Infrastructure

# Public site

# bot must follow this rules

# Site scaping is permited IF the user-agent is clearly identify it as a bot and

# the bot owner and is using less than 200 request per minute

# Bot identification must have a owner url or contact if we need to contact them

# Bots with fake user-agent will be blocked

# Bots trying to use too many IPs to increase performance may also be blocked.

# If you need more than 200 RPM, please contact the email techops at jumia com

#

# Sitemap files

Sitemap: https://static.jumia.co.ke/index-sitemap.xml

Sitemap: https://www.jumia.co.ke/slp/nc/sitemap/sitemap.xml


# --- AI Search Bots ---

# GPTBot, ChatGPT-User, OAI-SearchBot, PerplexityBot, ClaudeBot and

# anthropic-ai intentionally have NO group of their own.

#

# Under RFC 9309 2.2.1 a crawler obeys exactly ONE group - the most specific

# one matching its token - and never inherits "User-agent: *". A group such as

#     User-agent: GPTBot

#     Allow: /

# is therefore that crawler's COMPLETE ruleset, and exempts it from every

# facet / crawl-trap rule below. Position in the file is irrelevant.

#

# Letting these tokens fall through to "User-agent: *" is what gives them

# access to real content AND subjects them to the crawl-trap blocks.

# Do not re-add per-bot groups without copying the full ruleset into them.


# Training / grounding opt-in token, not a crawler - has no effect on crawl rate

User-agent: Google-Extended

Allow: /


# Block training-only crawlers

User-agent: CCBot

Disallow: /


# ============ All other crawlers ============

User-agent: *

# multiple brand selectors

Disallow: *--*

Disallow: /mobapi/


# EN Folder

Disallow: /en/

# facets

Disallow: /*ac_design=

Disallow: /*age_group=

Disallow: /*attachment_id=

Disallow: /*app_topsize=

Disallow: /*appbottom_size=

Disallow: /*area_of_use=

Disallow: /*band_material=

Disallow: /*battery=

Disallow: /*beauty_features=

Disallow: /*burners=

Disallow: /*capacity=

Disallow: /*capacity_litres=

Disallow: /*capacity_kg=

Disallow: /*capacity_kva=

Disallow: /*capacity_mah=

Disallow: /*car_scent=

Disallow: /*case_material=

Disallow: /*collection=

Disallow: /*color=

Disallow: /*color_family=

Disallow: /*collar_type=

Disallow: /*compatible_with=

Disallow: /*connection=

Disallow: /*connectivity=

Disallow: /*connexion=

Disallow: /*cookertype=

Disallow: /*cpu_brand=

Disallow: /*cpu_speed=

Disallow: /*diapers_size=

Disallow: /*dir=

Disallow: /*display_features=

Disallow: /*display_size=

Disallow: /*display_type=

Disallow: /*electronics_features=

Disallow: /*fan_type=

Disallow: /*fridge_feet=

Disallow: /*from=

Disallow: /*gender=

Disallow: /*graphics_card=

Disallow: /*graphics_memory=

Disallow: /*grounds=

Disallow: /*hair_type=

Disallow: /*hdd_size=

Disallow: /*heatertype=

Disallow: /*heels_height=

Disallow: /*heel_type=

Disallow: /*horse_power=

Disallow: /*jumia_recommended=

Disallow: /*kettle_material=

Disallow: /*lightingtype=

Disallow: /*machine_type=

Disallow: /*main_material=

Disallow: /*material_family=

Disallow: /*megapixels=

Disallow: /*megapixels_secondary=

Disallow: /*network_supported=

Disallow: /*network_type=

Disallow: /*operating_system=

Disallow: /*optical_zoom=

Disallow: /*paper_size=

Disallow: /*perfume_size=

Disallow: /*perfume_type=

Disallow: /*phone_compatibility=

Disallow: /*power=

Disallow: /*price=

Disallow: /*product_line=

Disallow: /*product_type=

Disallow: /*ram=

Disallow: /*ram_memory=

Disallow: /*rating=

Disallow: /*replytocom=

Disallow: /*rom_stockage=

Disallow: /*school_level=

Disallow: /*screentechnolgy=

Disallow: /*season=

Disallow: /*seller_product=

Disallow: /*seller_score=

Disallow: /*setDevice=

Disallow: /*shipped_from=

Disallow: /*shipped_from_overseas=

Disallow: /*shoe_size=

Disallow: /*sim_number=

Disallow: /*simcard_type=

Disallow: /*skin_type=

Disallow: /*sort=

Disallow: /*sortDirection=

Disallow: /*sortdirection=

Disallow: /*special_price=

Disallow: /*sports_features=

Disallow: /*storage_capacity=

Disallow: /*stove_type=

Disallow: /*style=

Disallow: /*system_memory=

Disallow: /*toys_characters=

Disallow: /*tv_technology=

Disallow: /*viewType=

Disallow: /*washingmachine_type=

Disallow: /*watch_resistance=

Disallow: /*waterdispenser=

Disallow: /*wattage=

Disallow: /*width=

Disallow: /*userSpecific=

Disallow: /*token=


# facets added June 2021

Disallow: /*price_discount=

Disallow: /*return=

Disallow: /*tag=

Disallow: /*shop_premium_services=

Disallow: /*size=

Disallow: /*crosslist_redirect_popin=


# tracking parameters - prevent crawl budget waste on campaign/ad URLs (JMIA-11849)

Disallow: /*?utm_*

Disallow: /*&utm_*

Disallow: /*?gclid=*

Disallow: /*&gclid=*

Disallow: /*?fbclid=*

Disallow: /*&fbclid=*

# site search

Disallow: /*q=

# paths

Disallow: */ur/

Disallow: */assets/

Disallow: */recommendation/

Disallow: */customer/

Disallow: */wishlist/

Disallow: */suggestion/

Disallow: */cart/

Disallow: */catalog/

Disallow: */onepagecheckout/

Disallow: */ratingreview/

Disallow: */index/error/

Disallow: */ajax/reminder/

Disallow: */all-products/

Disallow: */VoucherPage

Disallow: */fragment/

Disallow: /*/all-products/

Disallow: /all-products/*/

Disallow: /flash-sales/*flashsale=


# paths added June 2021

Disallow: */new-products/

Disallow: */special-price/

Disallow: */brands/

Disallow: */top-sellers/

Disallow: */seller/

# allow mobile crawling

Allow:  /catalog/productspecifications/

Allow:  /catalog/productratingsreviews/


#Bypass "--" Rule

Allow: /*.css

Allow: /*.js

Allow: *.png

Allow: /*/*/*/*.css

Allow: *--*.png

Allow: *.jpg

#Allow access to XML Sitemaps

Allow: /slp/nc/sitemap/


#Block Crawling of CSB pages

Disallow: /*/*/*/


#prevent waste crawl budget

Disallow: */generic/

Disallow: */fashion-brand/

Disallow: */universal/

Disallow: */sunshine/

Disallow: */text-book-center

Disallow: */neworldline/

Disallow: */eissely/ 

Disallow: */louis-will/

Disallow: */bluelans/

Disallow: */oem/

Disallow: */muyi/

Disallow: */vakind/

Disallow: */zlime/ 

Disallow: */sanwood/

Disallow: */duoya/

Disallow: */lige/

Disallow: */sunweb/


#Block MLP folders

Disallow: /mlp-*/*/

Disallow: /mlp-*/*page=

Disallow: /sp-*/*/

Disallow: /sp-*/*page=