned',
'favorite', 'favorites', 'wishlist', 'kindle', 'to-buy', 'library',
'ebook', 'maybe', 'my-book', 'e-book', 'e-books', 'books',
'my-library', 'want-to-read', 'have', 'own-it', 'own-to-read',
'giller-winners', 'recommended', 'wish-list', 'my-booshelf',
'short-stories', 'didn-t-finish', 'read-in-2015', 'coming-of-age',
'read-in-2009', 'read-in-2016', 'gave-up', 'dnf',
'personal-library', 'book-club', 'not-available-on-overdrive',
'abandoned', 'single-books', 'must-read'
])
for x in set(shelves).intersection(undesired_shelves):
shelves.remove(x)
if len(shelves) != 0:
genre = shelves[0]
books.set_value(isbn, 'Hashed-Genre', hash_text(genre))
else:
books.set_value(isbn, 'Hashed-Genre', 0)
# save constantly the books dataset
if i % chunk_size == 0:
save_processed_dataframe(books)
save_processed_dataframe(books)
def __init__(self, api_info, api_type='goodreads'):
"""
Inits a knowledgeSeeker who will seek out book information.
:param userlist_name: Name of userlist to get books from.
:param api_info: key info for the api we are using. This is (key, secret) for goodreads
and (amazon_access_key, amazon_secret_key, amazon_assoc_tag) for amazon.
:param api_type: 'goodreads' or 'amazon'. The first gets book objects from goodreads
and the second gets book objects from amazon.
"""
self.api_type = api_type
self.current_path = None
if api_type == 'goodreads':
self.api_client = client.GoodreadsClient(api_info[0], api_info[1])
self.bookshelf_path = "../data/book_db/goodreads_bookshelf.db"
else:
raise Exception("api_type must be \'goodreads\'.")
self.bookshelf = shelve.open(self.bookshelf_path)
def __init__(self,
index,
search_type,
rating_weight=1,
pages_weight=1,
shelf_weight=1,
regular_weight=1,
idf=True):
#sets up good reads client and elastic search,
#should not really need goodreads client
self.gc = client.GoodreadsClient(
"NGr7Zl6XG9nTeNClLz9xA",
"WILsiGKkWTEoKh4M7z11TF0P2ukSRcJ2OEFJMngDgY")
self.es = Elasticsearch([{'host': 'localhost', 'port': 9200}])
self.index = index
self.type = search_type
self.shelf_to_pos, self.shelf_to_score = self.read_shelf_file(idf)
self.rating_weight = rating_weight
self.pages_weight = pages_weight
self.regular_weight = regular_weight
self.shelf_weight = shelf_weight
self.reg = re.compile("\w+")
def main():
"""
Main function of the test module
"""
# setting up the API keys from local keys.py file
goodreads_key = os.environ['GOODREADS_KEY']
goodreads_secret = os.environ['GOODREADS_SECRET']
# creating a client for book search and information retrieval
gc = client.GoodreadsClient(goodreads_key, goodreads_secret)
current_path = os.getcwd()
file = open(os.path.join(current_path, "output", "log.txt"), "a")
# Getting the title of the first 3000 books on Project Gutenberg (EXTREMELY FAST)
for i in range(1, 10):
title = list(get_metadata('title', i))
if title:
# prepare the string for the file name
filename = ''.join(e for e in title[0] if e.isalnum()) + ".txt"
text = strip_headers(load_etext(i)).strip()
with open(os.path.join(current_path, "output", filename),
"w") as output_file:
output_file.write(text)
file.write(f"{title[0]} plaintext saved to '{title[0]}.txt'\n")
# Getting the titles and publishing years for the first 3000 books on Goodreads
# Pretty slow because Goodreads allows 1 request per second
for i in range(1, 20):
try:
book = gc.book(i)
file.write(
f"{book.title} - published in {dict(dict(book.work)['original_publication_year'])['#text']}\n"
)
except (request.GoodreadsRequestException, KeyError):
continue
from goodreads import client
import pickle
gc = client.GoodreadsClient("ueUMoVwAkXNUPcOA4Y35yA", "R2N1HWPOdt4EEwQionNz0h3BgkY2z0yP5T3eXp8djc")
book_dict = {}
def get_book(i):
try:
book = gc.book(str(i))
book_dict[i] = (book.publisher, book.description, book.average_rating)
except:
return None
for i in range(10000):
get_book(i)
print(i)
pickle.dump(book_dict, "data.pkl")
from flask import Flask, request, render_template
from goodreads import client
gc = client.GoodreadsClient('ZfHUtSBSMU3ZOTo82zl7wA','OlI30Km37ikK1EIgG7jwWDxeiaAJDX10Fm9zw9XTUA')
app = Flask(__name__)
@app.route('/')
def form():
return render_template('form.html' )
@app.route('/', methods=['POST'])
def form_post():
try:
input = request.form['input']
isbn_no = int(text.strip())
book_id = int(text.strip())
recommendations = gc.book(isbn_no).similar_books[:7]
recommendations.insert(0,gc.book(book_id))
print(recommendations)
return render_template('index.html', len = 7, recommendations=links)
except:
return render_template('404.html')
if __name__=="__main__":
app.run()
def main(argv):
# since we are reading only, no need to authenticate
# the script expects the api client key and the client secret as the first two arguments to the script
# you gets these from Goodreads (see https://www.goodreads.com/api for more details and to get your own)
gc = client.GoodreadsClient(argv[1], argv[2])
# parse the markdown document (table) into lines
lines = [line.strip() for line in open('books.md')]
# create new headings starting with the old markdown file header
headings = create_new_headings(lines[0])
# create a list for the parsed and extended book records
records = []
idx = 1
# skip the second line from the markdown file as it is markdown for the table header
for line in lines[2:]:
print(idx)
idx = idx + 1
# within each line use the table column markdown to split into fields
record = line.split(' | ')
# set some defaults for the book attributes in case they cannot be found
# set the default rating to '0.0' and the rating count to '0'
book_title = ''
average_rating = '0.0'
ratings_count = '0'
number_pages = '0'
publication_date = '1/1/1000'
publisher = ''
isbn = ''
# we can only use the Goodreads API to get the ratings data if a link to the book in Goodreads exists
if "[Goodreads]" in record[3]:
book_id = find_book_id(record[3])
attributes = get_book_attributes(gc, book_id)
book_title = book_title if attributes[
"title"] is None else attributes["title"]
average_rating = average_rating if attributes[
"average rating"] is None else attributes["average rating"]
ratings_count = ratings_count if attributes[
"ratings count"] is None else attributes["ratings count"]
number_pages = number_pages if attributes[
"number pages"] is None else attributes["number pages"]
publication_date = publication_date if attributes[
"publication date"] is None else attributes["publication date"]
publisher = publisher if attributes[
"publisher"] is None else attributes["publisher"]
isbn = isbn if attributes["isbn"] is None else attributes["isbn"]
record.append(book_title)
record.append(average_rating)
record.append(ratings_count)
record.append(number_pages)
record.append(publication_date)
record.append(publisher)
record.append(isbn)
records.append(record)
# sort by average rating: highest to lowest
records.sort(key=lambda x: float(x[5]), reverse=True)
# write the output
write_markdown("books_ratings.md", headings, records)
write_data("books_ratings", headings, records)
from goodreads import client
import json
import time
import requests
api_key = ''
api_token = ''
book_list = []
all_book_title = []
book_number = 1
gc = client.GoodreadsClient(api_key, api_token)
def API_json(gc, book_number, all_book_title, book_list):
while (book_number < 10000000):
try:
book = gc.book(book_number)
dist = book.rating_dist
#seprator = ';'
#KharCode = str(book.title) + seprator + str(book.authors[0]) + seprator + str(book.isbn) + seprator + str(book.language_code) + seprator + str(book.publication_date) + seprator + str(book.publisher) + seprator + str(book.num_pages) + seprator + str(book.rating_dist) + seprator + str(book.average_rating) + seprator + str(book.format) + seprator + str(book.is_ebook) + seprator + str(book.text_reviews_count) + seprator + str(book.gid) + "\n"
book_dic = {
"Id": str(book_number),
"Name": str(book.title),
"Authors": str(book.authors[0]),
"ISBN": book.isbn,
"Rating": float(book.average_rating),
"PublishYear": int(book.publication_date[2]),
"PublishMonth": int(book.publication_date[1]),
"PublishDay": int(book.publication_date[0]),
"Publisher": book.publisher,
from goodreads import client
from database import firebase
from FMRI import main_method
cache = SimpleCache()
app = Flask(__name__, template_folder='Templates')
app.secret_key = 'super secret key'
now = datetime.datetime.now()
#GR_KEY = 'hCgnomVsyFTNe73zLW7Q'
GR_KEY = 'HeN7az3JVPSRALsq6Jxpfg'
#GR_SECRET = 'SR9wYYUa5tzHx0vQrVZEDghDoMBjtkItshkYwVkCcQ'
GR_SECRET = 'J2qXu5Q1XSvSYusFWxEEAXeqNr72fEScyzhDk2Gx8'
GR_ACCESS_TOKEN = app.secret_key
GR_ACCESS_TOKEN_SECRET = app.secret_key
gc = client.GoodreadsClient(GR_KEY, GR_SECRET)
auth = firebase.auth()
db = firebase.database()
db_storage = firebase.storage()
@app.route('/')
def index():
return render_template('home.html')
@app.route('/about')
def about():
return render_template('about.html')
import logging
import logging.config
logging.config.fileConfig('logging.conf')
# create logger
logger = logging.getLogger('mainLMM')
logging.info("__________START______")
from goodreads import client
gc = client.GoodreadsClient('gOCk7w1mOcYTs97j9BmCkw',
'JlcnVqvmuoyznIO06huEbreIcT9mNw4qyFAbjVu3WI')
logging.debug("apres gc =")
book = gc.book(1)
logging.debug("apres gc.book")
msg = "BOKK TITLE : " + book.title
logging.info(msg)
logging.debug("apres book.title")
gc.authenticate()
logging.debug("apres authenticate")
def book_search(q, page=1, search_field='all'):
auth_client = client.GoodreadsClient(key, secret)
books_list = auth_client.search_books(str(q), page, search_field)
return books_list[0].title, books_list[0].average_rating
def authenticate(self):
self.auth_client = client.GoodreadsClient(self._client_key,
self._client_secret)
load_dotenv()
DISCORD_TOKEN = os.getenv('DISCORD_TOKEN')
GOOD_READS_KEY = os.getenv('GOOD_READS_KEY')
GOOD_READS_SECRET = os.getenv('GOOD_READS_SECRET')
FOLLOWERS_LIST_HANDLE = os.getenv('FOLLOWERS_LIST_HANDLE')
HELP_TEXT_TITLE = f'''grdbot: The handsomest D-Bot for accessing GoodReads'''
HELP_TEXT_HEADER = f'''
This is the GoodReads D-bot speaking, thanks for forcing me to be your slave.
