def update_current(self):
data_id = Data.current
data = Data.get_data()
Logger.debug('Update data: {}'.format(data))
data = json.dumps(data)
RestClient.patch(data, '/{}'.format(data_id))
self.get_all()
def add_data(self):
data = Data.get_data()
data['id'] = None # чтобы на сервере id сгенерилось
Logger.debug('Add data: {}'.format(data))
data = json.dumps(data)
RestClient.post(data)
RestClient.get()
def create_client():
global client
params = (config_root.host.value, config_root.port.value,
config_root.user.value, config_root.password.value)
debug("Creating openHAB client: host=%s, port=%d, user=%s, password=%s" %
params)
client = RestClient(*params)
def authenticate_dataforseo():
creds = None
with open("dataforseocreds.json", 'r') as f:
creds = json.load(f)
if creds:
return RestClient(creds["login"], creds["password"])
else:
raise ValueError('No datafroseo credentials.')
class Mapper:
def __init__(self):
self.client = RestClient(LOGIN, PASSWORD)
def save_get_response(self, path):
directory = path.split('/')
filepath = ''
for name in directory:
filepath += f"{name}_"
filepath = filepath[:-1] + '.json'
# get the data
response = json.dumps(self.client.get(path), indent=4)
with open(filepath, 'w') as outfile:
outfile.write(response)
if args.advanced:
fields.extend(['is_image','is_video','is_featured_snippet','is_malicious','is_web_story','amp_version','rating','sitelinks','faq','items','pixels_from_top'])
if args.knowledge_graph:
fields.extend(['sub_title','address','phone'])
# Output name
timestr = time.strftime("%Y%m%d-%H%M%S")
tag = args.output + "-" + timestr
filename = tag + ".csv"
with open(filename,'w',newline='') as file:
writer = csv.DictWriter(file, fieldnames=fields, delimiter=";")
writer.writeheader()
file.close()
client = RestClient(user,password)
# While there are results, request the next batch
next_batch = True
while next_batch:
response = client.get("/v3/serp/google/organic/tasks_ready")
if response['status_code'] == 20000:
tasks_available = response["tasks"][0]["result_count"]
print("{} tasks available".format(tasks_available))
if tasks_available < 1:
next_batch = False
results = []
for task in response['tasks']:
if (task['result'] and (len(task['result']) > 0)):
for resultTaskInfo in task['result']:
if(resultTaskInfo['endpoint_advanced']):
def get_all(self):
RestClient.get()
def del_current(self):
data_id = Data.current
RestClient.delete('/{}'.format(data_id))
self.get_all()
# Output headers
fields = [
'keyword', 'location_code', 'language_code', 'search_partners',
'search_volume', 'cpc', 'competition', 'categories', 'monthly_searches'
]
# Output name
timestr = time.strftime("%Y%m%d-%H%M%S")
tag = args.output + "-" + timestr
filename = tag + ".csv"
with open(filename, 'w', newline='') as file:
writer = csv.DictWriter(file, fieldnames=fields, delimiter=";")
writer.writeheader()
file.close()
client = RestClient(user, password)
# While there are results, request the next batch
next_batch = True
while next_batch:
response = client.get(
"/v3/keywords_data/google/search_volume/tasks_ready")
if response['status_code'] == 20000:
tasks_available = response["tasks"][0]["result_count"]
print("{} tasks available".format(tasks_available))
if tasks_available < 1:
next_batch = False
for task in response["tasks"]:
if (task['result'] and (len(task['result']) > 0)):
for result_task_info in task['result']:
class GetList:
client = RestClient("*****@*****.**", "2iHUO8lhRFD5vqEP")
stop_words = set(stopwords.words("french"))
stop_words_english = set(stopwords.words("english"))
stop_words_multilingual = stop_words.union(stop_words_english)
new_stopwords_list = stop_words_multilingual.union(stop)
def create_request(self, post_data):
response = self.client.post("/v2/live/srp_tasks_post", dict(data=post_data))
if response["status"] == "error":
print("error. Code: %d Message: %s" % (response["error"]["code"], response["error"]["message"]))
return []
else:
return response
def get_results_from_keywords(self, keywords):
rnd = Random() #you can set as "index of post_data" your ID, string, etc. we will return it with all results.
