adding mysql support (#136)

* test commit

* version 1.1.3.4 added mysql support

* Revert "(#126)"

This reverts commit ecafc09e784a097a358f78aa97398480ac30afb4.

* remove everything

* remove things

* delete all

* mysql init

to review

* renaming files

* some new addings

* remove unnecesary files

* twint.py

* adding files

* apdate text

* update file

* update

* delete all

* adding again all

* updating

* Update Twint.py

* Update Twint.py

* fix mysqlcheck

* fix db.py create tabñle and sqlite3 schema

* placing the sqlite3 schema properly

* fix db.py char left

* Create .travis.yml

* Create .gitignore

* Delete test_mysql_v1.py

README.md

@@ -74,6 +74,7 @@ twint.run.Search(c)
 - CSV
 - JSON
 - SQLite
+- Mysql (DB collation utf8mb4)
 - Elasticsearch
 - MySQL (See MySQL Branch)
 ### Elasticsearch Setup

Twint.py

@@ -31,6 +31,10 @@ def check(args):
             error("Error", "Please specify an output file (Example: -o file.csv).")
         elif args.json:
             error("Error", "Please specify an output file (Example: -o file.json).")
+    if args.hostname:
+        if args.Database is None or args.DB_user is None or args.DB_pwd is None:
+            error("Error", "Please specify database name, user and password")
+
 
     if not args.followers and not args.following:
         if args.user_full:
@@ -96,7 +100,10 @@ def initialize(args):
     c.Limit = args.limit
     c.Count = args.count
     c.Stats = args.stats
+    c.hostname = args.hostname
     c.Database = args.database
+    c.DB_user = args.DB_user
+    c.DB_pwd = args.DB_pwd
     c.To = args.to
     c.All = args.all
     c.Essid = args.essid
@@ -105,6 +112,7 @@ def initialize(args):
     c.Profile_full = args.profile_full
     c.Store_pandas = args.store_pandas
     c.Pandas_type = args.pandas_type
+    c.search_name = args.search_name
     return c
 
 def options():
@@ -134,7 +142,10 @@ def options():
     ap.add_argument("--count", help="Display number of Tweets scraped at the end of session.",
             action="store_true")
     ap.add_argument("--stats", help="Show number of replies, retweets, and likes.", action="store_true")
-    ap.add_argument("-db", "--database", help="Store Tweets in a sqlite3 database.")
+    ap.add_argument("--hostname", help="Store the mysql database host")
+    ap.add_argument("-db", "--database", help="Store Tweets in a sqlite3  or mysql database.")
+    ap.add_argument("--DB_user", help="Store the mysql database user")
+    ap.add_argument("--DB_pwd", help="Store the mysql database pwd")
     ap.add_argument("--to", help="Search Tweets to a user.")
     ap.add_argument("--all", help="Search all Tweets associated with a user.")
     ap.add_argument("--followers", help="Scrape a person's followers.", action="store_true")
@@ -154,7 +165,9 @@ def options():
             action="store_true")
     ap.add_argument("--store-pandas", help="Save Tweets in a DataFrame (Pandas) file.")
     ap.add_argument("--pandas-type", help="Specify HDF5 or Pickle (HDF5 as default)")
+    ap.add_argument("--search_name", help="name for identify the search like -3dprinter stuff- only for mysql")
     args = ap.parse_args()
+    
     return args
 
 def main():

db-schema/twint_db_mysql.sql

+CREATE DATABASE  IF NOT EXISTS `twitterdata_v9` /*!40100 DEFAULT CHARACTER SET utf8mb4 */;
+USE `twitterdata_v9`;
+-- MySQL dump 10.13  Distrib 5.7.22, for Linux (x86_64)
+--
+-- Host: localhost    Database: twitterdata_v9
+-- ------------------------------------------------------
+-- Server version	5.7.22-0ubuntu0.16.04.1
+
+/*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */;
+/*!40101 SET @OLD_CHARACTER_SET_RESULTS=@@CHARACTER_SET_RESULTS */;
+/*!40101 SET @OLD_COLLATION_CONNECTION=@@COLLATION_CONNECTION */;
+/*!40101 SET NAMES utf8 */;
+/*!40103 SET @OLD_TIME_ZONE=@@TIME_ZONE */;
+/*!40103 SET TIME_ZONE='+00:00' */;
+/*!40014 SET @OLD_UNIQUE_CHECKS=@@UNIQUE_CHECKS, UNIQUE_CHECKS=0 */;
+/*!40014 SET @OLD_FOREIGN_KEY_CHECKS=@@FOREIGN_KEY_CHECKS, FOREIGN_KEY_CHECKS=0 */;
+/*!40101 SET @OLD_SQL_MODE=@@SQL_MODE, SQL_MODE='NO_AUTO_VALUE_ON_ZERO' */;
+/*!40111 SET @OLD_SQL_NOTES=@@SQL_NOTES, SQL_NOTES=0 */;
+
+--
+-- Table structure for table `followers`
+--
+
+DROP TABLE IF EXISTS `followers`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!40101 SET character_set_client = utf8 */;
+CREATE TABLE `followers` (
+  `id` bigint(30) NOT NULL,
+  `name` mediumtext,
+  `username` text NOT NULL,
+  `bio` longtext,
+  `location` tinytext,
+  `url` longtext,
+  `join_date` tinytext NOT NULL,
+  `join_time` tinytext NOT NULL,
+  `tweets` int(11) DEFAULT NULL,
+  `following` int(11) DEFAULT NULL,
+  `followers` int(11) DEFAULT NULL,
+  `likes` int(11) DEFAULT NULL,
+  `media` int(11) DEFAULT NULL,
+  `private` tinytext NOT NULL,
+  `verified` tinytext NOT NULL,
+  `avatar` longtext NOT NULL,
+  `date_update` datetime NOT NULL,
+  `follower` text NOT NULL,
+  PRIMARY KEY (`follower`(255),`username`(255),`id`)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+/*!40101 SET character_set_client = @saved_cs_client */;
+
+--
+-- Table structure for table `followers_names`
+--
+
+DROP TABLE IF EXISTS `followers_names`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!40101 SET character_set_client = utf8 */;
+CREATE TABLE `followers_names` (
+  `user` text NOT NULL,
+  `date_update` datetime NOT NULL,
+  `follower` text NOT NULL,
+  PRIMARY KEY (`user`(255),`follower`(255))
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+/*!40101 SET character_set_client = @saved_cs_client */;
+
+--
+-- Table structure for table `following`
+--
+
+DROP TABLE IF EXISTS `following`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!40101 SET character_set_client = utf8 */;
+CREATE TABLE `following` (
+  `id` bigint(30) NOT NULL,
+  `name` mediumtext,
+  `username` text NOT NULL,
+  `bio` longtext,
+  `location` tinytext,
+  `url` longtext,
+  `join_date` tinytext NOT NULL,
+  `join_time` tinytext NOT NULL,
+  `tweets` int(11) DEFAULT NULL,
+  `following` int(11) DEFAULT NULL,
+  `followers` int(11) DEFAULT NULL,
+  `likes` int(11) DEFAULT NULL,
+  `media` int(11) DEFAULT NULL,
+  `private` tinytext NOT NULL,
+  `verified` tinytext NOT NULL,
+  `avatar` longtext NOT NULL,
+  `date_update` datetime NOT NULL,
+  `follows` text NOT NULL,
+  PRIMARY KEY (`id`,`username`(255),`follows`(255))
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+/*!40101 SET character_set_client = @saved_cs_client */;
+
+--
+-- Table structure for table `following_names`
+--
+
+DROP TABLE IF EXISTS `following_names`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!40101 SET character_set_client = utf8 */;
+CREATE TABLE `following_names` (
+  `user` text NOT NULL,
+  `date_update` datetime NOT NULL,
+  `follows` text NOT NULL,
+  PRIMARY KEY (`user`(255),`follows`(255))
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+/*!40101 SET character_set_client = @saved_cs_client */;
+
+--
+-- Table structure for table `tweets`
+--
+
+DROP TABLE IF EXISTS `tweets`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!40101 SET character_set_client = utf8 */;
+CREATE TABLE `tweets` (
+  `id` bigint(30) NOT NULL,
+  `user_id` bigint(30) DEFAULT NULL,
+  `date` date NOT NULL,
+  `time` time NOT NULL,
+  `timezone` tinytext NOT NULL,
+  `location` tinytext NOT NULL,
+  `user` text NOT NULL,
+  `tweet` longtext NOT NULL,
+  `replies` int(11) DEFAULT NULL,
+  `likes` int(11) DEFAULT NULL,
+  `retweets` int(11) DEFAULT NULL,
+  `hashtags` longtext,
+  `link` longtext,
+  `retweet` int(1) DEFAULT NULL,
+  `user_rt` text,
+  `mentions` longtext,
+  `date_update` datetime NOT NULL,
+  `search_name` mediumtext NOT NULL COMMENT 'user can use this field to know from which search the info comes. max 255 chars. if the user do not especify, it must be set to "-" ',
+  PRIMARY KEY (`id`,`search_name`(255))
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
+/*!40101 SET character_set_client = @saved_cs_client */;
+/*!40103 SET TIME_ZONE=@OLD_TIME_ZONE */;
+
+/*!40101 SET SQL_MODE=@OLD_SQL_MODE */;
+/*!40014 SET FOREIGN_KEY_CHECKS=@OLD_FOREIGN_KEY_CHECKS */;
+/*!40014 SET UNIQUE_CHECKS=@OLD_UNIQUE_CHECKS */;
+/*!40101 SET CHARACTER_SET_CLIENT=@OLD_CHARACTER_SET_CLIENT */;
+/*!40101 SET CHARACTER_SET_RESULTS=@OLD_CHARACTER_SET_RESULTS */;
+/*!40101 SET COLLATION_CONNECTION=@OLD_COLLATION_CONNECTION */;
+/*!40111 SET SQL_NOTES=@OLD_SQL_NOTES */;
+
+-- Dump completed on 2018-06-03 14:52:08

requirements.txt

@@ -6,3 +6,4 @@ elasticsearch
 pysocks
 pandas
 tables
+mysqlclient

twint/__version__.py

-VERSION = (1, 1, 3, 4)
+VERSION = (1, 1, 3, 4) #mysql support
 
 __version__ = '.'.join(map(str, VERSION))

twint/config.py

@@ -21,7 +21,10 @@ class Config:
     Limit = None
     Count = None
     Stats = False  
+    hostname = None #mysql
     Database = None
+    DB_user = None #mysql
+    DB_pwd = None  #mysql
     To = None
     All = None
     Debug = False
@@ -38,3 +41,4 @@ class Config:
     Store_pandas = False
     Pandas_type = None
     Pandas = False
+    search_name = "-" #for identify a records in mysql with the search it provides from.  it cannot be null for DB requirements. a tweet must be in several search so the PK are tweet ID and search_name

twint/db.py

@@ -21,7 +21,7 @@ def init(db):
         table_tweets = """
             CREATE TABLE IF NOT EXISTS
                 tweets (
-                    id integer primary key,
+                    id integer not null,
                     user_id integer,
                     date text not null,
                     time text not null,
@@ -37,7 +37,9 @@ def init(db):
                     retweet bool,
                     user_rt text,
                     mentions text,
-                    date_update text not null
+                    date_update text not null,
+                    search_name text not null,
+                    PRIMARY KEY (id, search_name)
                 );
         """
         cursor.execute(table_tweets)
@@ -175,7 +177,7 @@ def user(conn, Username, Followers,  User):
     except sqlite3.IntegrityError:
         pass
 
