Merge pull request #8 from zsinx6/master

add support for img single tag without close

main.py

-# June 27 2017
-# Andrew Xia
-# main program (for testing stuff)
-
-import tomd
-
-# FOLDER = "/home/andrew/Documents/Evernote_170625/"
-FOLDER = "/home/andrew/Documents/Github/evernote-analysis"
-# FILE = "Week11.html"
-FILE = "pensive.html"
-CONTENT = ""
-
-FOLDER = "/home/andrew/Documents/Evernote_170625/Log/2016"
-FILE = "Week 10 37 to 313.html"
-
-f = open(FOLDER + "/" + FILE)
-for line in f:
-  CONTENT += line
-
-# CONTENT = """
-# <p>For <em>Implementing</em>, working with <a href="http://chiraag.scripts.mit.edu/wiki/start" target="_blank"><strong>Chiraag Juvekar</strong></a> and <a href="http://www-mtl.mit.edu/~anantha/" target="_blank"><strong>Prof. Anantha Chandrakasan</strong></a>.</p>
-
-# <h3 id="abstract">Abstract</h3>
-
-# <p>Having an
-# is </p>
-# <hr/>
-# <p>My paper can be found <a href="/files/superUROP.pdf"><strong>here</strong></a></p>
-# """
-
-# CONTENT = """
-# <table bgcolor="#D4DDE5" border="0">
-# <tr><td><b>Created:</b></td><td><i>10/31/2011 8:59 PM</i></td></tr>
-# <tr><td><b>Updated:</b></td><td><i>5/12/2012 5:42 PM</i></td></tr>
-# <tr><td><b>Tags:</b></td><td><i>birthday</i></td></tr>
-# </table>
-# """
-
-# CONTENT = """<table border="1" cellpadding="2" cellspacing="0" style="font-size: 13px;" width="100%"><tbody><tr><td valign="top">Day (Sleep)</td><td valign="top">Internet</td><td valign="top">SAT Plan/Actual</td><td valign="top">PRIMES</td><td valign="top">Homework</td><td valign="top">Athletics</td></tr><tr><td valign="top">Monday<br/>
-# 7hr</td><td valign="top">2.30hr<br/>
-# 4LOL</td><td valign="top"><br/></td><td valign="top">0.05min<br/>
-# Email, </td><td valign="top">Dartmouth</td><td valign="top"><br/></td></tr><tr><td valign="top">Tuesday<br/>
-# 10hr</td><td valign="top">1.50hr<br/>
-# LOL</td><td valign="top">:SAT K8</td><td valign="top">1.00hr<br/>
-# 7Zip Data</td><td valign="top"><br/></td><td valign="top">Swim</td></tr><tr><td valign="top">Wednesday<br/>
-# 11hr</td><td valign="top">1.54hr<br/>
-# LOL</td><td valign="top">SAT 36</td><td valign="top">1.10hr<br/>
-# HIV Data, trying excel convert</td><td valign="top">College</td><td valign="top">Swim</td></tr><tr><td valign="top">Thursday<br/>
-# 10hr</td><td valign="top">1.37min<br/>
-# 4LOL</td><td valign="top">SAT 36, 35</td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top">Swim</td></tr><tr><td valign="top">Friday<br/>
-# 10hr</td><td valign="top">0.30min</td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top">Driving Lesson</td><td valign="top">Swim</td></tr><tr><td valign="top">Saturday<br/>
-# 8hr</td><td valign="top">2.10hr<br/>
-# 3LOL</td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top">Swim Meet</td></tr><tr><td valign="top">Sunday<br/>
-# 9hr</td><td valign="top">1.08hr<br/>
-# 2LOL</td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top"><br/></td><td valign="top">Swim Meet</td></tr></tbody></table>
-# """
-
-converter = tomd.Tomd(CONTENT,FOLDER,FILE)
-# print(converter.markdown())
-

setup.py

@@ -2,7 +2,7 @@ from setuptools import find_packages, setup
 
 setup(
     name="tomd",
-    version="0.1.3",
+    version="0.1.4",
     description="Convert HTML to Markdown.",
     author="Gaojiuli",
     author_email="gaojiuli@gmail.com",

test_tomd.py

@@ -12,6 +12,7 @@ string = """
 <a href="https://github.com">link</a>
 <img src="https://github.com" class="dsad">img</img>
 <img src="https://github.com" class="dsad"/>
+<img src="https://github.com" class="dsad">
 </p>
 <ul>
 <li>1</li>
@@ -33,6 +34,7 @@ string = """
 <b><i>bold italic</i></b>
 <em>em</em>
 <strong>strong</strong>
+aa <strong> strong   </strong> aa
 </p>
 
