move scraping for article content to files.

apiserver/scrapers/declutter.py

@@ -0,0 +1,28 @@
+import logging
+logging.basicConfig(
+        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+        level=logging.DEBUG)
+import requests
+
+DECLUTTER_API = 'https://declutter.1j.nz/details'
+
+
+def get_html(url):
+    try:
+		logging.info(f'Declutter Scraper: {url}')
+        details = get_details(url)
+        return details['content']
+    except:
+        raise
+
+def get_details(url):
+    try:
+        r = requests.post(DECLUTTER_API, data=dict(url=url), timeout=20)
+        if r.status_code != 200:
+            raise Exception('Bad response code ' + str(r.status_code))
+        return r.json()
+    except KeyboardInterrupt:
+        raise
+    except BaseException as e:
+        logging.error('Problem decluttering article: {}'.format(str(e)))
+        return {}

apiserver/scrapers/local.py

@@ -0,0 +1,28 @@
+import logging
+logging.basicConfig(
+        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+        level=logging.DEBUG)
+import requests
+
+READ_API = 'http://127.0.0.1:33843/details'
+
+
+def get_html(url):
+    try:
+        logging.info(f'Local Scraper: {url}')
+        details = get_details(url)
+        return details['content']
+    except:
+        raise
+
+def get_details(url):
+    try:
+        r = requests.post(READ_API, data=dict(url=url), timeout=20)
+        if r.status_code != 200:
+            raise Exception('Bad response code ' + str(r.status_code))
+        return r.json()
+    except KeyboardInterrupt:
+        raise
+    except BaseException as e:
+        logging.error('Problem getting article: {}'.format(str(e)))
+        return {}

apiserver/scrapers/outline.py

@@ -0,0 +1,38 @@
+import logging
+logging.basicConfig(
+        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+        level=logging.DEBUG)
+import requests
+
+OUTLINE_REFERER = 'https://outline.com/'
+OUTLINE_API = 'https://api.outline.com/v3/parse_article'
+
+
+def get_html(url):
+    try:
+        details = get_details(url)
+        return details['html']
+    except:
+        raise
+
+def get_details(url):
+    try:
+		logging.info(f'Outline Scraper: {url}')
+        params = {'source_url': url}
+        headers = {'Referer': OUTLINE_REFERER}
+        r = requests.get(OUTLINE_API, params=params, headers=headers, timeout=20)
+        if r.status_code == 429:
+            logging.info('Rate limited by outline, sleeping 30s and skipping...')
+            time.sleep(30)
+            return ''
+        if r.status_code != 200:
+            raise Exception('Bad response code ' + str(r.status_code))
+        data = r.json()['data']
+        if 'URL is not supported by Outline' in data['html']:
+            raise Exception('URL not supported by Outline')
+        return data
+    except KeyboardInterrupt:
+        raise
+    except BaseException as e:
+        logging.error('Problem outlining article: {}'.format(str(e)))
+		return {}