Merge pull request #264 from UBC-DSCI/web-scraping-api

Web scraping / API re-introduction

Author: trevorcampbell

.github/workflows/update_build_environment.yml

@@ -2,8 +2,7 @@ name: Rebuild and publish new ubcdsci/py-intro-to-ds image on DockerHub
 on:
   pull_request:
     types: [opened, synchronize]
-    paths:
-      - Dockerfile
+
 jobs:
   rebuild-docker:
     name: Rebuild docker image
@@ -21,20 +20,15 @@ jobs:
       run: |
         echo "GitHub PR action type: ${{ github.event.action }}"
         echo "Checking if the PR modifies the Dockerfile"
-        if [[ ${{ github.event.action }} == 'opened' ]]; then
-            echo "PR just opened, and it edits the Dockerfile, so rebuilding the image."
-            echo "stale_dockerfile=true" >> "$GITHUB_OUTPUT"
+        if git diff --quiet ${{ github.event.before }} ${{ github.event.after }} Dockerfile; then
+            echo "PR synchronized, but Dockerfile was not edited. Not rebuilding the image."
+            echo "stale_dockerfile=false" >> "$GITHUB_OUTPUT"
         else
-            if git diff --quiet ${{ github.event.before }} ${{ github.event.after }} Dockerfile; then
-                echo "PR synchronized, but Dockerfile was not edited. Not rebuilding the image."
-                echo "stale_dockerfile=false" >> "$GITHUB_OUTPUT"
-            else
-                echo "PR synchronized, and Dockerfile was edited, so rebuilding the image."
-                echo "stale_dockerfile=true" >> "$GITHUB_OUTPUT"
-            fi
+            echo "PR synchronized, and Dockerfile was edited, so rebuilding the image."
+            echo "stale_dockerfile=true" >> "$GITHUB_OUTPUT"
         fi
     - name: Rebuild and publish image
-      if: ${{steps.check-stale.outputs.stale_dockerfile == true }}
+      if: ${{ steps.check-stale.outputs.stale_dockerfile == 'true' }}
       id: rebuild
       uses: elgohr/Publish-Docker-Github-Action@v5
       with:
@@ -44,7 +38,7 @@ jobs:
         dockerfile: Dockerfile
         snapshot: true
     - name: Update build_html.sh script
-      if: ${{steps.check-stale.outputs.stale_dockerfile == true }}
+      if: ${{ steps.check-stale.outputs.stale_dockerfile == 'true' }}
       run: |
         git config --local user.email "[email protected]"
         git config --local user.name "GitHub Action"
@@ -54,7 +48,7 @@ jobs:
         git add build_html.sh
         git commit -m "update build_html.sh script with new docker image"
     - name: Update build_pdf.sh script
-      if: ${{steps.check-stale.outputs.stale_dockerfile == true }}
+      if: ${{ steps.check-stale.outputs.stale_dockerfile == 'true' }}
       run: |
         git config --local user.email "[email protected]"
         git config --local user.name "GitHub Action"
@@ -64,7 +58,7 @@ jobs:
         git add build_pdf.sh
         git commit -m "update build_pdf.sh script with new docker image"
     - name: Push changes to build scripts
-      if: ${{steps.check-stale.outputs.stale_dockerfile == true }}
+      if: ${{ steps.check-stale.outputs.stale_dockerfile == 'true' }}
       uses: ad-m/github-push-action@master
       with:
         github_token: ${{ secrets.GITHUB_TOKEN }}

Dockerfile

@@ -18,7 +18,7 @@ RUN pip install docutils==0.17.1 # Need to pin docutils to an old version for no
 RUN pip install referencing
 RUN pip install jupyter-book
 # Pinning pandas until altair 5.1.2 to avoid future warning https://github.com/altair-viz/altair/issues/3181
-RUN pip install numpy jinja2 pandas"<2.1" altair">=5.1.1" "vegafusion[embed]" vl-convert-python">=0.13" click ibis-framework ghp-import jupytext nodejs
+RUN pip install numpy jinja2 pandas"<2.1" altair">=5.1.1" "vegafusion[embed]" vl-convert-python">=0.13" click ibis-framework ghp-import jupytext nodejs lxml
 
 # forces scikit-learn to grab latest to avoid bug in 1.3.0 related to checking for c-contiguity breaking figures in classification 2. See https://github.com/scikit-learn/scikit-learn/pull/26772
 # TODO: remove this once scikit-learn 1.4.x or beyond releases and is incorporated into jupyter/scipy-notebook

build_html.sh

@@ -1,2 +1,2 @@
 chmod -R o+w source/
-docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230913180510589822 /bin/bash -c "jupyter-book build source"
+docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230923214301d47351 /bin/bash -c "jupyter-book build source"

build_pdf.sh

@@ -1,2 +1,2 @@
 chmod -R o+w source/
-docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230913180510589822 /bin/bash -c "export BOOK_BUILD_TYPE='PDF'; jupyter-book build source --builder pdflatex"
+docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230923214301d47351 /bin/bash -c "export BOOK_BUILD_TYPE='PDF'; jupyter-book build source --builder pdflatex"

source/_config.yml

@@ -48,7 +48,7 @@ html:
   use_multitoc_numbering: true # Continuous numbering across parts/chapters
   extra_navbar: Powered by <a href="https://jupyterbook.org">Jupyter Book</a> # Will be displayed underneath the left navbar.
   extra_footer: "" # Will be displayed underneath the footer.
-  google_analytics_id: "" # A GA id that can be used to track book views.
+  google_analytics_id: "G-7XBFF4RSN2" # A GA id that can be used to track book views.
   home_page_in_navbar: true # Whether to include your home page in the left Navigation Bar
   baseurl: "" # The base URL where your book will be hosted. Used for creating image previews and social links. e.g.: https://mypage.com/mybook/
   comments: