def get_news():
r = []
gn = GoogleNews(lang=NEWS_LANG, country=NEWS_COUNTRY)
for s in NEWS_SEARCHES:
search = gn.search(s, when=NEWS_PERIOD)
r += search.get('entries')
print(r[0])
import time
time.sleep(100)
return r
def getNewsClimate(max_articles=20):
gn = GoogleNews(lang='en', country='US')
climate_news = gn.topic_headlines('CAAqBwgKMKeh0wEw-sE1')
search = climate_news['entries'][:max_articles]
rtn = {}
for i in range(len(search)):
rtn[i] = {
'title': search[i].title,
'href': search[i]['links'][0]['href']
}
return rtn
def getNews(query, max_articles=20, time_period='1m'):
gn = GoogleNews(lang='en', country='US')
search = gn.search(query, when=time_period)
search = search['entries'][:max_articles]
rtn = {}
for i in range(len(search)):
rtn[i] = {
'title': search[i].title,
'href': search[i]['links'][0]['href']
}
return rtn
def get_articles(lang, country, number_articles):
gn = GoogleNews(lang.lower(), country.upper())
gn.BASE_URL = gn.BASE_URL + "?hl={}&gl={}".format(gn.lang, gn.country)
top_news = gn.top_news()
entries = top_news["entries"]
if number_articles < len(entries):
entries = entries[:number_articles]
return entries
def main():
print("hello world")
gn = GoogleNews()
top = gn.top_news()
for i in range(10):
print(top['entries'][i])
return 0
def handle_news_request(irc: IRC, nick: str, target: str,
message: IRCMessage) -> None:
"""Handle a news request."""
words = message.message.replace("{}:".format(nick), "").strip().split()
if len(words) < 3:
irc.send_message(target, "Bad command. See help message")
return
command = words[0]
country = words[1]
language = words[2]
parameter = " ".join(words[3:])
logger.info("Handling news request. Command=%s, country=%s, language=%s",
command, country, language)
google_news = GoogleNews(country=country, lang=language)
try:
if command == "topic":
handle_topic(irc, google_news, target, parameter)
elif command == "location":
handle_location(irc, google_news, target, parameter)
elif command == "search":
handle_search(irc, google_news, target, parameter)
elif command == "top":
handle_top(irc, google_news, target)
else:
irc.send_message(target, "I don't recognize that command")
except Exception: # pylint: disable=broad-except
logger.error("Unable to fetch news", exc_info=True)
irc.send_message(target, "I was unable to fetch news")
def handle_top(irc: IRC, google_news: GoogleNews, target: str) -> None:
"""Handle a search request."""
irc.send_message(target, "Working on it")
logger.info("Fetching top news")
news = google_news.top_news()
for entry in news["entries"][:5]:
irc.send_message(target, entry["title"])
def handle_search(irc: IRC, google_news: GoogleNews, target: str,
query: str) -> None:
"""Handle a search request."""
irc.send_message(target, "Working on it")
logger.info("Fetching news for query %s", query)
news = google_news.search(query)
for entry in news["entries"][:5]:
irc.send_message(target, entry["title"])
def handle_location(irc: IRC, google_news: GoogleNews, target: str,
location: str) -> None:
"""Handle a location request."""
irc.send_message(target, "Working on it")
logger.info("Fetching news for location %s", location)
news = google_news.geo_headlines(location)
for entry in news["entries"][:5]:
irc.send_message(target, entry["title"])
def get_news(self):
## get google news from player
gn = GoogleNews()
keys = str(
str(self.data_player.iloc[0, :]['info_lastname'] + ' ' +
str(self.player_team) + ' football'))
search = gn.search(keys)
news = pd.DataFrame(search['entries'])
news['Date'] = news['published_parsed'].apply(lambda x: str(
x.tm_mday) + '/' + str(x.tm_mon) + '/' + str(x.tm_year))
news = news[['Date', 'title', 'link']].head(30)
news = news.rename(columns={'title': 'Title', 'link': 'Link'})
table = news.to_dict('records')
columns = [{"name": i, "id": i} for i in news.columns]
# table = mf.MyFormating().table_news_player(news)
return table, columns
def scrape_google_news(self, company_name, start_date, end_date, bodies):
try:
gn = GoogleNews(lang=self.language, country='US')
news_entries = gn.search(company_name,
helper=True,
when=None,
from_=start_date,
to_=end_date,
proxies=None,
scraping_bee=None)
DATE_SLICE = slice(0, 16)
if bodies:
return [{
"headline":
entry['title'],
"body":
BeautifulSoup(entry['summary'], "html.parser").get_text(),
"source":
entry['link'],
"published_date":
format_date(entry['published'][DATE_SLICE],
to_datetime=True,
current_format='%a, %d %b %Y'),
"company_name":
company_name
} for entry in news_entries['entries']]
return [{
"headline":
entry['title'],
"source":
entry['link'],
"published_date":
format_date(entry['published'][DATE_SLICE],
to_datetime=True,
current_format='%a, %d %b %Y'),
"company_name":
company_name
} for entry in news_entries['entries']]
except Exception as e:
abort(400, e)
class NewsSpider(scrapy.Spider):
name = 'news'
# Получение списка ссылок на новости при помощи модуля GoogleNews
gn = GoogleNews(lang='en', country='US')
s = gn.search('Russia', from_='2020-10-08', to_='2020-11-08')
links = []
for x in range(0, 100):
links.append(s['entries'][x]['link'])
start_urls = links
def parse(self, response):
with open('News.txt', 'a') as file:
file.write(str(response.css('p::text').getall()))
def news_sentiment_analysis(word, n): #query, num articles
titles = []
keywords = []
polarities = []
subjectivities = []
links = []
texts = []
gn = GoogleNews(lang='en', country='US')
s = gn.search(word)
i = 0
for article in s['entries']:
if i >= n:
break
try:
a = Article(url=article['link'])
a.download()
a.parse()
titles.append(article['title'])
links.append(article['link'])
texts.append(a.text)
a.nlp()
keywords.append(a.keywords)
analysis = TextBlob(a.text)
polarities.append(analysis.sentiment.polarity)
subjectivities.append(analysis.sentiment.subjectivity)
except:
continue
i += 1
di = {
'title': titles,
'text': texts,
'keywords': keywords,
'polarity': polarities,
'subjectivity': subjectivities
}
return pd.DataFrame.from_dict(di)
def extract_news_data(company: str, ds: str, next_ds: str,
**kwargs: dict) -> str:
directory, file = f'{LOCAL_STORAGE}/google_news/{company}', f'{ds}.json'
# Create directory in case it does not already exist
path = Path(directory)
path.mkdir(parents=True, exist_ok=True)
# Download data
google_news_data = GoogleNews().search(query=company,
from_=ds,
to_=next_ds)
# Write data to storage in json format
full_path = path.joinpath(file)
with open(full_path, 'w') as fp:
json.dump(google_news_data, fp)
return str(full_path)
class API:
def __init__(self, terms, lang, country):
self.terms = terms
self.client = GoogleNews(lang, country)
@staticmethod
def format(x):
try:
return unidecode(x['title'])
except KeyError:
return ''
def __call__(self, from_, to_):
results = []
for q in self.terms:
results += self.client.search(query=q, from_=from_,
to_=to_)['entries']
return list(set(API.format(r) for r in results))
def handle_topic(irc: IRC, google_news: GoogleNews, target: str,
topic: str) -> None:
"""Handle a topic request."""
