From 032f8a57143a75071d7c8fb9fc63d9a70e829474 Mon Sep 17 00:00:00 2001
From: Armin Friedl <dev@friedl.net>
Date: Sat, 26 Dec 2020 17:12:08 +0100
Subject: [PATCH] Download additional resources

Scrape:
- https://web.stanford.edu/class/cs143/
- http://openclassroom.stanford.edu/MainFolder/courses/Compilers/docs

Both contain resources not found in the edx course. Among others:
- LaTeX sources for assignments
- Slides (annotated and un-annotated)
- Previous finals for practicing
---
 Dockerfile | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 3956dd1..a67549d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -41,6 +41,32 @@ RUN wget -O - https://courses.edx.org/asset-v1:StanfordOnline+SOE.YCSCS1+1T2020+
 RUN wget -O - https://courses.edx.org/asset-v1:StanfordOnline+SOE.YCSCS1+1T2020+type@asset+block@pa4-grading.pl \
   | tee /usr/class/assignments/PA5J/grade.pl /usr/class/assignments/PA5/grade.pl > /dev/null
 
+# Download additional resources to `class/handouts`. We scrape the whole
+# websites every time we build the container. On the other hand they could just
+# provide the resources in the course ¯\_(ツ)_/¯
+
+# Move the handouts in the student-dist.tar.gz to edx subfolder
+RUN mkdir -p /usr/class/handouts/edx \
+  && cd /usr/class/handouts \
+  && mv *.pdf edx
+
+# Download cs143 resources. This contains e.g. latex templates for the assignments, previous finals
+# https://web.stanford.edu/class/cs143/
+RUN mkdir -p /usr/class/handouts/cs143 \
+  && cd /usr/class/handouts/cs143 \
+  && wget -r -k -l1 https://web.stanford.edu/class/cs143/ \
+  && mv web.stanford.edu/class/cs143/* . && rm -fR web.stanford.edu
+
+# Download openclassroom resources. this contains e.g. the annotated video slides.
+# We are downloading the directory listing from
+# http://openclassroom.stanford.edu/MainFolder/courses/Compilers/docs
+# here, so we can use mirror (-m) without parents (-np) here.
+# see also: http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=Compilers
+RUN mkdir -p /usr/class/handouts/openclassroom \
+  && cd /usr/class/handouts/openclassroom \
+  && wget -np -m http://openclassroom.stanford.edu/MainFolder/courses/Compilers/docs \
+  && mv openclassroom.stanford.edu/MainFolder/courses/Compilers/docs/* . && rm -fR openclassroom.stanford.edu
+
 # Patch tar arguments in submission scripts
 # We add -o to tar command since --preserve-permissions and --same-owner
 # are default in tar for superuser. Since we are running as root
@@ -65,7 +91,9 @@ RUN patch -u /usr/class/assignments/PA2/cool.flex -i /tmp/build/cool.flex.patch
 RUN mkdir -p /class
 WORKDIR /class
 
-# Run entrypoint to connect working directory to mounted host volume
+# Run entrypoint to connect working directory to mounted host volume. This
+# copies files to the (potentially host-mounted) volume, s.t. files can be
+# edited on the host and are also visible in the container.
 COPY entrypoint.sh /usr/bin/entrypoint.sh
 ENTRYPOINT ["entrypoint.sh"]
 CMD ["/bin/bash"]