Checking links in """ + key)
f.write(head_code)
# Iterate over all links in each MD file
for link in link_dict.get(key):
# Check internet links: http,https
try:
assert type(link) is str
except AssertionError as e:
invalid_counter = invalid_counter + 1
a_row_code = """| Invalid Link Number """ + str(invalid_counter) +""" | """ + """This link is not string, which indicates that your MD file may not be well-formed.""" + """ | """ + key + """ |
"""
with open(report_name, "a", encoding="utf-8") as f:
f.write(a_row_code)
continue
# MD files that are not well-formed may raise exceptions. If parentheses are not correctly escaped, a NoneType object may be returned
if link.startswith("http://") or link.startswith("https://"):
try:
link_response = requests.get(link, timeout=60)
status_code = link_response.status_code
# Informational responses (100–199),
# Successful responses (200–299),
# Redirects (300–399),
# Client errors (400–499),
# and Server errors (500–599).
if status_code in range(200,299):
# For links that do not contain hashes
if "#" not in link:
row_code = """| """ + """""" + link + """""" + """ | """ + str(status_code) + """ | """ + key + """ |
"""
# For links that contain hashes
else:
try:
# Acquire the url after "#"
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req = urllib.request.Request(url=str(
urlparse(link).scheme + "://" + urlparse(link).netloc + urlparse(link).path), headers=headers)
response = urllib.request.urlopen(req,data=None)
html_code = response.read()
soup = BeautifulSoup(html_code.decode("utf-8"), "lxml")
a_hash = soup.find("a", {"id": str(urlparse(link).fragment)})
h1_hash = soup.find("h1", {"id": str(urlparse(link).fragment)})
h2_hash = soup.find("h2", {"id": str(urlparse(link).fragment)})
h3_hash = soup.find("h3", {"id": str(urlparse(link).fragment)})
h4_hash = soup.find("h4", {"id": str(urlparse(link).fragment)})
h5_hash = soup.find("h5", {"id": str(urlparse(link).fragment)})
h6_hash = soup.find("h6", {"id": str(urlparse(link).fragment)})
div_hash = soup.find("div",{"id": str(urlparse(link).fragment)})
if (None, None, None, None, None, None, None, None) != (
a_hash, h1_hash, h2_hash, h3_hash, h4_hash, h5_hash, h6_hash, div_hash):
row_code = """| """ + """""" + link + """""" + """ | """ + str(
status_code) + """ | """ + key + """ |
"""
else:
row_code = """| """ + """""" + link + """""" + """ | """ + str(
status_code) + """ The URL looks good but the anchor link does not work or is not using an anchor tag.""" + """ | """ + key + """ |
""" """"""
except urllib.error.HTTPError as http_error:
row_code = """| """ + """""" + link + """""" + """ | """ + str(
status_code) + """ """ + str(http_error) + """ The URL looks good but the page then returns an HTTP error. | """ + key + """ |
"""
except urllib.error.URLError as url_error:
row_code = """| """ + """""" + link + """""" + """ | """ + str(
status_code) + """ """ + str(url_error) + """ The URL looks good but the page then returns a URL error. | """ + key + """ |
"""
elif status_code in range(400,599):
row_code = """| """ + """""" + link + """""" + """ | """ + str(
status_code) + """ | """ + key + """ |
"""
except requests.exceptions.Timeout as timeout_error:
print(timeout_error)
row_code = """| """ + """""" + link + """""" + """ | """ + str(
timeout_error) + """ | """ + key + """ |
"""
except requests.exceptions.ConnectionError as connection_error:
print(connection_error)
row_code = """| """ + """""" + link + """""" + """ | """ + str(
connection_error) + """ | """ + key + """ |
"""
except requests.exceptions.HTTPError as http_error:
print(http_error)
row_code = """| """ + """""" + link + """""" + """ | """ + str(
http_error) + """ | """ + key + """ |
"""
# elif link.startswith("mailto:"):
# Check MD file links
# File path formats on Windows systems from https://docs.microsoft.com/en-us/dotnet/standard/io/file-path-formats
# C:\Documents\Newsletters\Summer2018.pdf An absolute file path from the root of drive C:
# \Program Files\Custom Utilities\StringFinder.exe An absolute path from the root of the current drive.
# 2018\January.xlsx A relative path to a file in a subdirectory of the current directory.
# ..\Publications\TravelBrochure.pdf A relative path to file in a directory that is a peer of the current directory.
# C:\Projects\apilibrary\apilibrary.sln An absolute path to a file from the root of drive C:
# C:Projects\apilibrary\apilibrary.sln A relative path from the current directory of the C: drive.
# We do not use absolute path formats in MD files and path formats are not likely to be from the root of the current drive. So here are possible formats:
# 2018\January.md
# ..\Publications\TravelBrochure.md
# Check if file exists
elif link.endswith(".md") or link.endswith(".MD") or link.endswith(".mD") or link.endswith(".Md"):
# A relative path to file in a directory that is a peer of the current directory.
if link.startswith("..\\"):
# Get the absolute location of the linked md
cur_direct = os.path.dirname(key)
final_direct = os.path.dirname(cur_direct)
linked_md = os.path.join(final_direct,link)
# Check if the linked md exists
if Path(linked_md).is_file():
row_code = """| """ + link + """ | The file link looks good. | """ + key + """ |
"""
else:
row_code = """| """ + link + """ | The file link is broken. | """ + key + """ |
"""
# A relative path to a file in a subdirectory of the current directory.
else:
# Get the absolute location of the linked md
cur_direct = os.path.dirname(key)
linked_md = os.path.join(cur_direct, link)
# Check if the linked md exists
if Path(linked_md).is_file():
row_code = """| """ + link + """ | The file link looks good. | """ + key + """ |
"""
else:
row_code = """| """ + link + """ | The file link is broken. | """ + key + """ |
"""
elif link.startswith("#"):
# Validate if anchors correctly show in the MD file
with open(key,"r",encoding="utf-8") as f:
md_text = f.read()
# print(str(md_text))
reg = re.compile(str("#" + "\s*" + link[1:]))
if """""" in str(md_text) or len(re.findall(reg,str(md_text))) == 2:
row_code = """| """ + link + """ | The anchor link looks good. | """ + key + """ |
"""
else:
row_code = """| """ + link + """ | The anchor link is broken. | """ + key + """ |
"""
# Writes row_code for the link to the table
with open(report_name, "a", encoding="utf-8") as f:
f.write(row_code)
# print(row_code)
# Writes the end of the table for the key
with open(report_name, "a", encoding="utf-8") as f:
f.write("