├── .github
    └── workflows
    │   └── update.yml
├── README.md
├── Street_Tree_List.csv
└── requirements.txt


/.github/workflows/update.yml:
--------------------------------------------------------------------------------
 1 | name: Scrape latest data
 2 | 
 3 | on:
 4 |   push:
 5 |   workflow_dispatch:
 6 |   schedule:
 7 |     - cron:  '21 11 * * *'
 8 | 
 9 | jobs:
10 |   scheduled:
11 |     runs-on: ubuntu-latest
12 |     steps:
13 |     - name: Check out this repo
14 |       uses: actions/checkout@v4
15 |       with:
16 |         fetch-depth: 0
17 |     - name: Set up Python
18 |       uses: actions/setup-python@v5
19 |       with:
20 |         python-version: 3.13
21 |     - uses: actions/cache@v4
22 |       name: Configure pip caching
23 |       with:
24 |         path: ~/.cache/pip
25 |         key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
26 |         restore-keys: |
27 |           ${{ runner.os }}-pip-
28 |     - name: Install Python dependencies
29 |       run: |-
30 |         pip install -r requirements.txt
31 |     - name: Fetch latest data
32 |       run: |-
33 |         cp Street_Tree_List.csv Street_Tree_List-old.csv
34 |         curl -o Street_Tree_List-unsorted.csv "https://data.sfgov.org/api/views/tkzw-k3nq/rows.csv?accessType=DOWNLOAD"
35 |         # Remove heading line and use it to start a new file
36 |         head -n 1 Street_Tree_List-unsorted.csv > Street_Tree_List.csv
37 |         # Sort all but the first line and append to that file
38 |         tail -n +2 "Street_Tree_List-unsorted.csv" | sort >> Street_Tree_List.csv
39 |         # Generate commit message using csv-diff
40 |         csv-diff Street_Tree_List-old.csv Street_Tree_List.csv --key=TreeID --singular=tree --plural=trees > message.txt
41 |     - name: Commit and push if it changed
42 |       run: |-
43 |         git config user.name "Automated"
44 |         git config user.email "actions@users.noreply.github.com"
45 |         git add Street_Tree_List.csv
46 |         timestamp=$(date -u)
47 |         git commit -F message.txt || exit 0
48 |         git push
49 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # sf-tree-history
 2 | 
 3 | Tracking the history of trees in San Francisco.
 4 | 
 5 | Background: [Generating a commit log for San Francisco’s official list of trees](https://simonwillison.net/2019/Mar/13/tree-history/). See also [Git Scraping](https://simonwillison.net/2020/Oct/9/git-scraping/) for a description of the general technique.
 6 | 
 7 | This repository [uses GitHub Actions](https://github.com/simonw/sf-tree-history/actions) to retrieve the [official CSV file of trees in San Francisco](https://data.sfgov.org/City-Infrastructure/Street-Tree-List/tkzw-k3nq) once a day and track any changes to it over time using the git commit history.
 8 | 
 9 | It uses [csv-diff](https://github.com/simonw/csv-diff) to generate human-readable commit messages.
10 | 
11 | You can see recent changes to the CSV file here: https://github.com/simonw/sf-tree-history/commits/main
12 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | csv-diff
2 | 


--------------------------------------------------------------------------------