spb/datacenterindex

1# ERCOT — news releases — connector definition (see docs/connectors/ercot.md)2id: ercot3name: "ERCOT — news releases"4domain: www.ercot.com5kind: utility6mode: html7priority: 28license: "Public information of the Electric Reliability Council of Texas; facts and links only"9attribution: "Electric Reliability Council of Texas (ercot.com)"10homepage: https://www.ercot.com/11notes: "Texas grid operator. Releases on large-load interconnection (Batch Zero / PGRR145), long-term load forecasts and PUCT approvals. Pages carry no date markup: the MMDDYYYY prefix of the slug is the release date. The Large Load Interconnection Status report itself lives on MIS paths that robots.txt disallows (/misapp, /misdownload) and is NOT fetched."12coverage: { countries: ["US"] }13fetch:14  level: 115  maxLevel: 216  rpm: 1017  concurrency: 118  respectRobots: true19  maxCreditsPerRun: 020discovery:21  seeds:22    - { url: "/news/releases", group: seed, pageType: news_index }23  # the index shows the current year; ?year=YYYY lists earlier years (backfill)24  pagination: { template: "?year={n}", start: 2024, max: 2026 }25  follow: ["^https://www\\.ercot\\.com/news/release/[a-z0-9-]+$"]26  include: ["/news/release/[a-z0-9-]+$"]27  exclude: ["/content/", "/misapp", "/misdownload"]28  classify:29    - { pattern: "/news/release/[a-z0-9-]+$", group: newsroom, pageType: press_release, priority: 70 }30schedule:31  newsroom: daily32  seed: daily33extractors:34  news:35    pageTypes: [press_release, project_announcement, expansion, acquisition, construction_update, planning_document, power_infrastructure, utility_announcement, closure, cloud_region, financial_disclosure, facility_page, operator_page, unknown]36    kind: news_event37    parser: news_press_release_v138    params: { keepText: true, urlDate: "/news/release/(?<m>\\d{2})(?<d>\\d{2})(?<y>\\d{4})-" }39