ZMediumToMarkdown 3.3.3 → 3.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 97751da25df535110c1771b77a009171f82bd761ff74a5948927a349d06358a0
-  data.tar.gz: e8063778d0980fc394ff52fb9f0e1caeb59578915e812881da385b8a4f2b0fe3
+  metadata.gz: 41871cb0a57ded38ba5b49cbe98b19ffa8f963b4425d0bf6a0e8597f305fcbc3
+  data.tar.gz: 555122d0f62b4434462200240910ed5fed97db9bebc7f54bc1b2b73a308b6702
 SHA512:
-  metadata.gz: f53c5d05e53b7ed984f65e908eef65b0fdab7606e740871c8639816eb32422d47d87c75b4f2f368f8aa6e89add6b531a818f977045a1af88e720757c1a386e24
-  data.tar.gz: fc8dff70656090f4d5ce5790aadadd4fea82ac2da5989979c1c9c2fe1edb36514b5ea8027652d13dff695ad7ba080e281dab822d3b4078afd4347b457b889b25
+  metadata.gz: 8f4b1e85672bbb3f24b2fcc7ab7f4e21455eb76dced1abefde45479fc5cce31a0ad928c73a08e34733ea8c0f1913073f547fa3bfaceeab10d3e17aed4d6e0711
+  data.tar.gz: 915db5d26bc3f78a67fd1d58cc858364f69f4cb5830527213ccefbc7d48911469c6a326367a476ea6d8ecb7da69978ac76fccd2f72f600e0fbcbcc6707615f09

data/lib/Request.rb

@@ -1,5 +1,6 @@
 require 'net/http'
 require 'nokogiri'
+require 'uri'
 require 'ChromeAuth'
 require 'CookieCache'
 
@@ -173,6 +174,7 @@ class Request
 
     def self.URL(url, method = 'GET', data = nil, retryCount = 0)
         retryCount += 1
+        url = mediumProxiedURL(url)
 
         uri = URI(url)
         https = Net::HTTP.new(uri.host, uri.port)
@@ -277,6 +279,32 @@ class Request
         response
     end
 
+    # If the user has configured a Cloudflare Worker proxy via MEDIUM_HOST,
+    # rewrite *any* https://medium.com/<path> URL to <worker-origin>/<path>
+    # so non-GraphQL hits (iframe metadata at /media/<id>, OG-image fallback
+    # to /<user>/<post>, etc.) also benefit from the proxy. GraphQL callers
+    # already hand us the proxy URL directly via ENV['MEDIUM_HOST'], so they
+    # short-circuit the rewrite.
+    def self.mediumProxiedURL(url)
+        return url unless url.is_a?(String) && url.start_with?('https://medium.com/')
+        origin = mediumProxyOrigin
+        return url if origin.nil?
+        url.sub(%r{\Ahttps://medium\.com}, origin)
+    end
+
+    # Extract the `<scheme>://<host>[:port]` of MEDIUM_HOST, or nil if no
+    # proxy is configured (or it still points at medium.com itself).
+    def self.mediumProxyOrigin
+        host = ENV['MEDIUM_HOST'].to_s
+        return nil if host.empty?
+        uri = URI.parse(host)
+        return nil if uri.host.nil? || uri.host == 'medium.com'
+        port = (uri.port && uri.port != uri.default_port) ? ":#{uri.port}" : ''
+        "#{uri.scheme}://#{uri.host}#{port}"
+    rescue URI::InvalidURIError
+        nil
+    end
+
     # Cloudflare tags blocked responses via either the cf-mitigated header
     # or the standard "Just a moment..." challenge HTML. We check both
     # so we catch challenges even on Cloudflare deployments that don't

data/lib/ZMediumFetcher.rb

@@ -153,9 +153,7 @@ class ZMediumFetcher
 
         existingMeta = readExistingFrontMatter(absolutePath)
 
-        if existingMeta[:lastModifiedAt] && existingMeta[:lastModifiedAt] >= postInfo.latestPublishedAt.to_i &&
-           !isPin.nil? && isPin == existingMeta[:pin] &&
-           !isLockedPreviewOnly.nil? && isLockedPreviewOnly == existingMeta[:lockedPreviewOnly]
+        if shouldSkipExistingPost?(existingMeta, postInfo, isPin, isLockedPreviewOnly)
             # Already downloaded and nothing has changed!, Skip!
             progress.currentPostParagraphIndex = paragraphs.length
             progress.message = "Skip, Post already downloaded and nothing has changed!"
@@ -374,6 +372,26 @@ class ZMediumFetcher
 
     # Reads YAML-ish front matter from a previously-generated post and
     # returns the fields we care about for skip-already-downloaded logic.
+    # Does the existing on-disk post still match the freshly-fetched
+    # metadata? All three signals must agree:
+    #   1. last_modified_at on disk is >= Medium's latestPublishedAt
+    #   2. isPin matches the file's pin flag
+    #   3. isLockedPreviewOnly matches the file's lockedPreviewOnly flag
+    #
+    # Boolean signals are normalized to true/false before comparing so that
+    # `nil` (Medium's GraphQL response can omit the field for non-paywalled
+    # / non-pinned posts) and `false` (the default written when the front-
+    # matter line is omitted by Helper.createPostInfo) are treated as
+    # equivalent — otherwise free, never-pinned posts would re-download on
+    # every run.
+    def shouldSkipExistingPost?(existingMeta, postInfo, isPin, isLockedPreviewOnly)
+        return false unless existingMeta[:lastModifiedAt]
+        return false unless existingMeta[:lastModifiedAt] >= postInfo.latestPublishedAt.to_i
+        return false unless (isPin == true) == existingMeta[:pin]
+        return false unless (isLockedPreviewOnly == true) == existingMeta[:lockedPreviewOnly]
+        true
+    end
+
     def readExistingFrontMatter(absolutePath)
         meta = { lastModifiedAt: nil, pin: false, lockedPreviewOnly: false }
         return meta unless File.file?(absolutePath)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ZMediumToMarkdown
 version: !ruby/object:Gem::Version
-  version: 3.3.3
+  version: 3.4.0
 platform: ruby
 authors:
 - ZhgChgLi