irc.send_message(target, "Working on it")
logger.info("Fetching news for topic %s", topic)
try:
news = google_news.topic_headlines(topic)
for entry in news["entries"][:5]:
irc.send_message(target, entry["title"])
except Exception as exception: # pylint: disable=broad-except
if str(exception) == "unsupported topic":
# See: https://github.com/kotartemiy/pygooglenews#stories-by-topic-1
irc.send_message(
target, "That topic is not supported. Supported topics are:")
irc.send_message(
target,
"world, nation, business, technology, entertainment, science, sports, health"
)
else:
raise exception
from pygooglenews import GoogleNews
import streamlit as st
import pandas as pd
f'''
-----------------------------------
# Google News Feed Searcher
-----------------------------------
'''
gn = GoogleNews()
search_term = st.text_input('Search Term:', 'Trump')
search_range = st.slider('Search Range (days):', 1, 365, 1)
search = gn.search(search_term, when=f'{search_range}d')
data = pd.DataFrame.from_dict(search['entries'])
f'''
# {search_term} News Articles
Last *{search_range} day/s*
-------------------------------------------
'''
# Display articles found
for row in range(1, data.shape[1]):
f'''
## {data['published'].iloc[row]}
### {data['title'].iloc[row]}
plt.figure(figsize=(8, ))
for i in range(n_classes):
plt.plot(fpr[i], tpr[i], label='ROC curve of {0} (area = {1:0.9f})'
''.format(category_id_df[category_id_df['category_id'] == i].Category, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.legend(loc="lower right")
plt.show()
pip install pygooglenews
from pygooglenews import GoogleNews
# default GoogleNews instance
gn = GoogleNews(lang = 'en', country = 'US')
business = gn.topic_headlines('BUSINESS', proxies=None, scraping_bee = None)
pip install newsapi-python
from newsapi import NewsApiClient
api = NewsApiClient(api_key='b1b6e4269a814e8bbe8a477b3226e918')
business = api.get_top_headlines(category = 'business', language = 'en', country='us')
sport = api.get_top_headlines(category = 'sports', language = 'en', country='us')
enter = api.get_top_headlines(category = 'entertainment', language = 'en', country='us')
def _get_api(self):
return GoogleNews()
from pygooglenews import GoogleNews
import time
from linkpreview import link_preview
import os
import django
gn = GoogleNews(lang='ar')
keyword_results = gn.search('أندرويد')
data = keyword_results['entries']
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'news_feed.settings')
django.setup()
from articles.models import article as classy
all_news = []
test_counter = 0
for i in data:
try:
preview = link_preview(i.link)
components = {'title': i.title, 'link': i.link, 'image': preview.image}
if str(components['image']) == 'None':
pass
else:
new_data = classy(title=components['title'],
link=components['link'],
image=components['image'])
new_data.save()
print('\n')
from pygooglenews import GoogleNews
gn = GoogleNews(lang='pt')
top = gn.top_news()
for item in top['entries']:
print(item.title)
objConfig = Config()
objConfig.browser_user_agent = strUserAgent
objEngine = create_engine('', echo=False)
objSession = sessionmaker(bind=objEngine)()
objToday = datetime.date.today()
objYesterday = objToday - datetime.timedelta(days=2)
strToday = objToday.strftime("%Y-%m-%d")
strYesterday = objYesterday.strftime("%Y-%m-%d")
proxyDict = None
objWPClient = WPClient()
print("Obtaining news")
objGnews = GoogleNews(lang='en', country='pk')
objSearch = objGnews.search('education school university pakistan',
proxies=proxyDict,
from_=strYesterday,
to_=strToday)
arrResults = objSearch['entries']
for dictResult in arrResults:
dictResult['published'] = dateparser.parse(dictResult['published']).date()
