Created
May 12, 2014 12:02
-
-
Save gear11/a2370485f7b24be264c7 to your computer and use it in GitHub Desktop.
wp-download configuration for downloading just the English article text.
This file contains hidden or 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
# wpdownloadrc.sample | |
# | |
# This file specifies which files should be downloaded from wikimedia | |
# | |
# Copy it to ~/.wpdownloadrc and adjust it to fit your needs. | |
[Configuration] | |
# base_url (string) | |
# ----------------- | |
# Base URL where wikipedia xml/sql dumps can be downloaded | |
base_url = http://dumps.wikimedia.org | |
[Templates] | |
# file_format (string) | |
# -------------------- | |
# File format string. | |
# | |
# You can use the following placeholders, which will be expanded later on: | |
# | |
# - ${langcode} The language code, like de, en, ... | |
# - ${date} The dump creation date, like 20090710, ... | |
# - $filename} The actual filename, like pages_articles, pagelinks, ... | |
# - ${filetype} The filetype, like sql.gz, xml.bz2, ... | |
# | |
# The given format string would for example expand to: | |
# | |
# dewiki-20090710-redirect.sql.gz | |
# | |
file_format = ${langcode}wiki-${date}-${filename}.${filetype} | |
# language_dir_format | |
# ------------------- | |
# The format of the directories for each language within base_url. | |
# | |
# You can use the following placeholders: | |
# | |
# - ${langcode} The language code, like de, en, ... | |
# | |
# The given format string would for example expand to: | |
# | |
# dewiki | |
language_dir_format = ${langcode}wiki | |
[Files] | |
# Specify which files to download | |
# pages_articles (boolean) | |
# ------------------------ | |
# pages_articles contains current versions of article content, and is the | |
# archive most mirror sites will probably want. | |
pages-articles = True | |
# redirect (boolean) | |
# ------------------ | |
# Redirect list | |
redirect = False | |
# page (boolean) | |
# -------------- | |
# Base per-page data (id, title, old restrictions, etc). | |
page = False | |
# category (boolean) | |
# ------------------ | |
# Category information | |
category = False | |
# interwiki (boolean) | |
# ------------------- | |
# Set of defined interwiki prefixes and links for this wiki. | |
interwiki = False | |
# langlinks (boolean) | |
# ------------------- | |
# Wiki interlanguage link records. | |
langlinks = False | |
# externallinks (boolean) | |
# ----------------------- | |
# Wiki external URL link records. | |
externallinks = False | |
# templatelinks (boolean) | |
# ----------------------- | |
# Wiki template inclusion link records. | |
templatelinks = False | |
# imagelinks (boolean) | |
# -------------------- | |
# Wiki image usage records. | |
imagelinks = False | |
# categorylinks (boolean) | |
# ----------------------- | |
# Wiki category membership link records. | |
categorylinks = False | |
# pagelinks (boolean) | |
# ------------------- | |
# Wiki page-to-page link records. | |
pagelinks = False | |
# site_stats (boolean) | |
# -------------------- | |
# A few statistics such as the page count. | |
site_stats = False | |
[Filetypes] | |
pages-articles = xml.bz2 | |
redirect = sql.gz | |
page = sql.gz | |
category = sql.gz | |
interwiki = sql.gz | |
langlinks = sql.gz | |
externallinks = sql.gz | |
templatelinks = sql.gz | |
imagelinks = sql.gz | |
categorylinks = sql.gz | |
pagelinks = sql.gz | |
site_stats = sql.gz | |
[Languages] | |
#aa = True | |
#ab = True | |
#af = True | |
#ak = True | |
#als = True | |
#am = True | |
#ang = True | |
#an = True | |
#arc = True | |
#ar = True | |
#arz = True | |
#ast = True | |
#as = True | |
#av = True | |
#ay = True | |
#az = True | |
#bar = True | |
#bat_smg = True | |
#ba = True | |
#bcl = True | |
#be = True | |
#be_x_old = True | |
#bg = True | |
#bh = True | |
#bi = True | |
#bm = True | |
#bn = True | |
#bo = True | |
#bpy = True | |
#br = True | |
#bs = True | |
#bug = True | |
#bxr = True | |
#ca = True | |
#cbk_zam = True | |
#cdo = True | |
#ceb = True | |
#ce = True | |
#cho = True | |
#chr = True | |
#ch = True | |
#chy = True | |
#co = True | |
#crh = True | |
#cr = True | |
#csb = True | |
#cs = True | |
#cu = True | |
#cv = True | |
#cy = True | |
#da = True | |
#de = True | |
#diq = True | |
#dsb = True | |
#dv = True | |
#dz = True | |
#ee = True | |
#el = True | |
#eml = True | |
en = True | |
#eo = True | |
#es = True | |
#et = True | |
#eu = True | |
#ext = True | |
#fa = True | |
#ff = True | |
#fiu_vro = True | |
#fi = True | |
#fj = True | |
#fo = True | |
#frp = True | |
#fr = True | |
#fur = True | |
#fy = True | |
#gan = True | |
#ga = True | |
#gd = True | |
#glk = True | |
#gl = True | |
#gn = True | |
#got = True | |
#gu = True | |
#gv = True | |
#hak = True | |
#ha = True | |
#haw = True | |
#he = True | |
#hif = True | |
#hi = True | |
#ho = True | |
#hr = True | |
#hsb = True | |
#ht = True | |
#hu = True | |
#hy = True | |
#hz = True | |
#ia = True | |
#id = True | |
#ie = True | |
#ig = True | |
#ii = True | |
#ik = True | |
#ilo = True | |
#io = True | |
#is = True | |
#it = True | |
#iu = True | |
#ja = True | |
#jbo = True | |
#jv = True | |
#kaa = True | |
#kab = True | |
#ka = True | |
#kg = True | |
#ki = True | |
#kj = True | |
#kk = True | |
#kl = True | |
#km = True | |
#kn = True | |
#ko = True | |
#kr = True | |
#ksh = True | |
#ks = True | |
#ku = True | |
#kv = True | |
#kw = True | |
#ky = True | |
#lad = True | |
#la = True | |
#lbe = True | |
#lb = True | |
#lg = True | |
#lij = True | |
#li = True | |
#lmo = True | |
#ln = True | |
#lo = True | |
#lt = True | |
#lv = True | |
#map_bms = True | |
#mdf = True | |
#mg = True | |
#mhr = True | |
#mh = True | |
#mi = True | |
#mk = True | |
#ml = True | |
#mn = True | |
#mo = True | |
#mr = True | |
#ms = True | |
#mt = True | |
#mus = True | |
#myv = True | |
#my = True | |
#mzn = True | |
#nah = True | |
#nap = True | |
#na = True | |
#nds_nl = True | |
#nds = True | |
#ne = True | |
#new = True | |
#ng = True | |
#nl = True | |
#nn = True | |
#nov = True | |
#no = True | |
#nrm = True | |
#nv = True | |
#ny = True | |
#oc = True | |
#om = True | |
#or = True | |
#os = True | |
#pag = True | |
#pam = True | |
#pap = True | |
#pa = True | |
#pdc = True | |
#pih = True | |
#pi = True | |
#pl = True | |
#pms = True | |
#pnt = True | |
#ps = True | |
#pt = True | |
#qu = True | |
#rm = True | |
#rmy = True | |
#rn = True | |
#roa_rup = True | |
#roa_tara = True | |
#ro = True | |
#ru = True | |
#rw = True | |
#sah = True | |
#sa = True | |
#scn = True | |
#sco = True | |
#sc = True | |
#sd = True | |
#se = True | |
#sg = True | |
#sh = True | |
#simple = True | |
#si = True | |
#sk = True | |
#sl = True | |
#sm = True | |
#sn = True | |
#so = True | |
#sq = True | |
#srn = True | |
#sr = True | |
#ss = True | |
#stq = True | |
#st = True | |
#su = True | |
#sv = True | |
#sw = True | |
#szl = True | |
#ta = True | |
#tet = True | |
#te = True | |
#tg = True | |
#th = True | |
#ti = True | |
#tk = True | |
#tl = True | |
#tn = True | |
#tokipona = True | |
#to = True | |
#tpi = True | |
#tr = True | |
#ts = True | |
#tt = True | |
#tum = True | |
#tw = True | |
#ty = True | |
#udm = True | |
#ug = True | |
#uk = True | |
#ur = True | |
#uz = True | |
#vec = True | |
#ve = True | |
#vi = True | |
#vls = True | |
#vo = True | |
#war = True | |
#wa = True | |
#wo = True | |
#wuu = True | |
#xal = True | |
#xh = True | |
#yi = True | |
#yo = True | |
#za = True | |
#zea = True | |
#zh_classical = True | |
#zh_min_nan = True | |
#zh = True | |
#zh_yue = True | |
#zu = True |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment