Skip to content

Instantly share code, notes, and snippets.

View kiska3's full-sized avatar
💭
I may be slow to respond.

kiska3

💭
I may be slow to respond.
View GitHub Profile
WARC/1.0
WARC-Type: request
WARC-Target-URI: http://static.tumblr.com/vr9xgox/lKbnf8tc5/sidebar-following.png
Content-Type: application/http;msgtype=request
WARC-Date: 2018-12-14T11:39:08Z
WARC-Record-ID: <urn:uuid:0c92740b-134a-496b-a3e3-5c95b358bcd9>
WARC-IP-Address: 152.199.19.43
WARC-Warcinfo-ID: <urn:uuid:d02a4e4c-ac44-4e81-be23-2331528e1674>
WARC-Block-Digest: sha1:KPGRN2MGW6AREHOTHRQVBJFDBFMQQUXH
Content-Length: 257
URI='http://staff.tumblr.com'
UA='ArchiveTeam'
CSRF=$(wget -o log --user-agent ${UA} ${URI} -O - | sed -n 's|.*tumblr_form_key" content="\(.*\)">.*"tumblr-gpop.*|\1|p')
REF='https://www.tumblr.com/privacy/consent?redirect=http%3A%2F%2Fstaff.tumblr.com%2F'
echo "CSRF Token: ${CSRF}"
wget --user-agent "ArchiveTeam" \
--save-cookies cookies.txt \
--referer=${REF} \
--header "Content-Type: application/json" \
--header "X-tumblr-form-key: ${CSRF}" \
# encoding=utf8
import datetime
from distutils.version import StrictVersion
import hashlib
import os.path
import random
from seesaw.config import realize, NumberConfigValue
from seesaw.externalprocess import ExternalProcess
from seesaw.item import ItemInterpolation, ItemValue
from seesaw.task import SimpleTask, LimitConcurrent
@kiska3
kiska3 / tumblr.lua
Last active December 4, 2018 16:27
dofile("table_show.lua")
dofile("urlcode.lua")
local item_type = os.getenv('item_type')
local item_value = os.getenv('item_value')
local item_dir = os.getenv('item_dir')
local warc_file_base = os.getenv('warc_file_base')
local ids = {}