Last active
July 25, 2021 12:30
-
-
Save t2psyto/1d54a7306305ed1d73c148ac80f7802f to your computer and use it in GitHub Desktop.
日経BPビズボードからpdfを取得する
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 日経BPビズボードからpdfを取得する | |
# | |
# required: busybox-w32 | |
# | |
#https://bizboard.nikkeibp.co.jp/simple/parts/search_mag.html | |
#URL: http://bizboard.nikkeibp.co.jp/simple/parts/mag_LIN2020.html | |
#URL: http://bizboard.nikkeibp.co.jp/simple/parts/mag_NSW2020.html | |
# 2020-01号 の記事一覧ページを取得 > _index.html | |
# 例) webページ上のリンク → javascript:funcSearch( '44', '20200101', '0230F'); | |
#set PATH=e:\opt\bin;%PATH% | |
#busybox64 bash | |
ARG1=$1;ARG2=$2;ARG3=$3 | |
echo ARG1=$1 ARG2=$2 ARG3=$3 ${ARG2}_${ARG3}_index.html | |
curl -o ${ARG2}_${ARG3}_index.html 'http://bizboard.nikkeibp.co.jp/simple_notauth/SearchServlet' -H 'Connection: keep-alive' -H 'Cache-Control: max-age=0' -H 'Origin: http://bizboard.nikkeibp.co.jp' -H 'Upgrade-Insecure-Requests: 1' -H 'Content-Type: application/x-www-form-urlencoded' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9' -H 'Referer: http://bizboard.nikkeibp.co.jp/simple/parts/mag.html' -H 'Accept-Language: en-US,en;q=0.9' --data "ACTION=3&ONLINE_MEDIA=%28%40kind%3D%3D1%26%40announcemediaid%3D%3D24%26%40writemediaid%3D%3D${ARG1}%29%26%28%40subsubject%3A%3D${ARG3}%29&SEARCH_START_DATE=${ARG2}&SEARCH_END_DATE=${ARG2}&j_encoding=UTF-8&NO_TERM_SEARCH=1&MAGAZINE_GET_COUNT=100" --insecure | |
# _index.html から pdfファイルへのリンクを抽出 > filelist.txt | |
grep -o -E "http://bizboard.nikkeibp.co.jp/houjin/cgi-bin/nsearch/md_pdf.pl/[0-9]+.pdf\?NEWS_ID=[0-9]+&CONTENTS=1&bt=[A-Z]+&SYSTEM_ID=HO" ${ARG2}_${ARG3}_index.html > ${ARG2}_${ARG3}_filelist.txt | |
# filelist.txt に列挙されたpdfをダウンロード | |
xargs -n 1 -P 4 curl -LOJ -e "http://bizboard.nikkeibp.co.jp/simple_notauth/SearchServlet" < ${ARG2}_${ARG3}_filelist.txt | |
# 念のため filelist.txt と ダウンロード済みpdfファイル数を表示 | |
wc -l ${ARG2}_${ARG3}_filelist.txt | |
ls *pdf* | wc -l | |
# pdfファイルの拡張子をきれいにする; 'xxxxxx.pdf_????????' → 'xxxxxx.pdf' | |
ls *pdf* | xargs -r -n1 -t bash -c 'echo mv \"${0}\" ${0%%.*}.pdf' | bash | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment