Ausgabe der neuen DB Einträge

venv/lib/python3.9/site-packages/scrapy/templates/spiders/basic.tmpl

@@ -0,0 +1,10 @@
+import scrapy
+
+
+class $classname(scrapy.Spider):
+    name = '$name'
+    allowed_domains = ['$domain']
+    start_urls = ['http://$domain/']
+
+    def parse(self, response):
+        pass

venv/lib/python3.9/site-packages/scrapy/templates/spiders/crawl.tmpl

@@ -0,0 +1,20 @@
+import scrapy
+from scrapy.linkextractors import LinkExtractor
+from scrapy.spiders import CrawlSpider, Rule
+
+
+class $classname(CrawlSpider):
+    name = '$name'
+    allowed_domains = ['$domain']
+    start_urls = ['http://$domain/']
+
+    rules = (
+        Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
+    )
+
+    def parse_item(self, response):
+        item = {}
+        #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
+        #item['name'] = response.xpath('//div[@id="name"]').get()
+        #item['description'] = response.xpath('//div[@id="description"]').get()
+        return item

venv/lib/python3.9/site-packages/scrapy/templates/spiders/csvfeed.tmpl

@@ -0,0 +1,20 @@
+from scrapy.spiders import CSVFeedSpider
+
+
+class $classname(CSVFeedSpider):
+    name = '$name'
+    allowed_domains = ['$domain']
+    start_urls = ['http://$domain/feed.csv']
+    # headers = ['id', 'name', 'description', 'image_link']
+    # delimiter = '\t'
+
+    # Do any adaptations you need here
+    #def adapt_response(self, response):
+    #    return response
+
+    def parse_row(self, response, row):
+        i = {}
+        #i['url'] = row['url']
+        #i['name'] = row['name']
+        #i['description'] = row['description']
+        return i

venv/lib/python3.9/site-packages/scrapy/templates/spiders/xmlfeed.tmpl

@@ -0,0 +1,16 @@
+from scrapy.spiders import XMLFeedSpider
+
+
+class $classname(XMLFeedSpider):
+    name = '$name'
+    allowed_domains = ['$domain']
+    start_urls = ['http://$domain/feed.xml']
+    iterator = 'iternodes' # you can change this; see the docs
+    itertag = 'item' # change it accordingly
+
+    def parse_node(self, response, selector):
+        item = {}
+        #item['url'] = selector.select('url').get()
+        #item['name'] = selector.select('name').get()
+        #item['description'] = selector.select('description').get()
+        return item