twitterscraper-ruby 0.15.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a950fb24329aaa1020441e258a8a2144100d732142b6c227bb9b026b8bb73996
+  data.tar.gz: 1f64f31e43189e2ee439f5ef6f6d54bc6ea58895adbed67cb8ddbe91af07681a
+SHA512:
+  metadata.gz: 8573affbc9a5faa05e5e489364bb2ba0da1aa4f12af35445e5de8b1f8c399eb0575cc9f408b2ba96c3d7fd8b2a74b7dd703229053a33c1f8a883856818033cb9
+  data.tar.gz: 2b2b3ad0b2dd9d089a7b6127ed1b0db21e7f4fa5f0c31e6b366d9b5ae444e2244d4200c813b7a3257f43702d2caa9f264515e701602c24f4482a746b89d41328

data/.circleci/config.yml

@@ -0,0 +1,31 @@
+version: 2.1
+orbs:
+  ruby: circleci/ruby@0.1.2
+
+jobs:
+  build:
+    docker:
+      - image: circleci/ruby:2.6.4-stretch-node
+        environment:
+          BUNDLER_VERSION: 2.1.4
+    executor: ruby/default
+    steps:
+      - checkout
+      - run:
+          name: Update bundler
+          command: gem update bundler
+      - run:
+          name: Which bundler?
+          command: bundle -v
+      - restore_cache:
+          keys:
+            - gem-cache-v1-{{ arch }}-{{ .Branch }}-{{ checksum "Gemfile.lock" }}
+            - gem-cache-v1-{{ arch }}-{{ .Branch }}
+            - gem-cache-v1
+      - run: bundle install --path vendor/bundle
+      - run: bundle clean
+      - save_cache:
+          key: gem-cache-v1-{{ arch }}-{{ .Branch }}-{{ checksum "Gemfile.lock" }}
+          paths:
+            - vendor/bundle
+      - run: bundle exec rspec

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/cache
+/.idea

data/.irbrc

@@ -0,0 +1,7 @@
+require 'irb/completion'
+require 'irb/ext/save-history'
+
+IRB.conf[:SAVE_HISTORY] = 10000
+IRB.conf[:HISTORY_FILE] = File.expand_path('~/.irb_history')
+
+require 'twitterscraper'

data/.rspec

@@ -0,0 +1,2 @@
+-fd
+--require spec_helper

data/.ruby-version

@@ -0,0 +1 @@
+2.6.4

data/.travis.yml

@@ -0,0 +1,6 @@
+---
+language: ruby
+cache: bundler
+rvm:
+  - 2.5.3
+before_install: gem install bundler -v 2.1.4

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at ts_3156@yahoo.co.jp. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [https://contributor-covenant.org/version/1/4][version]
+
+[homepage]: https://contributor-covenant.org
+[version]: https://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,8 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in twitterscraper-ruby.gemspec
+gemspec
+
+gem "rake", "~> 12.0"
+gem "minitest", "~> 5.0"
+gem "rspec"

data/Gemfile.lock

@@ -0,0 +1,42 @@
+PATH
+  remote: .
+  specs:
+    twitterscraper-ruby (0.15.0)
+      nokogiri
+      parallel
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.4.4)
+    mini_portile2 (2.4.0)
+    minitest (5.14.1)
+    nokogiri (1.10.10)
+      mini_portile2 (~> 2.4.0)
+    parallel (1.19.2)
+    rake (12.3.3)
+    rspec (3.9.0)
+      rspec-core (~> 3.9.0)
+      rspec-expectations (~> 3.9.0)
+      rspec-mocks (~> 3.9.0)
+    rspec-core (3.9.2)
+      rspec-support (~> 3.9.3)
+    rspec-expectations (3.9.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-mocks (3.9.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-support (3.9.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  minitest (~> 5.0)
+  rake (~> 12.0)
+  rspec
+  twitterscraper-ruby!
+
+BUNDLED WITH
+   2.1.4

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2020 ts-3156
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,174 @@
+# twitterscraper-ruby
+
+[![Build Status](https://circleci.com/gh/ts-3156/twitterscraper-ruby.svg?style=svg)](https://circleci.com/gh/ts-3156/twitterscraper-ruby)
+[![Gem Version](https://badge.fury.io/rb/twitterscraper-ruby.svg)](https://badge.fury.io/rb/twitterscraper-ruby)
+
+A gem to scrape https://twitter.com/search. This gem is inspired by [taspinar/twitterscraper](https://github.com/taspinar/twitterscraper).
+
+
+## Twitter Search API vs. twitterscraper-ruby
+
+### Twitter Search API
+
+- The number of tweets: 180 - 450 requests/15 minutes (18,000 - 45,000 tweets/15 minutes)
+- The time window: the past 7 days
+
+### twitterscraper-ruby
+
+- The number of tweets: Unlimited
+- The time window: from 2006-3-21 to today
+
+
+## Installation
+
+First install the library:
+
+```shell script
+$ gem install twitterscraper-ruby
+````
+    
+
+## Usage
+
+Command-line interface:
+
+```shell script
+# Returns a collection of relevant tweets matching a specified query.
+$ twitterscraper --type search --query KEYWORD --start_date 2020-06-01 --end_date 2020-06-30 --lang ja \
+      --limit 100 --threads 10 --output tweets.json
+```
+
+```shell script
+# Returns a collection of the most recent tweets posted by the user indicated by the screen_name
+$ twitterscraper --type user --query SCREEN_NAME --limit 100 --output tweets.json
+```
+
+From Within Ruby:
+
+```ruby
+require 'twitterscraper'
+client = Twitterscraper::Client.new(cache: true, proxy: true)
+```
+
+```ruby
+# Returns a collection of relevant tweets matching a specified query.
+tweets = client.search(KEYWORD, start_date: '2020-06-01', end_date: '2020-06-30', lang: 'ja', limit: 100, threads: 10)
+```
+
+```ruby
+# Returns a collection of the most recent tweets posted by the user indicated by the screen_name
+tweets = client.user_timeline(SCREEN_NAME, limit: 100)
+```
+
+
+## Attributes
+
+### Tweet
+
+```ruby
+tweets.each do |tweet|
+  puts tweet.tweet_id
+  puts tweet.text
+  puts tweet.tweet_url
+  puts tweet.created_at
+
+  hash = tweet.attrs
+  puts hash.keys
+end
+```
+
+- screen_name
+- name
+- user_id
+- tweet_id
+- text
+- links
+- hashtags
+- image_urls
+- video_url
+- has_media
+- likes
+- retweets
+- replies
+- is_replied
+- is_reply_to
+- parent_tweet_id
+- reply_to_users
+- tweet_url
+- created_at
+
+
+## Search operators
+
+| Operator | Finds Tweets... |
+| ------------- | ------------- |
+| watching now | containing both "watching" and "now". This is the default operator. |
+| "happy hour" | containing the exact phrase "happy hour". |
+| love OR hate | containing either "love" or "hate" (or both). |
+| beer -root | containing "beer" but not "root". |
+| #haiku | containing the hashtag "haiku". |
+| from:interior | sent from Twitter account "interior". |
+| to:NASA | a Tweet authored in reply to Twitter account "NASA". |
+| @NASA | mentioning Twitter account "NASA". |
+| puppy filter:media | containing "puppy" and an image or video. |
+| puppy -filter:retweets | containing "puppy", filtering out retweets |
+| superhero since:2015-12-21 | containing "superhero" and sent since date "2015-12-21" (year-month-day). |
+| puppy until:2015-12-21 | containing "puppy" and sent before the date "2015-12-21". |
+
+Search operators documentation is in [Standard search operators](https://developer.twitter.com/en/docs/tweets/rules-and-filtering/overview/standard-operators).
+
+
+## Examples
+
+```shell script
+$ twitterscraper --query twitter --limit 1000
+$ cat tweets.json | jq . | less
+```
+
+```json
+[
+  {
+    "screen_name": "@screenname",
+    "name": "name",
+    "user_id": 1194529546483000000,
+    "tweet_id": 1282659891992000000,
+    "tweet_url": "https://twitter.com/screenname/status/1282659891992000000",
+    "created_at": "2020-07-13 12:00:00 +0000",
+    "text": "Thanks Twitter!"
+  }
+]
+```
+
+## CLI Options
+
+| Option | Description | Default |
+| ------------- | ------------- | ------------- |
+| `-h`, `--help` | This option displays a summary of twitterscraper. | |
+| `--type` | Specify a search type. | search |
+| `--query` | Specify a keyword used during the search. | |
+| `--start_date` | Used as "since:yyyy-mm-dd for your query. This means "since the date". | |
+| `--end_date` | Used as "until:yyyy-mm-dd for your query. This means "before the date". | |
+| `--lang` | Retrieve tweets written in a specific language. | |
+| `--limit` | Stop scraping when *at least* the number of tweets indicated with --limit is scraped. | 100 |
+| `--order` | Sort order of the results. | desc |
+| `--threads` | Set the number of threads twitterscraper-ruby should initiate while scraping for your query. | 2 |
+| `--proxy` | Scrape https://twitter.com/search via proxies. | true |
+| `--cache` | Enable caching. | true |
+| `--format` | The format of the output. | json |
+| `--output` | The name of the output file. | tweets.json |
+| `--verbose` | Print debug messages. | tweets.json |
+
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/ts-3156/twitterscraper-ruby. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/ts-3156/twitterscraper-ruby/blob/master/CODE_OF_CONDUCT.md).
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+
+## Code of Conduct
+
+Everyone interacting in the twitterscraper-ruby project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/ts-3156/twitterscraper-ruby/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task :default => :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "twitterscraper/ruby"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/bin/twitterscraper

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/twitterscraper/cli'
+
+begin
+  cli = Twitterscraper::Cli.new
+  cli.parse
+  cli.run
+rescue => e
+  STDERR.puts e.inspect
+  STDERR.puts e.backtrace.join("\n")
+  exit 1
+end