initial

snowscraper/scrapers/medium.py

@@ -0,0 +1,34 @@
+from datetime import datetime
+from datetime import timezone
+
+import feedparser
+
+from ..controller import register_scraper
+from ..helpers import string_to_datetime
+from ..scraper import BaseScraper
+
+
+@register_scraper
+class MediumScraper(BaseScraper):
+    url = "https://medium.com/feed/snowflake"
+
+    def __init__(self, after=datetime(1970, 1, 1, tzinfo=timezone.utc), *args, **kwargs):
+        super(MediumScraper, self).__init__(*args, **kwargs)
+        self.data = {}
+        self.after = after
+
+    def scrape(self):
+        print("Scraping Medium")
+        for entry in feedparser.parse(MediumScraper.url)["entries"]:
+            updated = string_to_datetime(entry["updated"])
+            if updated > self.after:
+                self.data[entry["link"]] = {
+                    "title": entry["title"],
+                    "published": string_to_datetime(entry["published"]),
+                    "updated": updated,
+                }
+        print(self.data)
+        return self.data
+
+    def transform(self):
+        return self.data

snowscraper/scrapers/quickstarts.py

@@ -0,0 +1,47 @@
+from datetime import datetime
+from datetime import timezone
+
+import scrapy
+from scrapy.crawler import CrawlerProcess
+
+from ..controller import register_scraper
+from ..scraper import BaseScraper
+from snowscraper.helpers import string_to_datetime
+
+QuickStartsURL = "https://quickstarts.snowflake.com/"
+
+
+@register_scraper
+class QuickstartScraper(BaseScraper, scrapy.Spider):
+    name = "snowflakespider"
+
+    def __init__(self, after=datetime(1970, 1, 1, tzinfo=timezone.utc), *args, **kwargs):
+        super(QuickstartScraper, self).__init__(*args, **kwargs)
+        self.data = {}
+        self.after = after
+
+    def start_requests(self):
+        yield scrapy.Request(url=QuickStartsURL, callback=self.parse)
+
+    def scrape(self):
+        print("Scraping Quickstarts")
+        process = CrawlerProcess({"LOG_LEVEL": "ERROR"})
+        process.crawl(QuickstartScraper, after=self.after)
+        process.start()
+
+    def parse(self, response):
+        for card in response.css("card-sorter#cards > a.codelab-card"):
+            updated = string_to_datetime(card.attrib["data-updated"])
+            if updated > self.after:
+                print(f"Updated: {updated} > {self.after}")
+                key = QuickStartsURL.rstrip("/") + card.attrib["href"]
+                self.data[key] = {
+                    "title": card.attrib["data-title"],
+                    "updated": updated,
+                    "tags": card.attrib["data-tags"],
+                }
+                print(key, self.data[key])
+                yield self.data[key]
+
+    def transform(self):
+        return self.data

snowscraper/scrapers/youtube.py

@@ -0,0 +1,20 @@
+from datetime import datetime
+from datetime import timezone
+
+from ..controller import register_scraper
+from ..scraper import BaseScraper
+
+
+@register_scraper
+class YoutubeScraper(BaseScraper):
+    def __init__(self, after=datetime(1970, 1, 1, tzinfo=timezone.utc), *args, **kwargs):
+        super(YoutubeScraper, self).__init__(*args, **kwargs)
+        self.data = {}
+        self.after = after
+
+    def scrape(self):
+        print("Scraping YouTube... Unimplemented")
+        self.data = {}
+
+    def transform(self):
+        return self.data