 <hr/>

tomd.py

-import re, os
+import re
+import os
+import warnings
 
 __all__ = ['Tomd', 'convert']
 
@@ -14,7 +16,7 @@ MARKDOWN = {
     'ol': ('', ''),
     'li': ('- ', ''),
     'blockquote': ('\n> ', '\n'),
-    'em': ('**', '**'),
+    'em': ('*', '*'),
     'strong': ('**', '**'),
     'block_code': ('\n```\n', '\n```\n'),
     'span': ('', ''),
@@ -55,7 +57,7 @@ BlOCK_ELEMENTS = {
 
 
 INLINE_ELEMENTS = {
-    'td': '<td.*?>((.|\n)*?)</td>', #td element may span lines
+    'td': '<td.*?>((.|\n)*?)</td>',  # td element may span lines
     'tr': '<tr.*?>((.|\n)*?)</tr>',
     'th': '<th.*?>(.*?)</th>',
     'b': '<b.*?>(.*?)</b>',
@@ -70,13 +72,15 @@ INLINE_ELEMENTS = {
     'li': '<li.*?>(.*?)</li>',
     'img': '<img.*?src="(.*?)".*?>(.*?)</img>',
     'img_single': '<img.*?src="(.*?)".*?/>',
+    'img_single_no_close': '<img.*?src="(.*?)".*?>',
     'a': '<a.*?href="(.*?)".*?>(.*?)</a>',
     'em': '<em.*?>(.*?)</em>',
-    'strong': '<strong.*?>(.*?)</strong>',
+    'strong': '<strong.*?>(\s*)(.*?)(\s*)</strong>',
     'tbody': '<tbody.*?>((.|\n)*)</tbody>',
 }
 
-DELETE_ELEMENTS = ['<span.*?>', '</span>', '<div.*?>', '</div>','<br clear="none"/>', '<center.*?>', '</center>']
+DELETE_ELEMENTS = ['<span.*?>', '</span>', '<div.*?>', '</div>', '<br clear="none"/>', '<center.*?>', '</center>']
+
 
 class Element:
     def __init__(self, start_pos, end_pos, content, tag, folder, is_block=False):
@@ -90,10 +94,7 @@ class Element:
         self._result = None
 
         if self.is_block:
-            # print "parsing tag:", self.tag, ", content: ", repr(self.content)
             self.parse_inline()
-            # if self.tag != 'table':
-                # print "parsed:", self.tag, self.folder, ", content: ", repr(self.content)
 
     def __str__(self):
         wrapper = MARKDOWN.get(self.tag)
@@ -101,44 +102,43 @@ class Element:
         return self._result
 
     def parse_inline(self):
-        self.content = self.content.replace('\r', '') #windows \r character
-        self.content = self.content.replace('\xc2\xa0', ' ') #no break space
-        self.content = self.content.replace('&quot;', '\"') #html quote mark
+        self.content = self.content.replace('\r', '')  # windows \r character
+        self.content = self.content.replace('\xc2\xa0', ' ')  # no break space
+        self.content = self.content.replace('&quot;', '\"')  # html quote mark
 
-        for m in re.finditer("<img(.*?)en_todo.*?>",self.content):
-            #remove img and change to [ ] and [x]
-            #evernote specific parsing
-            imgSrc = re.search('src=".*?"',m.group())
-            imgLoc = imgSrc.group()[5:-1] #remove source and " "
-            imgLoc = imgLoc.replace('\\', '/') #\\ folder slash rotate
+        for m in re.finditer("<img(.*?)en_todo.*?>", self.content):
+            # remove img and change to [ ] and [x]
+            # evernote specific parsing
+            imgSrc = re.search('src=".*?"', m.group())
+            imgLoc = imgSrc.group()[5:-1]  # remove source and " "
+            imgLoc = imgLoc.replace('\\', '/')  # \\ folder slash rotate
             if os.stat(self.folder + "/" + imgLoc).st_size < 250:
-                self.content = self.content.replace(m.group(),"[ ] ")
+                self.content = self.content.replace(m.group(), "[ ] ")
             else:
-                self.content = self.content.replace(m.group(),"[x] ")
-        # print self.content
+                self.content = self.content.replace(m.group(), "[x] ")
 
-        if "e_" in self.tag: #evernote-specific parsing
-            # if self.content != re.sub(BlOCK_ELEMENTS['table'], '\g<1>', self.content):
+        if "e_" in self.tag:  # evernote-specific parsing
             for m in re.finditer(BlOCK_ELEMENTS['table'], self.content, re.I | re.S | re.M):
-                #hmm can there only be one table?
-                # print "AHHHH THERES A TABLE\n\n"
+                # hmm can there only be one table?
                 inner = Element(start_pos=m.start(),
-                                  end_pos=m.end(),
-                                  content=''.join(m.groups()),
-                                  tag='table',folder=self.folder,
-                                  is_block=True)
+                                end_pos=m.end(),
+                                content=''.join(m.groups()),
+                                tag='table', folder=self.folder,
+                                is_block=True)
                 self.content = inner.content
-                return #no need for further parsing ?
+                return  # no need for further parsing ?
 
             # if no table, parse as usual
             self.content = self.content.replace('<hr/>', '\n---\n')
             self.content = self.content.replace('<br/>', '')
 
-        if self.tag == "table": #for removing tbody
+        if self.tag == "table":  # for removing tbody
             self.content = re.sub(INLINE_ELEMENTS['tbody'], '\g<1>', self.content)
 
-        for tag, pattern in INLINE_ELEMENTS.items():
-            # print "---now looking at", tag, pattern
+        INLINE_ELEMENTS_LIST_KEYS = list(INLINE_ELEMENTS.keys())
+        INLINE_ELEMENTS_LIST_KEYS.sort()
+        for tag in INLINE_ELEMENTS_LIST_KEYS:
+            pattern = INLINE_ELEMENTS[tag]
 
             if tag == 'a':
                 self.content = re.sub(pattern, '[\g<2>](\g<1>)', self.content)
@@ -146,6 +146,8 @@ class Element:
                 self.content = re.sub(pattern, '![\g<2>](\g<1>)', self.content)
             elif tag == 'img_single':
                 self.content = re.sub(pattern, '![](\g<1>)', self.content)
+            elif tag == 'img_single_no_close':
+                self.content = re.sub(pattern, '![](\g<1>)', self.content)
             elif self.tag == 'ul' and tag == 'li':
                 self.content = re.sub(pattern, '- \g<1>', self.content)
             elif self.tag == 'ol' and tag == 'li':
@@ -156,19 +158,20 @@ class Element:
                 self.content = re.sub(pattern, '|\g<1>', self.content.replace('\n', ''))
             elif self.tag == 'tr' and tag == 'td':
                 self.content = re.sub(pattern, '|\g<1>|', self.content.replace('\n', ''))
-                self.content = self.content.replace("||","|") #end of column also needs a pipe
-                # print "---converting, td remove duplicate:", tag, self.content
+                self.content = self.content.replace("||", "|")  # end of column also needs a pipe
             elif self.tag == 'table' and tag == 'td':
                 self.content = re.sub(pattern, '|\g<1>|', self.content)
-                self.content = self.content.replace("||","|") #end of column also needs a pipe
-                self.content = self.content.replace('|\n\n', '|\n') #replace double new line
-                # print "---converting, td remove duplicate:", tag, self.content
+                self.content = self.content.replace("||", "|")  # end of column also needs a pipe
+                self.content = self.content.replace('|\n\n', '|\n')  # replace double new line
                 self.construct_table()
             else:
                 wrapper = MARKDOWN.get(tag)
-                self.content = re.sub(pattern, '{}\g<1>{}'.format(wrapper[0], wrapper[1]), self.content)
+                if tag == "strong":
+                    self.content = re.sub(pattern, '{}\g<2>{}'.format(wrapper[0], wrapper[1]), self.content)
+                else:
+                    self.content = re.sub(pattern, '{}\g<1>{}'.format(wrapper[0], wrapper[1]), self.content)
 
-        if self.tag == "e_p" and self.content[-1:] != '\n' and len(self.content) > 2: 
+        if self.tag == "e_p" and self.content[-1:] != '\n' and len(self.content) > 2:
             # focusing on div, add new line if not there (and if content is long enough)
             self.content += '\n'
 
@@ -176,39 +179,36 @@ class Element:
         # this function, after self.content has gained | for table entries,
         # adds the |---| in markdown to create a proper table
 
-        temp = self.content.split('\n',3)
+        temp = self.content.split('\n', 3)
         for elt in temp:
             if elt != "":
-                count = elt.count("|") #count number of pipes
+                count = elt.count("|")  # count number of pipes
                 break
-        pipe = "\n|" #beginning \n for safety
-        for i in xrange(count-1):
+        pipe = "\n|"  # beginning \n for safety
+        for i in range(count - 1):
             pipe += "---|"
         pipe += "\n"
-        self.content = pipe + pipe + self.content + "\n" #TODO: column titles?
-        self.content = self.content.replace('|\n\n', '|\n') #replace double new line
-        self.content = self.content.replace("<br/>\n","<br/>") #end of column also needs a pipe
+        self.content = pipe + pipe + self.content + "\n"  # TODO: column titles?
+        self.content = self.content.replace('|\n\n', '|\n')  # replace double new line
+        self.content = self.content.replace("<br/>\n", "<br/>")  # end of column also needs a pipe
 
 
 class Tomd:
-    def __init__(self, html='', folder='',file='',options=None):
-        self.html = html #actual data
+    def __init__(self, html='', folder='', file='', options=None):
+        self.html = html  # actual data
         self.folder = folder
         self.file = file
-        self.options = options # haven't been implemented yet
-        self._markdown = self.convert(self.html,self.options)
+        self.options = options  # haven't been implemented yet
+        self._markdown = self.convert(self.html, self.options)
 
     def convert(self, html="", options=None):
         if html == "":
             html = self.html
-        #main function here
+        # main function here
         elements = []
         for tag, pattern in BlOCK_ELEMENTS.items():
-            # print "pattern is", pattern, "tag", tag
             for m in re.finditer(pattern, html, re.I | re.S | re.M):
                 # now m contains the pattern without the tag
-                # if tag == "e_p":
-                # print "found", tag, m.groups(), "start", m.start(), "end", m.end(), self.folder
                 element = Element(start_pos=m.start(),
                                   end_pos=m.end(),
                                   content=''.join(m.groups()),
@@ -223,10 +223,6 @@ class Tomd:
                         elements.remove(e)
                 if can_append:
                     elements.append(element)
-        # print "\n\n\ndone with convert, element is"
-        # for e in elements:
-        #     print repr(str(e))
-        # print "---"
         elements.sort(key=lambda element: element.start_pos)
         self._markdown = ''.join([str(e) for e in elements])
 
@@ -239,19 +235,19 @@ class Tomd:
         self.convert(self.html, self.options)
         return self._markdown
 
-    def export(self,folder=False):
+    def export(self, folder=False):
         if len(self.file) < 1:
             warnings.warn("file not specified, renamed to tmp.md")
             file = "tmp.md"
         else:
-            file = self.file.replace('.html','.md') #rename to md
+            file = self.file.replace('.html', '.md')  # rename to md
         if len(self.folder) < 2:
             warnings.warn("folder not specified, will save to pwd")
         elif not folder:
             file = self.folder + '/' + file
-        else: #if folder is specified
+        else:  # if folder is specified
             file = folder + '/' + file
-        f = open(file,'w')
+        f = open(file, 'w')
         f.write(self._markdown)
         f.close()