コンテンツにスキップ

英文维基 | 中文维基 | 日文维基 | 草榴社区

利用者:Bcxfubot/ウェブアーカイブ/prog

# URL張替
# http://web.archive.org/web/
# ↓
# https://web.archive.org/web/
import re
import time
import pywikibot

#target = "http://ameblo.jp/"
target = "http://web.archive.org/web/"
target_https = "https://web.archive.org/web/"
#max = 10
#max = 10
max = 1
sleepsec = 60

######################################################
# 処理モード
#procmode = 0
procmode = 1
######################################################

def replace_page(pagetitle):
    site = pywikibot.Site()
    page = pywikibot.Page(site, pagetitle)
    #text = page.text
    #print(text)
    linelist = page.text.split('\n')
    #print(linelist)

    gaibu = 0
    modflag = 0
    outtext = ""
    for line in linelist:
        #print(gaibu,line)
        #if "==外部リンク" in line:
        #if re.search("==[ ]*外部リンク",line):
        #    gaibu = 1
        #if gaibu == 1:
        if target in line:
            #print(gaibu,line)
            line = line.replace( target, target_https)
            print(gaibu,line)
            modflag = 1
        outtext += line + "\n"

    if modflag == 1:
        page.text = outtext
        if procmode == 1:
            page.save("外部リンクの修正 " + target_https + " ([[Wikipedia:Bot|Bot]]による編集)")

# 処理対象のページ名をひとつ返す
# 処理対象がない場合は""を返す
def get_pagetitle():
    path = "list"
    with open(path) as f:
        for s_line in f:
            s_line = s_line.rstrip("\n")
            #print(s_line)
            #if not re.search(",sumi", s_line):
            if not s_line.endswith(",sumi"):
                return s_line
    return ""

# 処理した行にsumiをつける
def done_pagetitle(pagetitle):
    path = "list"
    alltext = ""
    with open(path) as f:
        for s_line in f:
            s_line = s_line.rstrip("\n")
            #print(s_line + "\n")
            #if re.search(pagetitle, s_line):
            if pagetitle == s_line:
                s_line = s_line + ",sumi"
            alltext += s_line + "\n"
    with open(path, mode='w') as f:
        f.write(alltext)
    return ""

def sub():
    num = 0
    for i in range(max):
        num = num + 1
        pagetitle = get_pagetitle()
        print("[" + str(num) + "/" + str(max) + "]" + ":" + "pagetitle=" + pagetitle)
        if pagetitle == "":
            break
        replace_page(pagetitle)
        done_pagetitle(pagetitle)
        
        if ( i < (max - 1) ):
            print("sleep(" + str(sleepsec) + ")")
            time.sleep(sleepsec)

def main():
    sub()
    print("done.")

if __name__ == '__main__':
    main()