Feel free to exploit my labor in other servers, [Invite Link](https://discord.com/api/oauth2/authorize?client_id=753716371992608828&permissions=26624&scope=bot)
I currently respond to the following commands:
'''
good_reads_client = client.GoodreadsClient(GOOD_READS_KEY, GOOD_READS_SECRET)
command_q = commands.CommandQueue(good_reads_client)
discord_client = discord.Client()
follow_manager = FollowManager()
COMMANDS = {
'\\activity': {
'args': ['[username]'],
'description':
'Will return the most recent GoodReads activity for the given user.',
'error': commands.ACTIVITY_COMMAND_ERROR,
'fx': commands.activity_command,
'name': 'activity',
'test': test.run_activity_command_test
},
def get_the_genre(id):
genre_list_found = []
#list of all possible valid genres
genre_list = [
'academia', 'academic', 'adult', 'adventure', 'biography', 'classic',
'classical', 'classics', 'counselling', 'crime', 'fantasy', 'fiction',
'historical', 'horror', 'humor', 'langauge', 'law', 'mystery',
'mystery-thriller', 'non-fiction', 'nonfiction', 'over-18', 'religion',
'romance', 'sci-fi', 'sci-fi-fantasy', 'science', 'science-fiction',
'scifi', 'self-help', 'social', 'thriller', 'tourism', 'travel', 'war',
'young-adult'
]
try:
gc = client.GoodreadsClient(
'UWKOBM9QcXAw8V1TzcI62g',
'XX8aOKqAjebooLjSWK3Rx8gn2MauCjWgy9IGAIEG4')
book = gc.book(id)
shelves_list_raw = book.popular_shelves
shelves_list = [str(val) for val in shelves_list_raw]
#print(shelves_list)
for genre in genre_list:
if (genre in shelves_list):
genre_list_found.append(genre)
#-------clean the genre list-----------------------------
for index in range(len(genre_list_found)):
if (genre_list_found[index] == 'academia'):
genre_list_found[index] = 'academic'
if (genre_list_found[index] == 'classics'):
genre_list_found[index] = 'classic'
if (genre_list_found[index] == 'classical'):
genre_list_found[index] = 'classic'
if (genre_list_found[index] == 'nonfiction'):
genre_list_found[index] = 'non-fiction'
if (genre_list_found[index] == 'scifi'):
genre_list_found[index] = 'sci-fi'
if (genre_list_found[index] == 'science-fiction'):
genre_list_found[index] = 'sci-fi'
if ('mystery-thriller' in genre_list_found):
genre_list_found.pop(genre_list_found.index('mystery-thriller'))
genre_list_found.append('thriller')
genre_list_found.append('mystery')
if ('sci-fi-fantasy' in genre_list_found):
genre_list_found.pop(genre_list_found.index('sci-fi-fantasy'))
genre_list_found.append('sci-fi')
genre_list_found.append('fantasy')
genre_list_found = sorted(genre_list_found)
genre_list_found = list(dict.fromkeys(genre_list_found))
#-------end of clean the genre list-----------------------------
except:
print("There is an error getting genre")
return genre_list_found
import time
import pandas as pd
from goodreads import client
#Settings for data scrapping
restart = False
write = True
classify_count = 25
backup_cycle = 1000
start_index = 250000
#current time, used to track run time.
t0 = time.time()
#initialize client for goodreads
gc = client.GoodreadsClient('fm1h6CpTTcPHEgwUAvOD1w',
'l62WO2kz3lmJifV7VkGZY4SAcWzkjtUw3Unj7zjE')
gc.authenticate('fm1h6CpTTcPHEgwUAvOD1w',
'l62WO2kz3lmJifV7VkGZY4SAcWzkjtUw3Unj7zjE')
#load in datafiles
df = pd.read_csv('Compiled_Data.csv', low_memory=False)
settings = pd.read_csv('Settings.csv', error_bad_lines=False, low_memory=False)
#restart classification data if desired
if restart:
for genre in settings['Genres']:
df[genre] = False
df['Classified'] = False
#pulls data from goodreads website
#starting settings
import os
from goodreads import client
CLIENT = client.GoodreadsClient(
os.environ.get('GOODREADS_KEY'),
os.environ.get('GOODREADS_SECRET'),
)
CLIENT.authenticate(
access_token=os.environ.get('GOODREADS_ACCESS_TOKEN'),
access_token_secret=os.environ.get('GOODREADS_ACCESS_SECRET'),
)
USER = CLIENT.user()
import os
import pickle
from pprint import pprint as pp
import sys
import xml.dom.minidom
import xmltodict
from goodreads import client
from authorize import authorize
CONSUMER_KEY = os.environ.get('GR_KEY')
CONSUMER_SECRET = os.environ.get('GR_SECRET')
SESSION = 'session'
try:
session = pickle.load(open(SESSION, "rb"))
except FileNotFoundError:
session = authorize()
ACCESS_TOKEN = session.access_token
ACCESS_TOKEN_SECRET = session.access_token_secret
gc = client.GoodreadsClient(CONSUMER_KEY, CONSUMER_SECRET)
gc.authenticate(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
resp = session.get("/updates/friends.xml")
#xml_out = xml.dom.minidom.parseString(resp.content)
d = xmltodict.parse(resp.content)
pp(d)