-def tweets(conn, Tweet):
+def tweets(conn, Tweet, config):
     try:
         date_time = str(datetime.now())
         cursor = conn.cursor()
@@ -195,8 +197,9 @@ def tweets(conn, Tweet):
                     Tweet.retweet,
                     Tweet.user_rt,
                     ",".join(Tweet.mentions),
-                    date_time,)
-        cursor.execute('INSERT INTO tweets VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)', entry)
+                    date_time,
+                    config.search_name,)
+        cursor.execute('INSERT INTO tweets VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)', entry)
         conn.commit()
     except sqlite3.IntegrityError:
         pass

twint/dbmysql.py

+from datetime import datetime
+import MySQLdb
+import sys
+
+def Conn(hostname,Database,db_user,db_pwd):
+    if Database:
+        print("[+] Inserting into Database: " + str(Database))
+        conn = init(hostname,Database,db_user,db_pwd)
+        if isinstance(conn, str):
+            print(str)
+            sys.exit(1)
+    else:
+        conn = ""
+
+    return conn
+
+def init(hostname,Database,db_user,db_pwd):
+    try:
+        conn = MySQLdb.connect(host=hostname,    # your host, usually localhost
+                     user=db_user,         # your username
+                     passwd=db_pwd,  # your password
+                     db=Database,# name of the data base
+					 charset='utf8mb4',
+                     use_unicode=True)          
+        cursor = conn.cursor()
+       #here would be the code for creating the tables if them don't exist
+        return conn
+    except Exception as e:
+        return str(e)
+
+def fTable(Followers):
+    if Followers:
+        table = "followers_names"
+    else:
+        table = "following_names"
+    
+    return table
+
+def uTable(Followers):
+    if Followers:
+        table = "followers"
+    else:
+        table = "following"
+    
+    return table
+
+def follow(conn, Username, Followers, User):
+    try:
+        date_time = str(datetime.now())
+        cursor = conn.cursor()
+        entry = (User, date_time, Username,)
+        query = 'INSERT INTO {} VALUES(%s,%s,%s)'.format(fTable(Followers))
+        cursor.execute(query, entry)
+        conn.commit()
+    except MySQLdb.IntegrityError:
+        pass
+
+def user(conn, Username, Followers,  User):
+    try:
+        date_time = str(datetime.now())
+        cursor = conn.cursor()
+        entry = (User.id,
+                User.name,
+                User.username,
+                User.bio,
+                User.location,
+                User.url,
+                User.join_date,
+                User.join_time,
+                User.tweets,
+                User.following,
+                User.followers,
+                User.likes,
+                User.media_count,
+                User.is_private,
+                User.is_verified,
+                User.avatar, 
+                date_time,
+                Username,)
+        query = 'INSERT INTO {} VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'.format(uTable(Followers))
+        cursor.execute(query, entry)
+        conn.commit()
+ 
+    except MySQLdb.IntegrityError:
+        pass
+           
+
+def tweets(conn, Tweet, config):
+    try:
+        date_time = str(datetime.now())
+        cursor = conn.cursor()
+        entry = (Tweet.id,
+                    Tweet.user_id,
+                    Tweet.datestamp,
+                    Tweet.timestamp,
+                    Tweet.timezone,
+                    Tweet.location,
+                    Tweet.username,
+                    Tweet.tweet,
+                    Tweet.replies,
+                    Tweet.likes,
+                    Tweet.retweets,
+                    ",".join(Tweet.hashtags),
+                    Tweet.link,
+                    Tweet.retweet,
+                    Tweet.user_rt,
+                    ",".join(Tweet.mentions),
+                    date_time,
+                    config.search_name,)
+        cursor.execute('INSERT INTO tweets VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)', entry)
+        conn.commit()
+    except MySQLdb.IntegrityError:
+        pass

twint/favorites.py

-from . import feed, get, db, output, verbose
+from . import feed, get, db, output, verbose, dbmysql
 
 class Favorites:
     def __init__(self, config):
@@ -6,6 +6,9 @@ class Favorites:
         self.feed = [-1]
         self.count = 0
         self.config = config
+        if config.hostname:
+            self.conn = dbmysql.Conn(config.hostname, config.Database, config.DB_user, config.DB_pwd)
+        else:
             self.conn = db.Conn(config.Database)
         self.config.Favorites = True
         

