-
-
Save garymanley/d85ff1ec2a9d2a31f47ea7212e5862b1 to your computer and use it in GitHub Desktop.
Twit2Blog
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Created on Sun Jan 14 13:08:30 2018 | |
@author: garym | |
""" | |
#run imports | |
import pandas as pd | |
from twitterscraper import query_tweets | |
import re | |
from sqlalchemy import create_engine | |
import pyodbc as py | |
import urllib | |
import codecs | |
__author__ = 'garymanley@gmail.com (Gary Manley)' | |
from oauth2client import client | |
from googleapiclient import sample_tools | |
# Authenticate and construct service. | |
argv ='P' | |
service, flags = sample_tools.init(argv, 'blogger', 'v3', __doc__, __file__, scope='https://www.googleapis.com/auth/blogger') | |
### set up connection string for database | |
conn_str = ( | |
r'Driver={SQL Server};' | |
r'Server=localhost\SQLEXPRESS;' | |
r'Database=Twitter;' | |
r'Trusted_Connection=yes;' | |
) | |
quoted_conn_str = urllib.parse.quote_plus(conn_str) | |
engine = create_engine('mssql+pyodbc:///?odbc_connect={}'.format(quoted_conn_str)) | |
cnxn = py.connect(conn_str) | |
cursor = cnxn.cursor() | |
## create function to download and save tweets | |
def download(twittersearch,number): | |
#### download tweets and write into a file | |
file = open(r'C:\Users\garym\Documents\New folder (2)\output.txt','w') | |
file.write('Date\tUser\tTweet\n') #\t Likes \t Retweets \n') | |
print('Collecting Data') | |
for tweet in query_tweets(twittersearch, number): | |
try: | |
file.write(str(tweet.timestamp) + '\t' + re.sub(r"[\n\t]*", "",tweet.user) + '\t' + re.sub(r"[\n\t]*", "",tweet.text) + '\n' ) #'\t' + tweet.likes + '\t' + tweet.retweets + '\n') | |
except: | |
print('error on tweet') | |
file.close() | |
### open the file as a dateframe | |
df = pd.read_table(r'C:\Users\garym\Documents\New folder (2)\output.txt' , encoding='latin-1') | |
print('Inserting Data into Tweets') | |
### import to database | |
df.to_sql(name='Tweets', con=engine, if_exists = 'replace') | |
### function to create HTML | |
def createHTML(): | |
print('Creating HTML') | |
df = pd.read_sql('SELECT TOP 50 [USER], count(*) TOTAL FROM [Twitter].[dbo].[Tweets] GROUP BY [USER] ORDER BY 2 desc',cnxn) | |
df.to_html(r'C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\top50.html') | |
df = pd.read_sql('select year([date]) Yr , month([date]) mon , day([date]) dy , datepart(hour , [date]) hr , count(*) total from tweets group by year([date]) , month([date]) , day([date]) , datepart(hour , [date])',cnxn) | |
# df.to_html(r'C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\timeTweets.html') | |
html = ( | |
df.style | |
.set_properties(**{'font-size': '9pt', 'font-family': 'Calibri'}) | |
.bar(subset=['total'], color='lightblue') | |
.render() | |
) | |
#print(html) | |
fh = open(r"C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\output.html","w") | |
fh.write(html) | |
fh.close() | |
## Create post from linking HTML together | |
def post(title,blogid,labels): | |
html = 'This is an automatically generated post using python!! <br><br><br>' | |
f=codecs.open(r"C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\output.html", 'r') | |
html = html + f.read() | |
html = html + '<br><br>' | |
f=codecs.open(r'C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\top50.html', 'r') | |
html = html + f.read() | |
posts = service.posts() | |
body = { | |
"kind": "blogger#post", | |
"id": blogid, | |
"title": "Twitter Analysis on " + title, | |
"content":html, | |
"labels":labels | |
} | |
insert = posts.insert(blogId=blogid, body=body) | |
insert.execute() | |
def HTMLTEST(): | |
html = 'This is an automatically generated post using python!! <br><br><br>' | |
f=codecs.open(r"C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\output.html", 'r') | |
html = html + f.read() | |
html = html + '<br><br>' | |
f=codecs.open(r'C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\top50.html', 'r') | |
html = html + f.read() | |
fh = open(r"C:\Users\garym\Documents\PyWinAutoBlog\AutoAutoBlog\postSample.html","w") | |
fh.write(html) | |
fh.close() | |
#### run the above functions | |
download('Low Carb',1000) | |
createHTML() | |
post('Low Carb',"3722853969266245324",['low carb','twitter']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment