Hello manager,
I'm a big fan of web scraper, and thank you for making such great tool.
I recently encountered the following problem while scraping website data.
I want to scrape the company website URL from the companies contact page. But when the company website can't be access, the scrape will stop.
The company list is
To https://clion-ev.en.made-in-china.com/
To YC CLION EV CO., LTD. - Contact Details
To http://www.fortiustruck.com/
For below URL and sitemap, it will stop after scraping 18 data, as the next company website can't be access. Please help, thank you so much.
Url: Auto, Motorcycle Parts & Accessories Manufacturer, Factory & Supplier Directory on Made-in-China.com
Sitemap:
{"_id":"mic-auto-parts","startUrl":["https://www.made-in-china.com/Auto-Parts-Accessories-manufacturers.html"],"selectors":[{"id":"sub-category-url","parentSelectors":["_root"],"type":"SelectorLink","selector":"h3 a","multiple":true,"linkType":"linkFromHref"},{"id":"netx","parentSelectors":["sub-category-url","netx"],"paginationType":"auto","selector":"a.next","type":"SelectorPagination"},{"id":"company","parentSelectors":["netx"],"type":"SelectorLink","selector":".company-name a","multiple":true,"linkType":"linkFromHref"},{"id":"Person1","parentSelectors":["company"],"type":"SelectorText","selector":"div.pic +","multiple":false,"regex":""},{"id":"Telephone1","parentSelectors":["company"],"type":"SelectorText","selector":"div.label:contains(Telephone) +","multiple":false,"regex":""},{"id":"Fax1","parentSelectors":["company"],"type":"SelectorText","selector":"div.label:contains(Fax) +","multiple":false,"regex":""},{"id":"Staff","parentSelectors":["company"],"type":"SelectorText","selector":"div.sr-comProfile-label:contains(Staff)+","multiple":false,"regex":""},{"id":"Account-Registered","parentSelectors":["company"],"type":"SelectorText","selector":"div.label:contains(Registered) +","multiple":false,"regex":""},{"id":"Business-Range","parentSelectors":["company"],"type":"SelectorText","selector":"div.label:contains(Range)+","multiple":false,"regex":""},{"id":"Address1","parentSelectors":["company"],"type":"SelectorText","selector":"div.label:contains(Address) +","multiple":false,"regex":""},{"id":"Person","parentSelectors":["contact-page"],"type":"SelectorText","selector":".sr-sendMsg-avatar + span.sr-sendMsg-name","multiple":false,"regex":""},{"id":"Telephone","parentSelectors":["contact-page"],"type":"SelectorText","selector":"div.info-label:contains(Telephone) +","multiple":false,"regex":""},{"id":"Mobile","parentSelectors":["contact-page"],"type":"SelectorText","selector":"div.info-label:contains(Mobile) +","multiple":false,"regex":""},{"id":"Fax","parentSelectors":["contact-page"],"type":"SelectorText","selector":"div.info-label:contains(Fax)+","multiple":false,"regex":""},{"id":"address","parentSelectors":["contact-page"],"type":"SelectorText","selector":"div.info-label:contains(Address) +","multiple":false,"regex":""},{"id":"click-website","parentSelectors":["contact-page"],"type":"SelectorLink","selector":"a.link-web:contains(Website)","multiple":false,"linkType":"linkFromHref"},{"id":"website","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a","multiple":false,"linkType":"linkFromHref"},{"id":"about","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a[href*="bout"]","multiple":false,"linkType":"linkFromHref"},{"id":"product","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a[href*="roduct"]","multiple":false,"linkType":"linkFromHref"},{"id":"news","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a[href*="ews"]","multiple":false,"linkType":"linkFromHref"},{"id":"contact","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a[href*="ontact"]","multiple":false,"linkType":"linkFromHref"},{"id":"faq","parentSelectors":["click-website"],"type":"SelectorLink","selector":"a[href*="faq"]","multiple":false,"linkType":"linkFromHref"},{"id":"About","parentSelectors":["company"],"type":"SelectorLink","selector":"a[href*="/company-"]","multiple":false,"linkType":"linkFromHref"},{"id":"Staff2","parentSelectors":["About"],"type":"SelectorText","selector":"div.sr-comProfile-label:contains(Staff)+","multiple":false,"regex":""},{"id":"Export-Year","parentSelectors":["About"],"type":"SelectorText","selector":"div.sr-comProfile-label:contains(Year)+","multiple":false,"regex":""},{"id":"Address","parentSelectors":["About"],"type":"SelectorText","selector":"div.sr-comProfile-label:contains(Address)+","multiple":false,"regex":""},{"id":"Main-Products","parentSelectors":["About"],"type":"SelectorText","selector":".info-label-td:contains(Products) +","multiple":false,"regex":""},{"id":"Person2","parentSelectors":["About"],"type":"SelectorText","selector":"div.sr-side-contSupplier-name","multiple":false,"regex":""},{"id":"contact-page","parentSelectors":["About"],"type":"SelectorLink","selector":"a[href*="contact-info"]","multiple":false,"linkType":"linkFromHref"}]}