twint/follow.py

-from . import feed, get, db, output, verbose
+from . import feed, get, db, output, verbose, dbmysql
 
 class Follow:
     def __init__(self, config):
@@ -6,6 +6,9 @@ class Follow:
         self.feed = [-1]
         self.count = 0
         self.config = config
+        if config.hostname:
+            self.conn = dbmysql.Conn(config.hostname, config.Database, config.DB_user, config.DB_pwd)
+        else:
             self.conn = db.Conn(config.Database)
         verbose.Elastic(config)
 

twint/output.py

 from datetime import datetime
 
-from . import db, elasticsearch, format, write, Pandas
+from . import db, elasticsearch, format, write, Pandas, dbmysql
 from .tweet import Tweet
 from .user import User
 
+
 tweets_object = []
 
 def datecheck(datestamp, config):
@@ -32,7 +33,6 @@ def _output(obj, output, config):
 
     if config.Pandas:
         Pandas.update(obj, config.Essid)
-
     if config.Elasticsearch:
         if config.Store_object:
             tweets_object.append(obj)
@@ -54,18 +54,21 @@ async def Tweets(tw, location, config, conn):
         if datecheck(tweet.datestamp, config):
             output = format.Tweet(config, tweet)
            
-            if config.Database:
-                db.tweets(conn, tweet)
+            if config.hostname:
+                dbmysql.tweets(conn, tweet, config)
+            elif config.Database:
+                db.tweets(conn, tweet, config)
             if config.Elasticsearch:
                 elasticsearch.Tweet(tweet, config.Elasticsearch, config.Essid)
-                
             _output(tweet, output, config)
 
 async def Users(u, config, conn):
     user = User(u)
     output = format.User(config.Format, user)
 
-    if config.Database:
+    if config.hostname:
+        dbmysql.user(conn, config.Username, config.Followers, user)
+    elif config.Database:
         db.user(conn, config.Username, config.Followers, user)
 
     if config.Elasticsearch:
@@ -81,7 +84,9 @@ async def Users(u, config, conn):
     _output(user, output, config)
 
 async def Username(username, config, conn):
-    if config.Database:
+    if config.hostname:
+        dbmysql.follow(conn, config.Username, config.Followers, username)
+    elif config.Database:
         db.follow(conn, config.Username, config.Followers, username)
 
     if config.Elasticsearch:

twint/profile.py

-from . import db, get, feed, output, verbose
+from . import db, get, feed, output, verbose, dbmysql
 
 class Profile:
     def __init__(self, config):
@@ -6,7 +6,12 @@ class Profile:
         self.feed = [-1]
         self.count = 0
         self.config = config
+
+        if config.hostname:
+            self.conn = dbmysql.Conn(config.hostname, config.Database, config.DB_user, config.DB_pwd)
+        else:
             self.conn = db.Conn(config.Database)
+
         self.config.Profile = True
 
         verbose.Elastic(config)

twint/run.py

@@ -6,6 +6,10 @@ def run(x):
 
 def Favorites(config):
     config.Favorites = True
+    if config.Username:
+        config.search_name="Favourites"+str(config.Username) #to identify to which user is related to
+    else:
+        config.search_name="Favourites"+str(config.User_id) #to identify to which user is related to
     run(favorites.Favorites(config).main())
 
 def Followers(config):

twint/search.py

-from . import datelock, db, get, feed, output, verbose
+from . import datelock, db, get, feed, output, verbose, dbmysql
 from datetime import timedelta
 
 class Search:
@@ -7,6 +7,9 @@ class Search:
         self.feed = [-1]
         self.count = 0
         self.config = config
+        if config.hostname:
+            self.conn = dbmysql.Conn(config.hostname, config.Database, config.DB_user, config.DB_pwd)
+        else:
             self.conn = db.Conn(config.Database)
         self.d = datelock.Set(self.config.Until, self.config.Since)
         self.config.TwitterSearch = True