def retrieve_google_trends(self, search, date_range):
# Set up the trend fetching object
pytrends = TrendReq(hl='en-US', tz=360)
kw_list = [search]
try:
# Create the search object
pytrends.build_payload(kw_list,
cat=0,
timeframe=date_range[0],
geo='',
gprop='news')
# Retrieve the interest over time
trends = pytrends.interest_over_time()
related_queries = pytrends.related_queries()
except Exception as e:
print('\nGoogle Search Trend retrieval failed.')
print(e)
return
return trends, related_queries
def retrieve_google_trends(self, search, date_range):
# 设置趋势提取对象
pytrends = TrendReq(hl='en-US', tz=360)
kw_list = [search]
try:
# 创建搜索对象
pytrends.build_payload(kw_list,
cat=0,
timeframe=date_range[0],
geo='',
gprop='news')
#随时检索
trends = pytrends.interest_over_time()
related_queries = pytrends.related_queries()
except Exception as e:
print('\nGoogle Search Trend retrieval failed.')
print(e)
return
return trends, related_queries
def wordcloud_queries(key,date):
pytrends.build_payload([key], cat=0, timeframe=date, geo='', gprop='')
query = pytrends.related_queries()
if query[key]['top'] is not None:
input_top = list(query[key]['top']['query'])
input_rising = list(query[key]['rising']['query'])
def plot_wordcloud(output):
text = " ".join(output)
wordcloud = WordCloud(max_font_size=70, max_words=1000, colormap="Blues", background_color="white").generate(text)
plt.figure(figsize=(8,6))
plt.title("WordCloud of Top 25 Related Queries",fontsize=20, weight = 'bold', fontfamily='sans-serif')
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.savefig("image/{}_google_wordcloud.png".format(key),bbox_inches='tight',dpi=100)
plt.close()
plot_wordcloud(input_top)
def pop2(lists):
from pytrends.request import TrendReq
# Create pytrends object, request data from Google Trends
pytrends = TrendReq(hl='en-US', tz=360)
# Extracts data based on our keywords
kw_list = lists
pytrends.build_payload(kw_list,
cat=0,
timeframe='today 5-y',
geo='',
gprop='')
# Specify, get, and normalize data
data = pytrends.interest_over_time()
data.drop('isPartial', axis=1, inplace=True)
normData = data.apply(lambda x: x / x.max(), axis=0)
# Max normalized value from most recent date + index in list
recent = normData.values[-1].tolist()
max_value = max(recent)
max_index = recent.index(max_value)
# Name of most popular normalized item
out = kw_list[max_index]
pytrends.build_payload(kw_list=[out],
cat=0,
timeframe='today 5-y',
geo='',
gprop='')
trend = pytrends.related_queries()
trend_list = trend[out]['top']['query']
# Adds variable number of hashtags to topList
numHashtags = 5
topList = []
for i in range(numHashtags):
topList.append(trend_list[i])
# TopList is a list of hashtags, out is most popular item
poplist = out
return (poplist)
def retrieve_google_trends(self, search, date_range):
# Set up the trend fetching object
pytrends = TrendReq(hl='en-US', tz=360)
kw_list = [search]
try:
# Create the search object
pytrends.build_payload(kw_list, cat=0, timeframe=date_range[0], geo='', gprop='news')
# Retrieve the interest over time
trends = pytrends.interest_over_time()
related_queries = pytrends.related_queries()
except Exception as e:
print('\nGoogle Search Trend retrieval failed.')
print(e)
return
return trends, related_queries
def google_trends(query):
# Set up the trend fetching object
pytrends = TrendReq(hl='en-US', tz=360)
kw_list = [search]
# Create the search object
pytrends.build_payload(kw_list, cat=0, geo='', gprop='news')
# Get the interest over time
interest = pytrends.interest_over_time()
print(interest.head())
# Get related searches
related_queries = pytrends.related_queries()
print(related_queries)
# # Get Google Top Charts
# top_charts_df = pytrend.top_charts(cid='actors', date=201611)
# print(top_charts_df.head())
return interest, related_queries
def pop(lists):
from pytrends.request import TrendReq
# Create pytrends object, request data from Google Trends
pytrends = TrendReq(hl='en-US', tz=360)
# Extracts data based on our keywords
kw_list = lists
pytrends.build_payload(kw_list,
cat=0,
timeframe='today 5-y',
geo='',
gprop='')
# Specify, get, and normalize data
data = pytrends.interest_over_time()
data.drop('isPartial', axis=1, inplace=True)
normData = data.apply(lambda x: x / x.max(), axis=0)
# Max normalized value from most recent date + index in list
recent = normData.values[-1].tolist()
max_value = max(recent)
max_index = recent.index(max_value)
# Name of most popular normalized item
out = kw_list[max_index]
pytrends.build_payload(kw_list=[out],
cat=0,
timeframe='today 5-y',
geo='',
gprop='')
trend = pytrends.related_queries()
trend_list = trend[out]['top']['query']
# Adds variable number of hashtags to topList
numHashtags = 5
topList = []
for i in range(numHashtags):
topList.append(trend_list[i])
# TopList is a list of hashtags, out is most popular item
poplist = topList
import pandas as pd
from pytrends.request import TrendReq
import pytrends
from pytrends.request import TrendReq
import pandas as pd
import time
import datetime
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, date, time
pytrend = TrendReq()
pytrend = TrendReq()
pytrend.build_payload(kw_list,
timeframe='today 12-m',
geo='GB',
cat=71)
interest_over_time_df = pytrend.interest_over_time()
print(interest_over_time_df.head())
sns.set(color_codes=True)
dx = interest_over_time_df.plot.line(figsize=(9, 6),
title="Interest Over Time")
dx.set_xlabel('Date')
dx.set_ylabel('Trends Index')
dx.tick_params(axis='both', which='major', labelsize=13)
dx.figure.savefig("static/output.png")
return (poplist)
df_split_test = df_split["keywords"].values.tolist()[0:500] #0-301 DONE
for x in range(0, len(df_split_test)):
keywords = [df_split_test[x]]
print(keywords)
keyword_data = pd.DataFrame()
# for x in range(0, len(df_split_test)):
# startTime = time.time()
# pytrends.build_payload(kw_list=[df_split_test[x]], cat=0, timeframe='2020-01-01 2020-07-30', geo='US')
# related_queries = pytrends.related_queries()
# trends_value = related_queries[df_split_test[x]]['top']
# if len(trends_value)==0:
# print(related_queries[df_split_test[x]]['key'])
for x in range(0, len(df_split_test)):
startTime = time.time()
pytrends.build_payload(kw_list=[df_split_test[x]],
cat=0,
timeframe='2020-01-01 2020-07-30',
geo='US')
related_queries = pytrends.related_queries()
if related_queries != None:
trends_value = related_queries[df_split_test[x]]['top'].head(25)
keyword_data = keyword_data.append(trends_value)
print(keyword_data)
keyword_data.to_csv('allkeywords100_200.csv')
