Neuer Ansatz für den Wettkampfsammler

Changes to be committed:
- kleinere Korrekturen/Verbesserungen
	modified:   homepage/redesign2018/markdownExperiment/Makefile
	modified:   homepage/redesign2018/markdownExperiment/src/jsonSd/cwsvJudo.json
- Neuer Ansatz für den Wettkampfsammler
	new file:   wkOrg/src/wkScraper/scrapyDocAuthorSpider.py
	new file:   wkOrg/src/wkScraper/scrapyDocQuoteSpider.py
	new file:   wkOrg/src/wkScraper/scrapyJvsKalender.py

wkOrg/src/wkScraper/scrapyDocAuthorSpider.py

@@ -0,0 +1,26 @@
+import scrapy
+
+
+class AuthorSpider(scrapy.Spider):
+    name = 'author'
+
+    start_urls = ['http://quotes.toscrape.com/']
+
+    def parse(self, response):
+        # follow links to author pages
+        for href in response.css('.author + a::attr(href)'):
+            yield response.follow(href, self.parse_author)
+
+        # follow pagination links
+        for href in response.css('li.next a::attr(href)'):
+            yield response.follow(href, self.parse)
+
+    def parse_author(self, response):
+        def extract_with_css(query):
+            return response.css(query).extract_first().strip()
+
+        yield {
+            'name': extract_with_css('h3.author-title::text'),
+            'birthdate': extract_with_css('.author-born-date::text'),
+            'bio': extract_with_css('.author-description::text'),
+        }

wkOrg/src/wkScraper/scrapyDocQuoteSpider.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+
+import scrapy
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "quotes"
+    start_urls = [
+        'http://quotes.toscrape.com/tag/humor/',
+    ]
+
+    def parse(self, response):
+        for quote in response.css('div.quote'):
+            yield {
+                'text': quote.css('span.text::text').extract_first(),
+                'author': quote.xpath('span/small/text()').extract_first(),
+            }
+
+        next_page = response.css('li.next a::attr("href")').extract_first()
+        if next_page is not None:
+            yield response.follow(next_page, self.parse)

wkOrg/src/wkScraper/scrapyJvsKalender.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+
+import scrapy
+
+
+class QuotesSpider(scrapy.Spider):
+	name = "quotes"
+	start_urls = [
+#		'https://judoverbandsachsen.de/kalender/',
+		"https://judoverbandsachsen.de/kalender/?term_id%5B%5D=48&altersklassen%5B%5D=m-U09&altersklassen%5B%5D=w-U09",
+	]
+	
+	def eventExtract( self, url, callbackHandler ):
+		yield self.follow( url, callbackHandler )
+	
+	def parseJvsKalenderEvent(self, response):
+		def extractingJvsEvent(query):
+			return "someStuff"
+		
+		yield {
+			'stuff': extractingJvsEvent("someSelector"),
+		}
+	
+	def parse(self, response):
+		for post in response.css('div.posts'):
+			url = post.css('div.col-4>a::attr(href)').extract_first()
+#			details = yield response.follow( url, self.parseJvsKalenderEvent )
+			
+			yield {
+				'date': " ".join( post.css('div.col-2>time::text').extract_first().split() ),
+				'name': " ".join( post.css('div.col-4>a::text').extract_first().split() ),
+				'url': url,
+				'ort' : " ".join( post.css('div.col-3::text').extract_first().split() ),
+			}
+			
+			yield response.follow( url, self.parseJvsKalenderEvent )