$echo '{
< "startUrls": [
< {
< "url": "https://crawlee.dev"
< }
< ],
< "maxCrawlingDepth": 1,
< "requestTimeout": 10,
< "linkSelector": "a[href]",
< "linkPatterns": [
< ".*crawlee\\\\.dev.*"
< ],
< "pageFunction": "from typing import Any\\nfrom crawlee.crawlers import BeautifulSoupCrawlingContext\\n\\n# See the context section in readme to find out what fields you can access \\n# https://apify.com/apify/beautifulsoup-scraper#context \\ndef page_function(context: BeautifulSoupCrawlingContext) -> Any:\\n url = context.request.url\\n title = context.soup.title.string if context.soup.title else None\\n return {'\''url'\'': url, '\''title'\'': title}\\n",
< "soupFeatures": "html.parser",
< "proxyConfiguration": {
< "useApifyProxy": true
< }
<}' |
<apify call apify/beautifulsoup-scraper --silent --output-dataset