tim/utility-scripts
1
0
Fork 0
Code Issues Pull Requests Releases Activity

Add a new show to download_daily_show.sh

Browse Source
This commit is contained in:
Timothy Allen 2017-09-04 21:07:51 +02:00
parent 393c2ec93b
commit b1b5b8aebf
1 changed files with 39 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
download_daily_shows.sh
View File

@ -17,9 +17,9 @@ YOUTUBE_DL="python3 /usr/local/bin/youtube-dl"
KEEP_DAYS=100 KEEP_DAYS=100
ARGS=-qwc ARGS=-qwc
if [ ! -d ${DOWNLOAD_DIR} ]; then if [ ! -d "${DOWNLOAD_DIR}" ]; then
echo "Error: directory not found: ${DOWNLOAD_DIR}" echo "Error: directory not found: ${DOWNLOAD_DIR}"
exit # exit
fi fi
OPTIND=1 # Reset is necessary if getopts was used previously OPTIND=1 # Reset is necessary if getopts was used previously
@ -60,41 +60,54 @@ function download_show {
show="$2" show="$2"
mkdir -p "${TMP_DIR}/${show}" mkdir -p "${TMP_DIR}/${show}"
mkdir -p "${DOWNLOAD_DIR}/${show}"
# Get a chosen video format for each site # Get a chosen video format for each site
if [[ "${url}" =~ cc.com ]]; then if [[ "${url}" =~ cc.com ]]; then
FORMAT="1028/907/498/500" #FORMAT="1028/907/498/500"
FORMAT="best[width<=?640]" FORMAT="best[width<=?640]"
elif [[ "${url}" =~ cbs.com ]]; then elif [[ "${url}" =~ cbs.com ]]; then
FORMAT="rtmp-496-0" FORMAT="rtmp-496-0"
elif [[ "${url}" =~ nbc.com ]]; then
FORMAT="best[width<=?640]"
fi
if [ -f "${DOWNLOAD_DIR}/${show}.archive" ]; then
cp "${DOWNLOAD_DIR}/${show}.archive" "${TMP_DIR}/${show}.archive"
fi fi
# Try and download twice (resume if partially downloaded) # Try and download twice (resume if partially downloaded)
for i in 1 2; do for i in 1 2; do
${YOUTUBE_DL} ${ARGS} -f ${FORMAT} \ ${YOUTUBE_DL} ${ARGS} -f ${FORMAT} \
-o "${TMP_DIR}/${show}/%(upload_date)s/%(title)s-%(id)s.%(ext)s" \ -o "${TMP_DIR}/${show}/%(upload_date)s/%(title)s-%(id)s.%(ext)s" \
--download-archive "${DOWNLOAD_DIR}/${show}.archive" \ --download-archive "${TMP_DIR}/${show}.archive" \
${url} ${url}
# Wait 10 minutes before trying again # Wait 10 minutes before trying again
#sleep 600 #sleep 600
cp -nr "${TMP_DIR}/${show}"/* "${DOWNLOAD_DIR}/${show}"/ if [ -d "${DOWNLOAD_DIR}/${show}" ]; then
mkdir -p "${DOWNLOAD_DIR}/${show}"
cp -nr "${TMP_DIR}/${show}"/* "${DOWNLOAD_DIR}/${show}"/
cp "${TMP_DIR}/${show}.archive" "${DOWNLOAD_DIR}/${show}.archive"
fi
done done
# Move files from ${DOWNLOAD_DIR}/The Daily Show/NA/ to ${DOWNLOAD_DIR}/The Daily Show/$date # Move files from ${DOWNLOAD_DIR}/The Daily Show/NA/ to ${DOWNLOAD_DIR}/The Daily Show/$date
while IFS= read -r -d '' file; do if [ -d "${DOWNLOAD_DIR}/${show}"/NA ]; then
dir=$( stat -c %y "$file" | sed -e 's/\([0-9]*\)-\([0-9]*\)-\([0-9]*\).*/\1\2\3/' ); while IFS= read -r -d '' file; do
mkdir -p "${DOWNLOAD_DIR}/${show}/${dir}/" dir=$( stat -c %y "$file" | sed -e 's/\([0-9]*\)-\([0-9]*\)-\([0-9]*\).*/\1\2\3/' );
# Keep a copy in /NA/ to avoid re-downloading mkdir -p "${DOWNLOAD_DIR}/${show}/${dir}/"
cp -n "$file" "${DOWNLOAD_DIR}/${show}/${dir}/" # Keep a copy in /NA/ to avoid re-downloading
done < <(find "${DOWNLOAD_DIR}/${show}/NA" -type f -print0) cp -n "$file" "${DOWNLOAD_DIR}/${show}/${dir}/"
# Remove old copies in /NA/, since we don't need to done < <(find "${DOWNLOAD_DIR}/${show}/NA" -type f -print0)
# worry about re-downloading them any more # Remove old copies in /NA/, since we don't need to
find "${DOWNLOAD_DIR}/${show}/NA/" -mindepth 1 -mtime +7 -delete # worry about re-downloading them any more
find "${DOWNLOAD_DIR}/${show}/NA/" -mindepth 1 -mtime +7 -delete
fi
# Remove old shows # Remove old shows
find "${DOWNLOAD_DIR}/${show}/" -mindepth 1 -mtime +${KEEP_DAYS} -delete if [ -d "${DOWNLOAD_DIR}/${show}" ]; then
find "${DOWNLOAD_DIR}/${show}/" -mindepth 1 -mtime +${KEEP_DAYS} -delete
fi
} }
@ -103,20 +116,25 @@ if [[ -n ${url} ]]; then
show="The Daily Show" show="The Daily Show"
elif [[ "${url}" =~ cbs.com ]]; then elif [[ "${url}" =~ cbs.com ]]; then
show="The Late Show" show="The Late Show"
elif [[ "${url}" =~ nbc.com ]]; then
show="Meet the Press"
fi fi
download_show "${url}" "${show}" download_show "${url}" "${show}"
else else
#for show in "The Daily Show" "The Late Show"; do #for show in "The Daily Show" "The Late Show" "Meet the Press"; do
for show in "The Daily Show"; do for show in "The Daily Show"; do
url= url=
if [[ "${show}" =~ Daily ]]; then if [[ "${show}" =~ Daily ]]; then
url=http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes/ url=http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes/
elif [[ "${show}" =~ Late ]]; then elif [[ "${show}" =~ Late ]]; then
# Get URL from http://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/ # Get URL from http://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/
# Requires Unotelly DNS: # Requires Unlocator/Unotelly DNS
# 197.242.94.51 #url=$( wget -qO- http://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/ | grep -E "/video/[^/]+/" | grep '"url":' | perl -pe 's/.*?"url":"(.*?)".*/$1/ims' | head -1 )
# 197.189.212.164 url=$( wget -qO- http://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/ | grep -Po '"url":.*?[^\\]",' | grep http | perl -pe 's/.*?"url":"(.*?)".*/$1\n/ims' | head -1 )
url=$( wget -qO- http://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/ | grep -E "/video/[^/]+/" | grep '"url":' | perl -pe 's/.*?"url":"(.*?)".*/$1/ims' | head -1 ) elif [[ "${show}" =~ Meet ]]; then
# Get URL from https://www.nbc.com/meet-the-press/episodes
# Note that youtube-dl has a bug on https connections: https://github.com/rg3/youtube-dl/issues/13651
url=$( wget -qO- https://www.nbc.com/meet-the-press/episodes | grep -Po '"permalink":.*?[^\\]",' | perl -pe 's/.*?"permalink":"(.*?)".*/$1\n/ims; s/https/http/g' | head -1 )
fi fi
download_show "${url}" "${show}" download_show "${url}" "${show}"
done done