dylanroy · October 12, 2020 13:39
diff --git a/action.yaml b/action.yaml
 name: scrape-wikipedia

 on:
  push:
    branches:
      - master
  schedule:
    - cron: "0 */1 * * *"

 jobs:
  build-and-deploy:
    runs-on: ubuntu-latest
    steps:
      - name: 🍽️ Get working copy
        uses: actions/checkout@master
        with:
          fetch-depth: 1                                                                 
      - name: 🐍 Set up Python 3.8                               
        uses: actions/setup-python@v2                               
        with:                                 
          python-version: '3.8'                                                   
      - name: 💿 Install Requirements                             
        run: pip install -r requirements.txt
      - name: 🍳 Update dataset
        run: python main.py
      - name: 🚀 Commit and push if it changed
        run: |
          git config user.name "${GITHUB_ACTOR}"
          git config user.email "${GITHUB_ACTOR}@users.noreply.github.com"
          git add -A
          timestamp=$(date -u)
          git commit -m "Latest data: ${timestamp}" || exit 0
          git push
diff --git a/action_1.yaml b/action_1.yaml
 name: scrape-wikipedia

 on:
  push:
    branches:
      - master
  schedule:
    - cron: "0 */1 * * *"
diff --git a/action_2.yaml b/action_2.yaml
 jobs:
  build-and-deploy:
    runs-on: ubuntu-latest
diff --git a/action_3.yaml b/action_3.yaml
    steps:
      - name: 🍽️ Get working copy
        uses: actions/checkout@master
        with:
          fetch-depth: 1     
diff --git a/action_4.yaml b/action_4.yaml
      - name: 🐍 Set up Python 3.8                               
        uses: actions/setup-python@v2                               
        with:                                 
          python-version: '3.8'
diff --git a/action_5.yaml b/action_5.yaml
      - name: 💿 Install Requirements                             
        run: pip install -r requirements.txt
diff --git a/action_6.yaml b/action_6.yaml
      - name: 🍳 Update dataset
        run: python main.py
diff --git a/action_7.yaml b/action_7.yaml
      - name: 🚀 Commit and push if it changed
        run: |
          git config user.name "${GITHUB_ACTOR}"
          git config user.email "${GITHUB_ACTOR}@users.noreply.github.com"
          git add -A
          timestamp=$(date -u)
          git commit -m "Latest data: ${timestamp}" || exit 0
          git push
diff --git a/main.py b/main.py
 import re

 import pandas as pd

 def scrape_wiki_table(url, table_index=0):
    df = pd.read_html(url, header=0)[table_index]
    return re.sub(r"\[?\s*(\d+)(?=(?:, \d+)|\])(?=[^\[]*\]).", "", df.to_csv(index=False))

 if __name__ == '__main__':
    with open('data.csv', 'w+') as f:
        f.write(scrape_wiki_table('https://en.wikipedia.org/wiki/List_of_chief_executive_officers'))
diff --git a/Simple Versioned Datasets With Github Actions b/Simple Versioned Datasets With Github Actions
 # Medium Post
diff --git a/snippet_1.py b/snippet_1.py
 df = pd.read_html(url, header=0)[table_index]
diff --git a/snippet_2.csv b/snippet_2.csv
diff --git a/snippet_3.py b/snippet_3.py
 return re.sub(r"\[?\s*(\d+)(?=(?:, \d+)|\])(?=[^\[]*\]).", "", df.to_csv(index=False))
	name: scrape-wikipedia

	on:
	push:
	branches:
	- master
	schedule:
	- cron: "0 /1 * *"

	jobs:
	build-and-deploy:
	runs-on: ubuntu-latest
	steps:
	- name: 🍽️ Get working copy
	uses: actions/checkout@master
	with:
	fetch-depth: 1
	- name: 🐍 Set up Python 3.8
	uses: actions/setup-python@v2
	with:
	python-version: '3.8'
	- name: 💿 Install Requirements
	run: pip install -r requirements.txt
	- name: 🍳 Update dataset
	run: python main.py
	- name: 🚀 Commit and push if it changed
	run: \|
	git config user.name "${GITHUB_ACTOR}"
	git config user.email "${GITHUB_ACTOR}@users.noreply.github.com"
	git add -A
	timestamp=$(date -u)
	git commit -m "Latest data: ${timestamp}" \|\| exit 0
	git push
	import re

	import pandas as pd

	def scrape_wiki_table(url, table_index=0):
	df = pd.read_html(url, header=0)[table_index]
	return re.sub(r"\[?\s(\d+)(?=(?:, \d+)\|\])(?=[^\[]\]).", "", df.to_csv(index=False))

	if __name__ == '__main__':
	with open('data.csv', 'w+') as f:
	f.write(scrape_wiki_table('https://en.wikipedia.org/wiki/List_of_chief_executive_officers'))
Company	Executive	Title	Since	Notes	Updated
Accenture	Julie Sweet[1]	CEO	2019	Succeeded Pierre Nanterme, died	2019-01-31
Aditya Birla Group	Kumar Birla	Chairman	1995	Part of the Birla family business house in India[2]	2018-10-01
Adobe Systems	Shantanu Narayen	Chairman, president and CEO	2007	Formerly with Apple Inc.[3]	2018-10-01