Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ensure linkcheck pretends to be a browser by sending those headers #18

Merged
merged 1 commit into from
Nov 9, 2018
Merged

Ensure linkcheck pretends to be a browser by sending those headers #18

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 34 additions & 9 deletions linkcheck
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,25 @@ FOLLOW_REDIRECT=""
###
URL_REGEX="http(s)?:\\/\\/[-+%=?&():,._/#0-9a-zA-Z]+"

MY_VERSION="v0.10"
MY_VERSION="v0.11"


###
### Curl defaults
###
### Some sites are very pickey about giving you correct return code if they think
### you are nun human-enough.
### This adds some sane defaults to all curl requests
###
### Note: Additionally 'Host' will be added dynamically
### Host: FQDN of URL
###
CURL_DEFAULTS=""
CURL_DEFAULTS="${CURL_DEFAULTS} -H 'Cache-Control: max-age=0'"
CURL_DEFAULTS="${CURL_DEFAULTS} -H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.89 Safari/537.36'"
CURL_DEFAULTS="${CURL_DEFAULTS} -H 'Accept-Language: en-US,en;q=0.8,en-GB;q=0.6,es;q=0.4'"
CURL_DEFAULTS="${CURL_DEFAULTS} -H 'DNT: 1'"
CURL_DEFAULTS="${CURL_DEFAULTS} -H 'Referer: https://www.google.com'"


############################################################
Expand Down Expand Up @@ -221,6 +239,7 @@ probe_urls() {
local status_codes="${4}"
local insecure_ssl="${5}"
local follow_redirect="${6}"
local host=
local ret_code=0

status_codes="${status_codes//,/|}" # comma to |
Expand All @@ -232,17 +251,23 @@ probe_urls() {
# Probe each url
for url in ${urls}; do

# Determine hostname for Host header
host="$( echo "${url}" | sed 's|^http\(s\)*://||g' | sed 's|/.*$||g' )"

opts="-SsI"
opts="${opts} --retry-delay 2"
opts="${opts} --retry ${retries}"
opts="${opts} --connect-timeout ${timeout}"
opts="${opts} ${insecure_ssl}"
opts="${opts} -H 'Host: ${host}'"
opts="${opts} ${CURL_DEFAULTS}"
opts="${opts} ${follow_redirect}"
#echo "curl ${opts} ${url}"

printf "\\e[0;33m[TEST]\\e[0m %s ..." "${url}"

# Get header from URL
eval "$( curl -SsI \
--retry-delay 2 \
--retry "${retries}" \
--connect-timeout "${timeout}" \
"${insecure_ssl}" \
"${follow_redirect}" \
"${url}" 2> >(setval errval) > >(setval header); <<<"$?" setval retval;
)"
eval "$(eval "curl ${opts} \"${url}\"" 2> >(setval errval) > >(setval header); <<<$? setval retval)";

# Curl request failed
# shellcheck disable=SC2154
Expand Down