Merge pull request #2285 from return42/fix-digg

bugfix & refactor digg engine

Makefile

@@ -212,15 +212,15 @@ gecko.driver:
 PHONY += test test.sh test.pylint test.pep8 test.unit test.coverage test.robot
 test: buildenv test.pylint test.pep8 test.unit gecko.driver test.robot
 
-
+PYLINT_FILES=\
-# TODO: balance linting with pylint
-test.pylint: pyenvinstall
-	$(call cmd,pylint,\
 	searx/preferences.py \
 	searx/testing.py \
 	searx/engines/gigablast.py \
 	searx/engines/deviantart.py \
-	)
+	searx/engines/digg.py
+
+test.pylint: pyenvinstall
+	$(call cmd,pylint,$(PYLINT_FILES))
 	$(call cmd,pylint,\
 		--disable=$(PYLINT_SEARX_DISABLE_OPTION) \
 		--additional-builtins=$(PYLINT_ADDITIONAL_BUILTINS_FOR_ENGINES) \
@@ -249,7 +249,7 @@ test.sh:
 
 test.pep8: pyenvinstall
 	@echo "TEST      pycodestyle (formerly pep8)"
-	$(Q)$(PY_ENV_ACT); pycodestyle --exclude='searx/static, searx/languages.py, searx/engines/gigablast.py, searx/engines/deviantart.py' \
+	$(Q)$(PY_ENV_ACT); pycodestyle --exclude='searx/static, searx/languages.py, $(foreach f,$(PYLINT_FILES),$(f),)' \
         --max-line-length=120 --ignore "E117,E252,E402,E722,E741,W503,W504,W605" searx tests
 
 test.unit: pyenvinstall

searx/engines/digg.py

@@ -1,7 +1,7 @@
 """
  Digg (News, Social media)
 
- @website     https://digg.com/
+ @website     https://digg.com
  @provide-api no
 
  @using-api   no
@@ -9,59 +9,58 @@
  @stable      no (HTML can change)
  @parse       url, title, content, publishedDate, thumbnail
 """
+# pylint: disable=missing-function-docstring
 
-import random
-import string
 from json import loads
 from urllib.parse import urlencode
 from datetime import datetime
 
+from lxml import html
+
 # engine dependent config
 categories = ['news', 'social media']
 paging = True
+base_url = 'https://digg.com'
 
 # search-url
-base_url = 'https://digg.com/'
+search_url = base_url + (
-search_url = base_url + 'api/search/?{query}&from={position}&size=20&format=html'
+    '/api/search/'
+    '?{query}'
+    '&from={position}'
+    '&size=20'
+    '&format=html'
+)
 
-# specific xpath variables
-results_xpath = '//article'
-link_xpath = './/small[@class="time"]//a'
-title_xpath = './/h2//a//text()'
-content_xpath = './/p//text()'
-pubdate_xpath = './/time'
-
-digg_cookie_chars = string.ascii_uppercase + string.ascii_lowercase +\
-    string.digits + "+_"
-
-
-# do search-request
 def request(query, params):
     offset = (params['pageno'] - 1) * 20
-    params['url'] = search_url.format(position=offset,
+    params['url'] = search_url.format(
-                                      query=urlencode({'q': query}))
+        query = urlencode({'q': query}),
-    params['cookies']['frontend.auid'] = ''.join(random.choice(
+        position = offset,
-        digg_cookie_chars) for _ in range(22))
+    )
     return params
 
-
-# get response from search-request
 def response(resp):
     results = []
 
-    search_result = loads(resp.text)
-
     # parse results
-    for result in search_result['mapped']:
+    for result in loads(resp.text)['mapped']:
 
-        published = datetime.strptime(result['created']['ISO'], "%Y-%m-%d %H:%M:%S")
+        # strip html tags and superfluous quotation marks from content
-        # append result
+        content = html.document_fromstring(
-        results.append({'url': result['url'],
+            result['excerpt']
+        ).text_content()
+
+        # 'created': {'ISO': '2020-10-16T14:09:55Z', ...}
+        published = datetime.strptime(
+            result['created']['ISO'], '%Y-%m-%dT%H:%M:%SZ'
+        )
+        results.append({
+            'url': result['url'],
             'title': result['title'],
-                        'content': result['excerpt'],
+            'content' : content,
             'template': 'videos.html',
             'publishedDate': published,
-                        'thumbnail': result['images']['thumbImage']})
+            'thumbnail': result['images']['thumbImage'],
+        })
 
-    # return results
     return results