Merge branch 'dev' into method_allow_deny

archivebox/extractors/dom.py

@@ -9,6 +9,7 @@ from ..util import (
     enforce_types,
     is_static_file,
     chrome_args,
+    chrome_cleanup,
 )
 from ..config import (
     TIMEOUT,
@@ -57,6 +58,7 @@ def save_dom(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
     except Exception as err:
         status = 'failed'
         output = err
+        chrome_cleanup()
     finally:
         timer.end()
 

archivebox/extractors/pdf.py

@@ -9,6 +9,7 @@ from ..util import (
     enforce_types,
     is_static_file,
     chrome_args,
+    chrome_cleanup,
 )
 from ..config import (
     TIMEOUT,
@@ -54,6 +55,7 @@ def save_pdf(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
     except Exception as err:
         status = 'failed'
         output = err
+        chrome_cleanup()
     finally:
         timer.end()
 

archivebox/extractors/readability.py

@@ -71,7 +71,7 @@ def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEO
         result = run(cmd, cwd=out_dir, timeout=timeout)
         try:
             result_json = json.loads(result.stdout)
-            assert result_json and 'content' in result_json
+            assert result_json and 'content' in result_json, 'Readability output is not valid JSON'
         except json.JSONDecodeError:
             raise ArchiveError('Readability was not able to archive the page', result.stdout + result.stderr)
 
@@ -85,7 +85,7 @@ def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEO
         #  "Downloaded: 76 files, 4.0M in 1.6s (2.52 MB/s)"
         output_tail = [
             line.strip()
-            for line in (result.stdout + result.stderr).decode().rsplit('\n', 3)[-3:]
+            for line in (result.stdout + result.stderr).decode().rsplit('\n', 5)[-5:]
             if line.strip()
         ]
         hints = (

archivebox/extractors/screenshot.py

@@ -9,6 +9,7 @@ from ..util import (
     enforce_types,
     is_static_file,
     chrome_args,
+    chrome_cleanup,
 )
 from ..config import (
     TIMEOUT,
@@ -54,6 +55,7 @@ def save_screenshot(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEO
     except Exception as err:
         status = 'failed'
         output = err
+        chrome_cleanup()
     finally:
         timer.end()
 

archivebox/extractors/title.py

@@ -26,7 +26,7 @@ from ..logging_util import TimedProgress
 
 HTML_TITLE_REGEX = re.compile(
     r'<title.*?>'                      # start matching text after <title> tag
-    r'(.[^<>]+)',                      # get everything up to these symbols
+    r'([^<>]+)',                      # get everything up to these symbols
     re.IGNORECASE | re.MULTILINE | re.DOTALL | re.UNICODE,
 )