diff --git a/poc.sh b/poc.sh index 6c244f9..21079dd 100644 --- a/poc.sh +++ b/poc.sh @@ -5,12 +5,17 @@ main() { set -e set -o pipefail - local output="${1:-$(mktemp -d)}" log "$output" #set -x + #should_scrape_book_chapter https://www.dndbeyond.com/sources/ai/credits || true + #scrape_book_chapter https://www.dndbeyond.com/sources/ai/credits + + #scrape_book_chapter https://www.dndbeyond.com/sources/ai + #scrape_book_chapter https://www.dndbeyond.com/compendium/rules/ggtr/krenkos-way + #scrape_book_chapter https://www.dndbeyond.com/compendium/rules/ggtr/bestiary #scrape_book_chapter https://www.dndbeyond.com/compendium/rules/ggtr/azorius-senate #scrape_book_chapter https://www.dndbeyond.com/sources/mm/monsters-e #scrape_book_chapter https://www.dndbeyond.com/compendium/rules/dmg/appendix-b-monster-lists @@ -64,6 +69,9 @@ scrape_book() { for chapter in $(list_chapters_in_book "$book_url"); do log scraping book chapter $chapter of $book_url + if ! should_scrape_book_chapter "$chapter"; then + continue + fi scrape_book_chapter "$chapter" > "$f" log scraping book title from $f local title="$(grep '^\#' "$f" | head -n 1 | sed 's/^\#*//' | sed 's/^[ ]*//' | sed 's/[ ]*$//')" @@ -80,10 +88,20 @@ scrape_book() { rm "$output/.wip" } +should_scrape_book_chapter() { + local url="$1" + log foo:should_scrape_book_chapter $url + if scrape_dndbeyond "$url" | grep -i "add to cart" &> /dev/null; then + log "not purchased: $url" + return 1 + fi +} + scrape_book_chapter() { local url="$1" - scrape_dndbeyond $url \ - | html_to_markdown $url + log foo:scrape_book_chapter $url + scrape_dndbeyond "$url" \ + | html_to_markdown "$url" } list_chapters_in_book() { @@ -103,7 +121,37 @@ list_chapters_in_book() { } scrape_dndbeyond() { + log foo:scrape_dndbeyond $@ + local d="${TMPDIR:-/tmp}/scrape_cache" + mkdir -p "$d" + local f="$d/$(echo "$*" | base64)" + if [ -f "$f" ]; then + if cat "$f" | grep .; then + return + fi + fi + _scrape_dndbeyond "$@" | tee "$f" +} + +_scrape_dndbeyond() { + log foo:_scrape_dndbeyond $@ rate_limit_1s scrape_dndbeyond + curl -L -sS "$1" \ + -H 'authority: www.dndbeyond.com' \ + -H 'cache-control: max-age=0' \ + -H 'upgrade-insecure-requests: 1' \ + -H 'user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36' \ + -H 'accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9' \ + -H 'sec-gpc: 1' \ + -H 'sec-fetch-site: none' \ + -H 'sec-fetch-mode: navigate' \ + -H 'sec-fetch-user: ?1' \ + -H 'sec-fetch-dest: document' \ + -H 'accept-language: en-US,en;q=0.9' \ + -H 'cookie: Preferences=undefined; Preferences=undefined; Geo={%22region%22:%22UT%22%2C%22country%22:%22US%22%2C%22continent%22:%22NA%22}; ResponsiveSwitch.DesktopMode=1; sublevel=ANON; Preferences=undefined; ddbSiteBanner:fd981371-c501-4638-a64b-0d9a5c8da68b=true; G_ENABLED_IDPS=google; User.ID=109926924; User.Username=squeaky2x3; Preferences.Language=1; UserInfo={"UserId":109926924,"UserJoinDate":"2021-03-25","UserSessionId":"5993614e-774f-4b55-89de-c88120abea59"}; RequestVerificationToken=6dc61cff-204f-45a0-a39f-edcea6a23072; Preferences.TimeZoneID=1; LoginState=aa3ada1f-7ab9-4804-a177-858bd2b4d693; CobaltSession=eyJhbGciOiJkaXIiLCJlbmMiOiJBMTI4Q0JDLUhTMjU2In0..ZYTOkNPFaI619J4f0rSamg.Wu7iDGvwCv-S2uiAftwHIienWEyGno2diWV6KU_KMnjzJGog2bIr8XorEpMshuGW.GN5g3TsaP_jm0d3THUnftA; ddbSiteBanner:d7e00153-5c1f-442c-a584-b3b814abc854=true; AWSELB=17A593B6CA59C3C4856B812F84CD401A582EF083E14A2E133FB99235E1D3CC671549BC8DF3DD0A01DD4815C023F988F55E0E9527B680F5A93AEBF8E5ADAA49A8F75A9276; AWSELBCORS=17A593B6CA59C3C4856B812F84CD401A582EF083E14A2E133FB99235E1D3CC671549BC8DF3DD0A01DD4815C023F988F55E0E9527B680F5A93AEBF8E5ADAA49A8F75A9276; _pxhd=fFcuMtI4ivDtBeMpMP/C7iQM0Tq6VQ3S7Ez2cFTQR3660-FAmmxJN1nf10BpNrlWlqlcOEbI4RNwUBHISjoo/A==:daB4hDYpQC3vi3ldLNM4PFvrSLt41cDr81ohF5gDoCaFGENWNSNvkbM9u5BjZ2zgHKWbzxAz4B0PTu0FnstnbJzhd3uPJGcXecasPyv7C04=; WarningNotification.Lock=1' \ + -H 'dnt: 1' \ + --compressed + return curl -L -sS \ "$1" \ --compressed \ @@ -124,7 +172,7 @@ scrape_dndbeyond() { -H 'TE: trailers'; } -html_to_markdown() { +url_to_title_candidate() { local url="${1%#*}" url="${url%/}" local url_title_candidate="${url##*/}" @@ -133,9 +181,21 @@ html_to_markdown() { | tr '[:upper:]' '[:lower:]' \ | sed 's/[^a-z]/./g' )" + local with_wildcards=".*" + for i in $(seq 0 ${#url_title_candidate}); do + with_wildcards+=${url_title_candidate:$i:1} + with_wildcards+=".*" + done + url_title_candidate="$with_wildcards" + echo "$url_title_candidate" +} + +html_to_markdown() { + local url_title_candidate="$(url_to_title_candidate "$1")" + local url_title_candidate_2="$(url_to_title_candidate "$(dirname "$1")")" local out="$( pandoc -f html -t markdown --ascii --toc --wrap=none --strip-comments -o - \ - | sed '/^:::.*/d' \ + | sed '/^[ ]*:::.*/d' \ | sed -e '/^Share$/,$d' \ | sed 's/^\(\#\#*\) \[](#\([^)]*\))/\1 /' \ | sed 's/{#\([^ ]*\)[^}]*}/\n\n<\/a>/' \ @@ -143,30 +203,31 @@ html_to_markdown() { | sed "s/\\\\\([\"']\)/\1/g" )" local target="$( - if echo "$out" | grep '^##* Appendix' &> /dev/null; then + if echo "$out" | grep '^# Appendix' &> /dev/null; then echo Appendix - elif echo "$out" | grep '^##* Chapter' &> /dev/null; then + elif echo "$out" | grep '^# Chapter' &> /dev/null; then echo Chapter - elif echo "$out" | grep '^##* Preface' &> /dev/null; then + elif echo "$out" | grep '^# Preface' &> /dev/null; then echo Preface - elif echo "$out" | grep '^##* Introduction' &> /dev/null; then + elif echo "$out" | grep '^# Introduction' &> /dev/null; then echo Introduction - elif echo "$out" | grep '^##* Credits' &> /dev/null; then + elif echo "$out" | grep '^# Credits' &> /dev/null; then echo Credits - elif echo "$out" | grep '^##* Monsters' &> /dev/null; then + elif echo "$out" | grep '^# Monsters' &> /dev/null; then echo Monsters - elif echo "$out" | grep -i '^##* '"$url_title_candidate" &> /dev/null; then - target="$(echo "$out" | grep -i '^##* '"$url_title_candidate" | sed 's/^\#\#*[ ]*//' | head -n 1)" + elif echo "$out" | grep -i '^# '"$url_title_candidate" &> /dev/null; then + target="$(echo "$out" | grep -i '^# '"$url_title_candidate" | sed 's/^\#[ ]*//' | head -n 1)" log WARNING: URL title candidate $target echo "$target" else - log WARNING: NOTHING INDICITIVE OF TYPE OF CONTENT FOUND + log WARNING: NOTHING INDICITIVE OF TYPE OF CONTENT FOUND, including matching $url_title_candidate echo "$out" | grep '^#' | while read -r line; do log candidate="$line" done echo Chapter fi )" + log target=$target echo "$out" \ | sed -e '/^# '"$target"'/p' -e '0,/^# '"$target"'/d' }