post_data = dict()
post_data[rnd.randint(1, 30000000)] = dict(
se_name="google.fr",
se_language="French",
se_localization= 'fr-fr',
loc_id= 1006094,
key=keywords
)
return self.create_request(post_data)
def get_results_from_taskid(self, taskId):
srp_response = self.client.get("/v2/srp_tasks_get/%d" % (taskId))
if srp_response["status"] == "error":
print("error. Code: %d Message: %s" % (srp_response["error"]["code"], srp_response["error"]["message"]))
return []
else:
return srp_response
def get_results(self, keywords):
allinfo = []
if (type(keywords) is int):
allinfo = self.get_results_from_taskid(keywords)
else:
allinfo = self.get_results_from_keywords(keywords)
return allinfo
def extract_url_from_results(self, data):
url_result = []
for i in data["results"]["organic"]:
url_result.append(i["result_url"])
return url_result
def extract_text_from_url(self, list):
text = []
count = 0
for i in list:
try:
html = requests.get(i).text
#html = urllib.request.urlopen(i, timeout=3).read().decode("utf8")
text.append(get_text(html))
count += 1
except:
print("Error: " + i)
print("Count = ", count)
return text
def normalize_text_list(self, textArray):
corpus = []
for i in range(len(textArray)):
#Remove accents
text = re.sub("'"," ", textArray[i])
text = re.sub('"'," ", text)
# Removes urls
text = re.sub("/(?:(?:https?|ftp|file):\/\/|www\.|ftp\.)(?:\([-A-Z0-9+&@#\/%=~_|$?!:,.]*\)|[-A-Z0-9+&@#\/%=~_|$?!:,.])*(?:\([-A-Z0-9+&@#\/%=~_|$?!:,.]*\)|[A-Z0-9+&@#\/%=~_|$])/igm", " ", text)
#text = str(unicodedata.normalize('NFKD', text).encode('ASCII', 'ignore'))
#Remove Special characters
#text = re.sub('[^a-zA-Z0-9]', ' ', text)
text = re.sub('[^a-zA-Z0-9áéèíóúÁÉÍÓÚâêîôÂÊÎÔãõÃÕçÇû: ]', ' ', text)
#Convert to lowercase
text = text.lower()
#remove tags
text = re.sub("</?.*?>"," <> ",text)
# remove special characters and digits
text=re.sub("(\\d|\\W)+"," ",text)
##Convert to list from string
text = text.split()
##Stemming
#ps=PorterStemmer()
#Lemmatisation
#lem = WordNetLemmatizer()
text = [word for word in text if not word in
self.new_stopwords_list]
text = " ".join(text)
corpus.append(text)
return corpus
def write_corpus_to_file(self,corpus):
with open("corpus.txt", "wb") as fp:
pickle.dump(corpus, fp)
def write_corpus_to_file_from_keywords(self, keywords):
allinfo = self.get_results(keywords)
vim = self.extract_url_from_results(allinfo)
tex = self.extract_text_from_url(vim)
corpus = self.normalize_text_list(tex)
self.write_corpus_to_file(tex)
def write_corpus_to_file_not_normalized_from_keywords(self, keywords):
allinfo = self.get_results(keywords)
vim = self.extract_url_from_results(allinfo)
tex = self.extract_text_from_url(vim)
self.write_corpus_to_file(tex)
def read_corpus_from_file(self, filename):
corpus = []
with open(filename, 'rb') as fp:
corpus = pickle.load(fp)
return corpus
def get_top_n_ygrams_words(self, corpus, n=None, y=1):
vec = CountVectorizer(min_df = 0.1,stop_words=self.new_stopwords_list, max_features=10000, ngram_range=(y,y)).fit(corpus)
bag_of_words = vec.transform(corpus)
sum_words = bag_of_words.sum(axis=0)
words_freq = [(word, sum_words[0, idx]) for word, idx in
vec.vocabulary_.items()]
words_freq =sorted(words_freq, key = lambda x: x[1],
reverse=True)
frame = pd.DataFrame(words_freq[:n])
switcher = {
1: "Monogram",
2: "Bigram",
3: "Trigram",
}
switcherFreq = {
1: "Freq_Mono",
2: "Freq_Bi",
3: "Freq_Tri",
}
frame.columns = [switcher.get(y), switcherFreq.get(y)]
return frame
def get_all_ygrams(self,corpus, monograms, bigrams, trigrams):
mono = self.get_top_n_ygrams_words(corpus, monograms, 1)
bi = self.get_top_n_ygrams_words(corpus, bigrams, 2)
tri = self.get_top_n_ygrams_words(corpus, trigrams, 3)
monodict = mono.to_dict()
bidict = bi.to_dict()
tridict = tri.to_dict()
all = {}
all.update(monodict)
all.update(bidict)
all.update(tridict)
return all
def prepare_corpus(self,doc_clean):
"""
Input : clean document
Purpose: create term dictionary of our courpus and Converting list of documents (corpus) into Document Term Matrix
Output : term dictionary and Document Term Matrix
"""
# Creating the term dictionary of our courpus, where every unique term is assigned an index. dictionary = corpora.Dictionary(doc_clean)
dictionary = corpora.Dictionary(doc_clean)
# Converting list of documents (corpus) into Document Term Matrix using dictionary prepared above.
doc_term_matrix = [dictionary.doc2bow(doc) for doc in doc_clean]
# generate LDA model
return dictionary,doc_term_matrix
def create_gensim_lsa_model(self,doc_clean,number_of_topics,words):
"""
Input : clean document, number of topics and number of words associated with each topic
Purpose: create LSA model using gensim
Output : return LSA model
"""
dictionary,doc_term_matrix=self.prepare_corpus(doc_clean)
# generate LSA model
lsamodel = LsiModel(doc_term_matrix, num_topics=number_of_topics, id2word = dictionary) # train model
print(lsamodel.print_topics(num_topics=number_of_topics, num_words=words))
return lsamodel
def compute_coherence_values(self,dictionary, doc_term_matrix, doc_clean, stop, start=2, step=3):
"""
Input : dictionary : Gensim dictionary
corpus : Gensim corpus
texts : List of input texts
stop : Max num of topics
purpose : Compute c_v coherence for various number of topics
Output : model_list : List of LSA topic models
coherence_values : Coherence values corresponding to the LDA model with respective number of topics
"""
coherence_values = []
model_list = []
for num_topics in range(start, stop, step):
# generate LSA model
print("Number of topics: ", num_topics)
model = LsiModel(doc_term_matrix, num_topics=num_topics, id2word = dictionary) # train model
model_list.append(model)
coherencemodel = CoherenceModel(model=model, texts=doc_clean, dictionary=dictionary, coherence='c_v')
coherenceSS = coherencemodel.get_coherence()
coherence_values.append(coherenceSS)
return model_list, coherence_values
def plot_graph(self, doc_clean,start, stop, step):
dictionary,doc_term_matrix=self.prepare_corpus(doc_clean)
model_list, coherence_values = self.compute_coherence_values(dictionary, doc_term_matrix,doc_clean,
stop, start, step)
# Show graph
x = range(start, stop, step)
for i in range(len(coherence_values)):
if float(coherence_values[i]) > float("0.4"):
print(coherence_values[i])
plt.plot(x, coherence_values)
plt.xlabel("Number of Topics")
plt.ylabel("Coherence score")
plt.legend(("coherence_values"), loc='best')
plt.show()
def calculate_optimal_coherence_value(self, doc_clean, start, stop, step):
dictionary,doc_term_matrix=self.prepare_corpus(doc_clean)
model_list, coherence_values = self.compute_coherence_values(dictionary, doc_term_matrix,doc_clean,
stop, start, step)
max = 0
topics = 0
for i in range(len(coherence_values)):
if float(coherence_values[i]) > float("0.35"):
if coherence_values[i] > max:
topics = i
print(coherence_values[i])
return topics
def generate_optimal_topic(self, doc_clean, start, stop, step):
topics = self.calculate_optimal_coherence_value(doc_clean, start, stop, step)
print(self.create_gensim_lsa_model(doc_clean,topics,3))
def corpus_to_gensim(self,corpus):
gensim = []
for i in corpus:
token = i.split()
gensim.append(token)
return gensim
def generate_results(self, keywords):
allinfo = self.get_results(keywords)
vim = self.extract_url_from_results(allinfo)
tex = self.extract_text_from_url(vim)
corpus = self.normalize_text_list(tex)
gensim = self.corpus_to_gensim(corpus)
#model = self.create_gensim_lsa_model(gensim,10,3)
start,stop,step = 2,10,1
#self.plot_graph(gensim,start,stop,step)
self.generate_optimal_topic(gensim,start,stop,step)
results = self.get_all_ygrams(corpus, 40, 20, 10)
print(results)
return results
def generate_results_from_file(self, filename):
corpus = self.read_corpus_from_file(filename)
corpus = self.normalize_text_list(corpus)
gensim = self.corpus_to_gensim(corpus)
#model = self.create_gensim_lsa_model(gensim,10,3)
start,stop,step = 2,10,1
self.generate_optimal_topic(gensim,start,stop,step)
results = self.get_all_ygrams(corpus, 100, 40, 10)
print(results)
return 1
def generate_results_from_url(self, url):
rscraper = RecursiveScraper(url)
rscraper.scrape()
rscraper.urls
tex = self.extract_text_from_url(rscraper.urls)
corpus = self.normalize_text_list(tex)
gensim = self.corpus_to_gensim(corpus)
#model = self.create_gensim_lsa_model(gensim,10,3)
start,stop,step = 2,10,1
self.generate_optimal_topic(gensim,start,stop,step)
results = self.get_all_ygrams(corpus, 40, 20, 10)
print(results)
return results
def __init__(self):
self.client = RestClient(LOGIN, PASSWORD)
from client import RestClient
import json, logging, requests, random
client = RestClient('*****@*****.**', 'LD87rm8Od9dfWnVn')
# Search class has modules for different functions
class Search():
# https://docs.dataforseo.com/#get-related-keywords
def keywords_related(self, word, location):
rnd = random.Random() #you can set as "index of post_data" your ID, string, etc. we will return it with all results.
post_data = dict()
post_data[rnd.randint(1, 30000000)] = dict(
keyword=word,
country_code=location,
language="en",
depth=1,
limit=2,
offset=0,
orderby="cpc,desc",
filters=[
["cpc", ">", 0],
"or",
[
["search_volume", ">", 0],
"and",
["search_volume", "<=", 1000]
]
]
)
# Output name
timestr = time.strftime("%Y%m%d-%H%M%S")
tag = args.output + "-" + timestr
filename = tag + ".csv"
conf = configparser.ConfigParser()
conf.read(args.config)
user = conf['general']['user']
password = conf['general']['password']
with open(filename, 'w', newline='') as file:
writer = csv.DictWriter(file, fieldnames=fields, delimiter=args.sep)
writer.writeheader()
file.close()
client = RestClient(user, password)
i = 0
j = args.batch
# Cut the kws list in batches
while j < len(kws) + args.batch:
post_data = {}
post_data[len(post_data)] = dict(
language_code=args.language_code,
location_code=args.location_code,
keywords=kws[i:j],
tag=tag,
)
response = client.post(
"/v3/keywords_data/google/search_volume/task_post", post_data)
# Set priority queue
priority = {0: 0, 'low': 1, 'high': 2}
priority = priority[args.priority]
conf = configparser.ConfigParser()
conf.read(args.config)
user = conf['general']['user']
password = conf['general']['password']
# Send requests
with open(filename, 'w', newline='') as file:
writer = csv.DictWriter(file, fieldnames=fields, delimiter=args.sep)
writer.writeheader()
client = RestClient(user, password)
# We need to send batches of max 100 tasks
i = 0
j = args.batch
# Cut the kws list in batches
while j < len(kws) + args.batch:
post_data = dict()
for kw in kws[i:j]:
post_data[len(post_data)] = dict(
language_code=args.language_code,
location_code=args.location_code,
keyword=kw,
priority=priority,
depth=args.nb_results,
##
## Shows number of tasks ready for download.
####
import configparser
import argparse
from client import RestClient
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--config',
default="config.ini",
type=str,
help='Global config file (default: "config.ini")')
args = parser.parse_args()
conf = configparser.ConfigParser()
conf.read(args.config)
user = conf['general']['user']
password = conf['general']['password']
client = RestClient(user, password)
response = client.get("/v3/keywords_data/google/search_volume/tasks_ready")
if response["status_code"] == 20000:
tasks_available = response["tasks"][0]["result_count"]
print("{} tasks available".format(tasks_available))
else:
print("error. Code: %d Message: %s" %
(response["status_code"], response["status_message"]))
####
## DATAFORSEO SERPS API
##
## Shows number of tasks ready for download
####
import configparser
import argparse
from client import RestClient
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--config', default="config.ini",
type=str, help='Global config file (default: "config.ini")')
args = parser.parse_args()
conf = configparser.ConfigParser()
conf.read(args.config)
user = conf['general']['user']
password = conf['general']['password']
client = RestClient(user,password)
response = client.get("/v3/serp/google/organic/tasks_ready")
if response["status_code"] == 20000:
tasks_available = response["tasks"][0]["result_count"]
print("{} tasks available".format(tasks_available))
else:
print("error. Code: %d Message: %s" % (response["status_code"], response["status_message"]))