skip link visibility on cli with status

Author: digitronik

README.md

@@ -24,7 +24,7 @@ This is simple link status checker for text/markdown files.
 - source
 
     ```bash
-    python install . --user
+    pip install . --user
     ```
 
 ### Usage:
@@ -37,10 +37,13 @@ Usage: linkstatus [OPTIONS] [SOURCE]...
 Options:
   -r, --recursive        Include all files from directories recursively
   -t, --timeout INTEGER  Request timeout (default 4 second)
+  -rt, --retry INTEGER   Retry link status (default 2 time)
   --help                 Show this message and exit.
 ```
 
-![linkstatus](https://user-images.githubusercontent.com/11618054/67676030-aafb6400-f9a6-11e9-9d56-c27c21a9e0a8.png)
+   ![linkstatus](https://user-images.githubusercontent.com/11618054/67754970-5a930d80-fa5d-11e9-851c-afd38147cf28.png)
 
 
-**Note: Skip `link` check for any line by adding `noqa` (no quality assurance) as inline comment.**
+
+**Note: Skip `link` check for any line by adding `noqa` (no quality assurance) as inline comment
+.** like `<-- noqa -->` for `html` and `markdown`, `#noqa` for `python` etc...

linkstatus/linkstatus.py

@@ -58,37 +58,47 @@ def main(source, recursive, timeout, retry):
         links = parse_file(f)
 
         if links:
-            click.echo(click.style("File: {}".format(f), bg="blue", fg="white"))
+            click.echo(click.style("Links in File: '{}'".format(f), bg="blue", fg="white"))
 
             for link in links:
                 for url in link.urls:
-                    # try two time at least
-                    for _ in range(int(retry)):
-                        status, code = link_status(url, int(timeout))
-                        if status is True:
-                            break
-
-                    if status:
-                        fg = "green"
-                        icon = "✓"
+                    if link.skip:
+                        click.echo(
+                            "{icon} L{ln} : {url} (skip)".format(
+                                icon=click.style("…", fg="blue", bold=True),
+                                ln=link.line,
+                                url=click.style(url, fg="blue"),
+                            )
+                        )
                     else:
-                        fg = "red"
-                        icon = "✗"
-                        exit_code = 1
-
-                    click.echo(
-                        "{icon} L{ln} : {url} {code}".format(
-                            icon=click.style(icon, fg=fg, bold=True),
-                            ln=link.line,
-                            url=click.style(url, fg=fg),
-                            code="" if code == 200 else "({})".format(code),
+                        # retry to take status default 2 time
+                        for _ in range(int(retry)):
+                            status, code = link_status(url, int(timeout))
+                            if status is True:
+                                break
+
+                        if status:
+                            fg = "green"
+                            icon = "✓"
+                        else:
+                            fg = "red"
+                            icon = "✗"
+                            exit_code = 1
+
+                        click.echo(
+                            "{icon} L{ln} : {url} {code}".format(
+                                icon=click.style(icon, fg=fg, bold=True),
+                                ln=link.line,
+                                url=click.style(url, fg=fg),
+                                code="" if code == 200 else "({})".format(code),
+                            )
                         )
-                    )
+
     if exit_code == 1:
         click.echo(
             click.style(
-                "Note: Use `noqa` inline comment to skip link check. "
-                "eg. response code 403 due to header restrictions etc...",
+                "Warning: Use `noqa` inline comment to skip link check. "
+                "like, response code 403 due to header restrictions etc...",
                 fg="red",
                 bold=True,
             )

linkstatus/parser.py

@@ -6,7 +6,7 @@
 
 REGULAR_EXP = r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
 
-LINKS = namedtuple("LINKS", ["line", "urls"])
+LINKS = namedtuple("LINKS", ["line", "urls", "skip"])
 
 
 def parse_line(line):
@@ -18,17 +18,12 @@ def parse_line(line):
         list of links
     """
     string = line.strip()
+    html_format = markdown.markdown(string, output_format="html")
+    links = re.findall(REGULAR_EXP, html_format)
 
-    # if `noqa` (no quality assurance) marked in line then just skip that string
-    if "noqa" not in string:
-        html_format = markdown.markdown(string, output_format="html")
-        links = re.findall(REGULAR_EXP, html_format)
-
-        # TODO: Improve regex to remove this workaround for trailing </p> or </li>
-        links = [l.replace("</p>", "").replace("</li>", "").replace("</a>", "") for l in links]
-        return links
-    else:
-        return []
+    # TODO: Improve regex to remove this workaround for trailing </p> or </li>
+    links = [l.replace("</p>", "").replace("</li>", "").replace("</a>", "") for l in links]
+    return links
 
 
 def parse_file(file_path):
@@ -43,5 +38,6 @@ def parse_file(file_path):
         for line_number, line in enumerate(f):
             line_links = parse_line(line)
             if line_links:
-                links.append(LINKS(line=line_number + 1, urls=line_links))
+                skip = True if "noqa" in line else False
+                links.append(LINKS(line=line_number + 1, urls=line_links, skip=skip))
     return links