go directly to xml for youtube, print out current BC channel

This commit is contained in:
Alexander Bocken 2021-01-08 20:21:24 +01:00
parent 553bdff07d
commit c315f9c021
Signed by: Alexander
GPG Key ID: 1D237BE83F9B05E8

8
ripper
View File

@ -66,7 +66,7 @@ for channel_id in $IDs; do
LEGACYMODE=1 LEGACYMODE=1
fi fi
elif [ -n "$LEGACYMODE" ];then elif [ -n "$LEGACYMODE" ];then
lynx --dump --nonumbers -listonly "https://www.youtube.com/channel/$channel_id" | grep 'videos.xml' | xargs curl -s > /tmp/"${channel_id}.xml" curl -s "https://www.youtube.com/feeds/videos.xml?channel_id=$channel_id"> /tmp/"${channel_id}.xml"
python -c "from lxml import etree python -c "from lxml import etree
file=\"/tmp/${channel_id}.xml\" file=\"/tmp/${channel_id}.xml\"
root = etree.parse(file) root = etree.parse(file)
@ -84,7 +84,11 @@ grep 'youtube' "$DLARCHIVE" | sed 's/youtube /https:\/\/www\.youtube\.com\/watch
##BITCHUTE ##BITCHUTE
#This section is quite generic and could probably be easily adapted for other video hosting websites #This section is quite generic and could probably be easily adapted for other video hosting websites
echo "Scanning on Bitchute..." echo "Scanning on Bitchute..."
grep 'bitchute' "$CHANNELSFILE" | grep -v '^#' | xargs -L1 lynx --dump --nonumbers -listonly | grep 'bitchute\.com\/video' | sort -u | grep -vf "$BLACKLIST" >> /tmp/todownload$$ BC_CHANNELS="$(grep 'bitchute' "$CHANNELSFILE" | grep -v '^#')"
for channel in $BC_CHANNELS; do
printf 'BC channel: %s\n' "$( echo "$channel" | sed 's|https://www.bitchute.com/channel/||; s|/||')"
lynx --read_timeout=5 --dump --nonumbers -listonly "$channel"| grep 'bitchute\.com\/video' | sort -u | grep -vf "$BLACKLIST" >> /tmp/todownload$$
done
grep 'bitchute' "$DLARCHIVE" | sed 's/bitchute /https:\/\/www\.bitchute\.com\/video\//' >> /tmp/alreadydownloaded$$ grep 'bitchute' "$DLARCHIVE" | sed 's/bitchute /https:\/\/www\.bitchute\.com\/video\//' >> /tmp/alreadydownloaded$$
##DOWNLOAD VIDEOS FROM ACCUMULATED LINKS ##DOWNLOAD VIDEOS FROM ACCUMULATED LINKS