Closed suzuhiroruri closed 4 months ago
It's their aggressive use of Cloudflare. You can try using the CDP scraper below.
name: "XsList (JAV)"
performerByName:
action: scrapeXPath
queryURL: https://xslist.org/search?query={}&lg=en
scraper: performerSearch
performerByURL:
- action: scrapeXPath
url:
- xslist.org/en/model/
scraper: performerScraper
xPathScrapers:
performerSearch:
performer:
Name: //li[@class="clearfix"]/h3/a/@title
URL:
selector: //li[@class="clearfix"]/h3/a/@href
performerScraper:
performer:
Name:
selector: //span[@itemprop="name"]/text()
#Uncomment below to convert to Surname Name (JavLibrary compatible)
#postProcess:
# - replace:
# - regex: (.+)(\s)(.+)
# with: $3$2$1
Aliases:
selector: //span[@itemprop="additionalName"]/text()|//div[@id="layout"]/div/h2[1]/text()
concat: ", "
postProcess:
- replace:
- regex: "(.+)( \\b[a-zA-Z]+\\s\\b[a-zA-Z]+)(.+?)([\\p{Han}\\p{Hiragana}\\p{Katakana}ー]+)(.+)"
with: $4, $1
- regex: "(\\b.+?|)([\\p{Han}\\p{Hiragana}\\p{Katakana}ー]+)(.+)(Profile)(.+)|(.+)"
with: $2$6
- regex: ^,|,$
with:
URL: //head/meta[@property="og:url"]/@content
Birthdate:
selector: //div[@id="layout"]/div/p[1]/text()[not(contains(.,"n/a")) and contains(.,"Born")]
postProcess:
- replace:
- regex: (Born:\s)(.+)
with: $2
- parseDate: January 2, 2006
Height:
selector: //span[@itemprop="height"]/text()[not(contains(.,"n/a"))]
postProcess:
- replace:
- regex: "cm"
with: ""
Measurements:
selector: //div[@id="layout"]/div/p[1]/text()[not(contains(.,"n/a")) and contains(.,"Measurements")]|//div[@id="layout"]/div/p[1]/text()[not(contains(.,"n/a")) and contains(.,"Cup Size")]
concat: "|"
postProcess:
- replace:
- regex: (.+:\s\w)(\d*)(\s\/\s.?)(\d*)(\s\/\s.?)(\d*)(.+:\s)(\w*)(\s.*)
with: $2$8-$4-$6
- regex: "Measurements: B|W|H|\\s"
with: ""
- regex: "CupSize:|Cup"
with: ""
- regex: \/
with: "-"
CareerLength:
selector: //div[@id="layout"]/div/p[1]/text()[not(contains(.,"n/a")) and contains(.,"AV Activity")]
postProcess:
- replace:
- regex: (.+)(\d{4})
with: $2
Image: //a[@class="gallery-item gallery-jpg" and number(@data-height)>number(@data-width)][1]/@href|//img[@class='profile_img']/@src
Ethnicity:
fixed: "asian"
Country:
fixed: "Japan"
Gender:
fixed: "Female"
driver:
useCDP: true
# Last Updated August 20, 2020
Also, there is https://github.com/stashapp/CommunityScrapers/issues/123 for reporting broken scrapers.
403 error