Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
Added TODO
Jan Curn9541f612fa91
diff --git a/src/utils_social.js b/src/utils_social.jsindex 9731d39da..db33d55b9 100644--- a/src/utils_social.js+++ b/src/utils_social.js@@ -188,7 +188,7 @@ const phonesFromUrls = (urls) => {// eslint-disable-next-line max-lenconst LINKEDIN_REGEX_STRING = '(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:(?:[a-z]+\\.)?linkedin\\.com\\/in\\/)([a-z0-9\\-_%]{2,60})(?![a-z0-9\\-_%])(?:/)?';-// TODO: Skip https://www.instagram.com/explore/ !!!+// TODO: Skip https://www.instagram.com/explore/ !!! and "https://www.instagram.com/_n/", "https://www.instagram.com/_u/"// eslint-disable-next-line max-lenconst INSTAGRAM_REGEX_STRING = '(?<!\\w)(?:http(?:s)?:\\/\\/)?(?:(?:www\\.)?(?:instagram\\.com|instagr\\.am)\\/)([a-z0-9_.]{2,30})(?![a-z0-9_.])(?:/)?';