print("Obtained news: {0} items".format(len(arrResults)))
arrKeywords = [
"school", "education", "school", "university", "class", "grade",
"kindergarten", "student", "institute"
]
Default accepted topics are:
world, nation, business, technology, entertainment
science, sports, health
"""
from pygooglenews import GoogleNews
import smtplib
from datetime import datetime
from pytz import timezone
from email.mime.text import MIMEText
# Initiate Google News class to get access to all functions
gn = GoogleNews(lang='en', country='CA')
# For time conversion crap
mountain = timezone('America/Edmonton')
gmt = timezone('GMT')
# Initialize other vars
email_message = ''
# Some helpful functions
def print_titles(results):
for x in results['entries']:
print('\n' + x['title'])
print('\n')
"Sandro Alex","Sargento Fahur","Sebastião Oliveira","Sérgio Brito","Sergio Souza","Sérgio Toledo",
"Sérgio Vidigal","Severino Pessôa","Shéridan","Sidney Leite","Silas Câmara","Silvia Cristina",
"Sílvio Costa Filho","Soraya Santos","Sóstenes Cavalcanti","Stefano Aguiar","Subtenente Gonzaga",
"Tabata Amaral","Tadeu Alencar","Talíria Petrone","Tereza Cristina","Tereza Nelma","Tiago Dimas",
"Tiago Mitraud","Tiririca","Tito","Toninho Wandscheer","Túlio Gadêlha","Uldurico Júnior",
"Vaidon Oliveira","Valdevan Noventa","Valmir Assunção","Vanda Milani","Vander Loubet","Vanderlei Macris",
"Vavá Martins","Vermelho","Vicentinho","Vicentinho Júnior","Vilson da FETAEMG","Vinicius Carvalho",
"Vinícius Farah","Vinícius Gurgel","Vinicius Poit","Vitor Hugo","Vítor Lippi","Wagner Montes",
"Waldenor Pereira","Walter Alves","Weliton Prado","Wellington Roberto","Wilson Santiago",
"Wladimir Garotinho","Wolney Queiroz","Zé Carlos","Zé Mário","Zé Neto","Zé Silva","Zé Vitor","Zeca Dirceu"]
from pandas import DataFrame
from pygooglenews import GoogleNews
gn = GoogleNews(lang = 'pt', country = 'BR')
top = gn.top_news()
news = []
contagem = 0
for dep in range(len(deputados_manchetes)):
s = gn.search('intitle:{}'.format(deputados_manchetes[dep]), when = '336h')
for x in range(len(s.get('entries'))):
news.append([deputados_manchetes[dep], s.get('entries')[x].get('title'),s.get('entries')[x].get('link'),s.get('entries')[x].get('published'),
s.get('entries')[x].get('source').get('href'),s.get('entries')[x].get('source').get('title')])
contagem += 1
print(contagem)
f_issue = open(Issue_counter_filename, "r")
var_issue_counter = int(f_issue.readline())
f_issue.close()
var_issue_counter += 1
f_issue = open(Issue_counter_filename, "w")
f_issue.write(str(var_issue_counter))
f_issue.close()
else:
var_issue_counter = 1
f_issue = open(Issue_counter_filename, "w")
f_issue.write(str(var_issue_counter))
f_issue.close()
issue_counter_flg=1
today = date.today()
issue_date = today.strftime("%B %d %Y")
gn = GoogleNews(lang='en', country='IN')
covid_news = gn.topic_headlines('CAAqIggKIhxDQkFTRHdvSkwyMHZNREZqY0hsNUVnSmxiaWdBUAE')
covid_news_local=gn.search(f'coronavirus {loc}')
f_more = open(more_stories_filename, encoding='utf-8', mode="a")
f_more.write('<!DOCTYPE html>')
f_more.write('<html>')
f_more.write('<body>')
f = open(html_filename, encoding='utf-8', mode="a")
f.write('<!DOCTYPE html>')
f.write('<html>')
f.write('<body>')
f.write('<div>')
cover_image_idx=np.random.randint(0,7)
cover_image=coverpic_li[cover_image_idx]
f.write(f'<img src={cover_image} width="1000" height="400">')
f.write(
def __init__(self, terms, lang, country):
self.terms = terms
self.client = GoogleNews(lang, country)
def execute_interview_request(ir_object):
LOGGER.info(
f'[tag:INTRUNTER10] tasks.execute_interview_request: received execute request for ir_id: {ir_object.id}'
)
alphabet_list = ['A', 'B', 'C', 'D', 'E', 'F']
tag_dict = {
'funding': {
'keywords': [
'funding', 'investor', 'valuation', 'term sheet',
'venture capital', 'venture debt'
],
'mail_tag_line':
'Type {}: Funding'
},
'acquisition': {
'keywords': ['acquisition', 'acquired'],
'mail_tag_line': 'Type {}: Acquisition'
},
'collabaration': {
'keywords': ['collabarate', 'collabaration'],
'mail_tag_line': 'Type {}: Collabaration'
},
'social good': {
'keywords': ['donate'],
'mail_tag_line': 'Type {}: Strategic initiative'
},
'covid': {
'keywords': ['covid'],
'mail_tag_line': 'Type {}: Covid'
},
}
# ir_object = InterviewRequest.objects.get(id=ir_id)
irr_object = get_object_or_None(InterviewRequestResult,
type_form_id=ir_object.type_form_id,
interview_request_id=ir_object.id,
company_id=ir_object.company.id,
user=ir_object.user.id)
if not irr_object:
irr_object = InterviewRequestResult(
type_form_id=ir_object.type_form_id,
is_published=False,
interview_request_id=ir_object.id,
company_id=ir_object.company.id,
user_id=ir_object.user.id,
)
irr_object.save()
user_name = ir_object.user.first_name
company_name = ir_object.company.name
result_data = dict()
try:
post_log("Getting news from google", 'STARTED')
attachment_file_list = []
user_tag_list = []
from pygooglenews import GoogleNews
gn = GoogleNews()
s = gn.search(company_name.lower())
final_data = []
for news in s['entries']:
new_dict = {
'title': news['title'],
'link': news['link'],
'published': news['published']
}
summary_texts = []
tags = []
try:
soup = BeautifulSoup(
requests.get(news['link'], timeout=300).content,
"html.parser")
for p in soup.findAll('p'):
# print(p.text)
dummy_text = p.text
tags.extend(get_tag(dummy_text))
if "“" in dummy_text:
summary_texts.append(dummy_text)
# break
if summary_texts:
new_dict['summary'] = summary_texts
new_dict['tags'] = list(set(tags))
user_tag_list.extend(new_dict['tags'])
final_data.append(new_dict)
except Exception as e:
print(f"{e} : {news}")
result_data['news_data'] = final_data
user_email = ir_object.user.email
post_log(f"Getting news from google for {user_email}", 'COMPLETED')
# creating a Dataframe object
news_df = pd.DataFrame(final_data)
news_df['Date'] = pd.to_datetime(news_df['published'], errors='coerce')
news_df.sort_values(by=['Date'], inplace=True, ascending=False)
del news_df['Date']
file_name = f'{company_name}_Scrapped News.csv'
news_df.to_csv(f'{DEFAULT_PATH}/{file_name}')
post_log(f"File creation for the scrapped news for {user_email}",
'COMPLETED')
attachment_file_list.append(file_name)
google_play_app_id = ir_object.company.google_play_app_id
if google_play_app_id:
post_log(f"Srapping reviews for the app for {user_email}",
'STARTED')
result = reviews_all(
google_play_app_id,
sleep_milliseconds=0, # defaults to 0
lang='en', # defaults to 'en'
country='us', # defaults to 'us'
sort=Sort.NEWEST # defaults to Sort.MOST_RELEVANT
# filter_score_with=5 # defaults to None(means all score)
)
post_log(f"Srapping reviews for the app for {user_email}",
'COMPLETED')
df = pd.DataFrame(result)
# df = pd.read_csv('{DEFAULT_PATH}/Netflix_all_reviews.csv')
# print(df.head())
# Product Scores
# post_log(f"Histogram creation for the app reviews for {user_email}", 'STARTED')
# fig = px.histogram(df, x="score")
# fig.update_traces(marker_color="turquoise", marker_line_color='rgb(8,48,107)',
# marker_line_width=1.5)
# fig.update_layout(title_text='Product Score')
# HTML(fig.to_html())
# fig.write_image(f"{DEFAULT_PATH}/{company_name}_playstore_ratings.png")
# plt.show()
# plt.savefig(f'{DEFAULT_PATH}/{company_name}_playstore_ratings.png')
# attachment_file_list.append(f"{company_name}_playstore_ratings.png")
# post_log(f"Histogram creation for the app reviews for {user_email}", 'COMPLETED')
reviews_df = df
# reviews_df["review"] = reviews_df["content"].apply(lambda x: x.replace("No Negative", "").replace("No Positive", ""))
reviews_df["is_bad_review"] = reviews_df["score"].apply(
lambda x: 1 if x < 3 else 0)
# select only relevant columnss
reviews_df = reviews_df[[
"content", "reviewCreatedVersion", "at", "is_bad_review"
]]
# reviews_df.head()
reviews_df["review"] = reviews_df["content"]
# reviews_df
post_log(f"Sentiment analysis for {user_email}", 'STARTED')
# return the wordnet object value corresponding to the POS tag
# clean text data
reviews_df["review_clean"] = reviews_df["review"].apply(
lambda x: clean_text(x))
# add sentiment anaylsis columns
sid = SentimentIntensityAnalyzer()
reviews_df["sentiments"] = reviews_df["review"].apply(
lambda x: sid.polarity_scores(str(x)))
reviews_df = pd.concat([
reviews_df.drop(['sentiments'], axis=1),
reviews_df['sentiments'].apply(pd.Series)
],
axis=1)
# add number of characters column
reviews_df["nb_chars"] = reviews_df["review"].apply(
lambda x: len(str(x)))
# add number of words column
reviews_df["nb_words"] = reviews_df["review"].apply(
lambda x: len(str(x).split(" ")))
# create doc2vec vector columns
documents = [
TaggedDocument(doc, [i])
for i, doc in enumerate(reviews_df["review_clean"].apply(
lambda x: str(x).split(" ")))
]
# train a Doc2Vec model with our text data
model = Doc2Vec(documents,
vector_size=5,
window=2,
min_count=1,
workers=4)
# transform each document into a vector data
doc2vec_df = reviews_df["review_clean"].apply(
lambda x: model.infer_vector(str(x).split(" "))).apply(
pd.Series)
doc2vec_df.columns = [
"doc2vec_vector_" + str(x) for x in doc2vec_df.columns
]
reviews_df = pd.concat([reviews_df, doc2vec_df], axis=1)
# add tf-idfs columns
tfidf = TfidfVectorizer(min_df=10)
tfidf_result = tfidf.fit_transform(
reviews_df["review_clean"]).toarray()
tfidf_df = pd.DataFrame(tfidf_result,
columns=tfidf.get_feature_names())
tfidf_df.columns = ["word_" + str(x) for x in tfidf_df.columns]
tfidf_df.index = reviews_df.index
reviews_df = pd.concat([reviews_df, tfidf_df], axis=1)
# show is_bad_review distribution
# reviews_df["sentiment"].value_counts(normalize = True)
post_log(f"Sentiment analysis for {user_name}", 'COMPLETED')
# print wordcloud
post_log(f"Creating word cloud for {user_name}", 'STARTED')
wc_name = show_wordcloud(reviews_df["review"], company_name)
attachment_file_list.append(wc_name)
post_log(f"Creating word cloud for {user_name}", 'COMPLETED')
# highest positive sentiment reviews (with more than 5 words)
reviews_df[reviews_df["nb_words"] >= 5].sort_values(
"pos", ascending=False)[["review", "pos"]].head(10)
# show is_bad_review distribution
reviews_df["is_bad_review"].value_counts(normalize=True)
# lowest negative sentiment reviews (with more than 5 words)
post_log(f"Creating negative reviews csv for {user_name}",
'STARTED')
negative_df = reviews_df[reviews_df["nb_words"] >= 5].sort_values(
"neg", ascending=False)[["content", "neg"]].head(50)
negative_df.to_csv(
f'{DEFAULT_PATH}/{company_name}_negative_reviews.csv',
columns=["content"])
attachment_file_list.append(f'{company_name}_negative_reviews.csv')
negative_reviews_data = negative_df.to_json(orient="split")
parsed = json.loads(negative_reviews_data)
result_data['negative_reviews'] = parsed
post_log(f"Creating negative reviews csv for {user_name}",
'COMPLETED')
else:
attachment_file_list.extend(
['app_playstore.png', 'app_word_cloud.png'])
# gbrowniepoint
post_log(f"Creation of email body for {user_name}", 'STARTED')
# Set Global Variables
gmail_user = '******'
gmail_password = GMAIL_PASSWORD
fromaddr = "*****@*****.**"
toaddr = "*****@*****.**"
# instance of MIMEMultipart
msg = MIMEMultipart()
# storing the senders email address
msg['From'] = fromaddr
# storing the receivers email address
msg['To'] = toaddr
# storing the subject
msg['Subject'] = f"Interview Brownie : {user_name}'s report"
# string to store the body of the mail
body = f'''
<p>Hi {user_name},</p>
<div dir="ltr"><br />Here is your report<br /><br /><strong><u>1. PR synthesis</u></strong> <br /><br />
'''
# print(f'body before adding tags : {body}')
# print(user_tag_list)
for index, tag in enumerate(list(set(user_tag_list))):
tag_data = get_first_tag_quotes(tag, final_data)
type_str = tag_dict[tag]['mail_tag_line'].format(
alphabet_list[index])
summary = '<br />'.join(map(str, tag_data["summary"]))
body = body + f'<u>{type_str}</u><br /><br />Quote:<br /> “{summary}<br />Source: <a href="{tag_data["link"]}" target="_blank">{tag_data["title"]}</a><br /><br />'
# print(f'body after adding tags : {body}')
body = body + f'''
<p><strong><u><em>How do you use these insights in your interview?<br /></em></u></strong><br />
Interviewer - Do you have any questions for us?<br />{user_name} - Yes, I read about the launch of ASAP - how do people get assigned to such projects internally?<br /><br />
From Type A.<br /><br />Another one,<br />{user_name} - I also read about the platform for data collaboration for covid - amazing to see the pace of execution on that one, how is that going?<br /><br />
From type B<br /><br />{user_name} - There were 40 million raised for the clinical analysis, do we raise money for specific projects / verticals or was this a covid specific development?<br /><br />
From type C.<br /><br />Now remember, these are just examples and you should be able to come up with genuine talking points, questions, things that you can relate to now with minimal effort of going through the links <br /><br />You can also find a consolidated list of all public mentions of {company_name} in the past year attached.<br /><u></u></p><div dir="ltr"> </div>
'''
if google_play_app_id:
body = body + f'''<div dir="ltr"><strong><u>2. End user understanding</u></strong></div>
<ul>
<li>A significant chunk of the bad ratings of the app are generic bad reviews, investing in talking to these consumers might uncover issues yet unknown</li>
<li>1 peculiar thing was the mention of cbse in a cluster of reviews, the CBSE learning experience might have some issues in particular</li>
</ul>
</div>
<div>This is a word cloud from all the positive reviews,<br />
<br><img src="cid:1"><br>
<ul>
<li>The trend of generic reviews continues here as well, 1 suggestion could be to request reviewers to write a few lines describing what they loved about their experience</li>
</ul>
<div>Thanks for trying out the beta, please feel free to revert with any questions, suggestions/ feedback etc and it will be super helpful to us if you can share this in your network - a linkedin post talking about your experience will help us reach more people<br /><br />If you don't have anything to ask or say, please revert with your rating on 5 on how useful did you find this tool, it will help us gauge it's efficacy <br /><br />Cheers,</div>
</div>
<p>--</p>
<div dir="ltr" data-smartmail="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div>Gaurav Dagde and Gagan Gehani</div>
</div>
</div>
</div>
</div>
</div>
</div>'''
else:
body = body + f'''
<div><strong><u>2. End user understanding<br /></u></strong></div>
<div><br />Playstore reviews - Our system couldn't find {company_name} app on the playstore.
Nonetheless, I am attaching screenshots of the output of another beta tester to give you a taste of what you can expect from this section</div>
<br><img src="cid:0"><br>
<br><img src="cid:1"><br>
<p>If you don't have anything to ask or say, please revert with your rating on 5 on how useful did you find this tool, it will help us gauge it's efficacy
<br /><br />All the best for your interview!</p>
<div>Thanks for trying out the beta, please feel free to revert with any questions, suggestions/ feedback etc and it will be super helpful to us if you can share this in your network - a linkedin post talking about your experience will help us reach more people<br /><br />If you don't have anything to ask or say, please revert with your rating on 5 on how useful did you find this tool, it will help us gauge it's efficacy <br /><br />Cheers,</div>
</div>
<p>--</p>
<div dir="ltr" data-smartmail="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div>Gaurav Dagde and Gagan Gehani</div>
</div>
</div>
</div>
</div>
</div>
</div
'''
result_data['mail_body'] = body
# attach the body with the msg instance
msg.attach(MIMEText(body, 'html', 'utf-8'))
# file_list = ['ps_image.png',file_name]
img_count = 0
for attach_file in attachment_file_list:
# open the file to be sent
# filename = file_name
attachment = open(f'/app/mail_content/{attach_file}', "rb")
# to add an attachment is just add a MIMEBase object to read a picture locally.
post_log(f"filename : {attach_file}", "IN_PROGRESS")
if '.png' in attach_file:
# post_log(f"In PNG block", "IN_PROGRESS")
# with open(f'/app/mail_content/{attach_file}', 'rb') as attachment:
# set attachment mime and file name, the image type is png
mime = MIMEBase('image', 'png', filename=attach_file)
# add required header data:
mime.add_header('Content-Disposition',
'attachment',
filename=attach_file)
mime.add_header('X-Attachment-Id', '{}'.format(img_count))
mime.add_header('Content-ID', '<{}>'.format(img_count))
# read attachment file content into the MIMEBase object
mime.set_payload(attachment.read())
# encode with base64
encoders.encode_base64(mime)
# add MIMEBase object to MIMEMultipart object
msg.attach(mime)
img_count += 1
else:
# post_log(f"In else block", "IN_PROGRESS")
# instance of MIMEBase and named as p
p = MIMEBase('application', 'octet-stream')
# To change the payload into encoded form
p.set_payload(attachment.read())
# encode into base64
encoders.encode_base64(p)
p.add_header('Content-Disposition',
"attachment; filename= %s" % attach_file)
# attach the instance 'p' to instance 'msg'
msg.attach(p)
# creates SMTP session
s = smtplib.SMTP('smtp.gmail.com', 587)
# start TLS for security
s.starttls()
# Authentication
s.login(fromaddr, gmail_password)
# Converts the Multipart msg into a string
text = msg.as_string()
post_log(f"Creation of email body for {user_name}", 'COMPLETED')
# sending the mail
s.sendmail(fromaddr, toaddr, text)
post_log(f"Email sending for the user : {user_name}", 'COMPLETED')
# terminating the session
s.quit()
# updating object value
ir_object.is_visited_by_cron = True
ir_object.save()
# updating result
irr_object.is_published = True
irr_object.data = result_data
irr_object.save()
except Exception as e:
# df.to_csv(f'{company_name}_all_reviews.csv')
# traceback.print_exc()
post_log(f"{e} : for user : {user_name}", "ERROR")
irr_object.data = result_data
irr_object.save()
LOGGER.info(
f'[tag:INTRUNTER20] tasks.execute_interview_request: finished execution for ir_id: {ir_object.id}'
)
def get_articles_info(company_name, start=None, end=None):
gn = GoogleNews()
return gn.search(company_name, from_=start, to_=end)['entries']
