Last active
April 19, 2024 21:05
-
-
Save matheusfillipe/b90710104ecb57bed83438104c1b77ad to your computer and use it in GitHub Desktop.
Metacritic scrapper with bash and htmlq
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
#!/usr/bin/env bash | |
query="Final%20Fantasy" | |
user_agent='user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36' | |
results=$(curl "https://www.metacritic.com/search/$query/?page=1&category=3" -H "$user_agent" | htmlq 'div.c-pageSiteSearch-results a' -a href | xargs printf "https://www.metacritic.com%s\n" % '_') | |
item () { | |
name="$1" | |
selector="$2" | |
body="$3" | |
echo "$body" | htmlq "$selector" -t | tr -d '\n' | xargs -I '_' printf "%s: %s\n" "$name" '_' | |
} | |
for result in $results; do | |
echo "URL: $result" | |
body="$(curl --silent "$result" -H "$user_agent")" | |
item "Title" 'div.c-productHero_title h1' "$body" | |
item "Platform" 'div.c-productHero_score-container div.c-ProductHeroGamePlatformInfo title' "$body" | |
item "Release Date" 'div.c-productHero_score-container div.g-text-xsmall span.u-text-uppercase' "$body" | |
item "Meta Score" 'div.c-productScoreInfo_scoreNumber div.c-siteReviewScore_background-critic_medium span' "$body" | |
item "User Score" 'div.c-productScoreInfo_scoreNumber div.c-siteReviewScore_background-user span' "$body" | |
echo "--------------------------------------------------------------------------------" | |
echo | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment