Hi!
I am pretty new to scraping and just getting into it for university. I think I got everything to run fine, I can get all the data I want, but now my problem is that when i try to scrape more than around 90 datasets I get the Chrome Error "ERR_TOO_MANY_REDIRECTS". I thought I had a problem with my pagination (maybe a loop) and changed the method to the dynamic URL and not via the element click selector. This didn't help. Clearing cookies and the cache only fixes it to the degree that I can scrape for another 90 datasets and then get the same error. Did anyone have the same problems? I am supposed to scrape around 12.000 datasets and doing this in steps that small would be not something I prefer
I would appreciate the help if someone has an idea how I can fix this, thank you very much!
Url: upwork.com
Sitemap:
{"_id":"rettungstest","startUrl":["https://www.upwork.com/o/jobs/browse/?page=[2-26]&q="long%20time"&sort=recency"],"selectors":[{"id":"posts","type":"SelectorLink","parentSelectors":["_root"],"selector":"a.job-title-link","multiple":true,"delay":0},{"id":"JobTitle","type":"SelectorText","parentSelectors":["posts"],"selector":".content h2","multiple":false,"regex":"","delay":0},{"id":"JobCategory","type":"SelectorText","parentSelectors":["posts"],"selector":"a.specialization","multiple":false,"regex":"","delay":0},{"id":"Description","type":"SelectorText","parentSelectors":["posts"],"selector":".job-description div","multiple":false,"regex":"","delay":0},{"id":"ClientCountry","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:nth-of-type(1) strong","multiple":false,"regex":"","delay":0},{"id":"ClientCity","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:nth-of-type(1) span:nth-of-type(1)","multiple":false,"regex":"","delay":0},{"id":"ClientMoneySpent","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("spent") strong","multiple":false,"regex":"","delay":0},{"id":"ClientHireRate","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("hire rate") div","multiple":false,"regex":"","delay":0},{"id":"PrefExperience","type":"SelectorText","parentSelectors":["posts"],"selector":".job-features li:contains("level") strong","multiple":false,"regex":"","delay":0},{"id":"ProjectType","type":"SelectorText","parentSelectors":["posts"],"selector":".m-md-top .justify-xs-md:contains("Project Type") span","multiple":false,"regex":"","delay":0},{"id":"prefSkills","type":"SelectorText","parentSelectors":["posts"],"selector":"section.air-card-divider-sm:contains("Skills") ","multiple":false,"regex":"","delay":0},{"id":"prefEnglishLevel","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("English")","multiple":false,"regex":"","delay":0},{"id":"prefUpworkHours","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Upwork")","multiple":false,"regex":"","delay":0},{"id":"prefSuccessScore","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Success")","multiple":false,"regex":"","delay":0},{"id":"prefFreelancerType","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Freelancer")","multiple":false,"regex":"","delay":0},{"id":"ProjectLength","type":"SelectorText","parentSelectors":["posts"],"selector":".job-features li:contains("Length") strong","multiple":false,"regex":"","delay":0},{"id":"ProjectHours","type":"SelectorText","parentSelectors":["posts"],"selector":".job-features li:contains("Hourly") strong","multiple":false,"regex":"","delay":0},{"id":"ClientAVGRatePaid","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("paid") strong","multiple":false,"regex":"","delay":0},{"id":"ClientHires","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("hires") div","multiple":false,"regex":"","delay":0},{"id":"ClientHours","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("hours") div","multiple":false,"regex":"","delay":0},{"id":"ProjectFixedPrice","type":"SelectorText","parentSelectors":["posts"],"selector":".job-features li:contains("Fixed") strong","multiple":false,"regex":"","delay":0},{"id":"prefLocation","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Location") ","multiple":false,"regex":"","delay":0},{"id":"NumberOfFreelancers","type":"SelectorText","parentSelectors":["posts"],"selector":".air-card-divider-sm strong:contains("Needs to hire")","multiple":false,"regex":"","delay":0},{"id":"ClientReviews","type":"SelectorText","parentSelectors":["posts"],"selector":".rating span.nowrap","multiple":false,"regex":"","delay":0},{"id":"ClientMemberSince","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("Member since") ","multiple":false,"regex":"","delay":0},{"id":"ClientPaymentVerified","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar div:contains("method") strong","multiple":false,"regex":"","delay":0},{"id":"ClientNumberOfJobs","type":"SelectorText","parentSelectors":["posts"],"selector":".sidebar li:contains("jobs posted") strong","multiple":false,"regex":"","delay":0},{"id":"ActivityProposals","type":"SelectorText","parentSelectors":["posts"],"selector":".list-unstyled li:contains("Proposals:") ","multiple":false,"regex":"","delay":0},{"id":"prefGroup","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Group")","multiple":false,"regex":"","delay":0},{"id":"ProposalQuestions","type":"SelectorText","parentSelectors":["posts"],"selector":"ol.break ","multiple":false,"regex":"","delay":0},{"id":"prefRisingTalent","type":"SelectorText","parentSelectors":["posts"],"selector":"div.col-lg-6:contains("qualifications") li:contains("Rising")","multiple":false,"regex":"","delay":0},{"id":"ActivityInterviewing","type":"SelectorText","parentSelectors":["posts"],"selector":".list-unstyled li:contains("Interviewing:") ","multiple":false,"regex":"","delay":0},{"id":"ActivityInvites","type":"SelectorText","parentSelectors":["posts"],"selector":".list-unstyled li:contains("Invites sent:") ","multiple":false,"regex":"","delay":0},{"id":"ActivityUnansweredInvites","type":"SelectorText","parentSelectors":["posts"],"selector":".list-unstyled li:contains("Unanswered") ","multiple":false,"regex":"","delay":0},{"id":"ActivityLastViewed","type":"SelectorText","parentSelectors":["posts"],"selector":".list-unstyled li:contains("viewed") ","multiple":false,"regex":"","delay":0}]}