使用Python3將Markdown（.md）文字轉換成 html、pdf
阿新 • • 發佈：2018-12-02
一、Markdown中不同的文字內容會分成不同的文字塊，並通過markdown的語法控制進行文字的拼接，組成新的檔案。
二、利用Python3實現（.md）檔案轉換成（.html）檔案
在cmd命令列下進入（.py）檔案目錄下，使用命令進行執行
>python md2html.py <file.md> <file.html>
import sys, re #生成器模組 def lines(file): #在文字最後加一空行 for line in file: yield line yield'\n' def blocks(file): #生成單獨的文字塊 block = [] for line in lines(file): if line.strip(): block.append(line) elif block: yield ''.join(block).strip() block = [] #文字塊處理程式 class Handler: """ 處理程式父類 """ def callback(self, prefix, name, *args): method= getattr(self, prefix + name, None) if callable(method): return method(*args) def start(self, name): self.callback('start_', name) def end(self, name): self.callback('end_', name) def sub(self, name): def substitution(match): result= self.callback('sub_', name, match) if result is None: result = match.group(0) return result return substitution class HTMLRenderer(Handler): """ HTML處理程式,給文字塊加相應的HTML標記 """ def start_document(self): print('<html><head><title>Python文字解析</title></head><body>') def end_document(self): print('</body></html>') def start_paragraph(self): print('<p style="color: #444;">') def end_paragraph(self): print('</p>') def start_heading(self): print('<h2 style="color: #68BE5D;">') def end_heading(self): print('</h2>') def start_list(self): print('<ul style="color: #363736;">') def end_list(self): print('</ul>') def start_listitem(self): print('<li>') def end_listitem(self): print('</li>') def start_title(self): print('<h1 style="color: #1ABC9C;">') def end_title(self): print('</h1>') def sub_emphasis(self, match): return('<em>%s</em>' % match.group(1)) def sub_url(self, match): return('<a target="_blank" style="text-decoration: none;color: #BC1A4B;" href="%s">%s</a>' % (match.group(1), match.group(1))) def sub_mail(self, match): return('<a style="text-decoration: none;color: #BC1A4B;" href="mailto:%s">%s</a>' % (match.group(1), match.group(1))) def feed(self, data): print(data) #規則，判斷每個文字塊應該如何處理 class Rule: """ 規則父類 """ def action(self, block, handler): """ 加標記 """ handler.start(self.type) handler.feed(block) handler.end(self.type) return True class HeadingRule(Rule): """ 一號標題規則 """ type = 'heading' def condition(self, block): """ 判斷文字塊是否符合規則 """ return not '\n' in block and len(block) <= 70 and not block[-1] == ':' class TitleRule(HeadingRule): """ 二號標題規則 """ type = 'title' first = True def condition(self, block): if not self.first: return False self.first = False return HeadingRule.condition(self, block) class ListItemRule(Rule): """ 列表項規則 """ type = 'listitem' def condition(self, block): return block[0] == '-' def action(self, block, handler): handler.start(self.type) handler.feed(block[1:].strip()) handler.end(self.type) return True class ListRule(ListItemRule): """ 列表規則 """ type = 'list' inside = False def condition(self, block): return True def action(self, block, handler): if not self.inside and ListItemRule.condition(self, block): handler.start(self.type) self.inside = True elif self.inside and not ListItemRule.condition(self, block): handler.end(self.type) self.inside = False return False class ParagraphRule(Rule): """ 段落規則 """ type = 'paragraph' def condition(self, block): return True class Code(Rule): ''' 程式碼框規則 高亮顯示規則 。。。 ''' pass # 對整個文字進行解析 class Parser: """ 解析器父類 """ def __init__(self, handler): self.handler = handler self.rules = [] self.filters = [] def addRule(self, rule): """ 新增規則 """ self.rules.append(rule) def addFilter(self, pattern, name): """ 新增過濾器 """ def filter(block, handler): return re.sub(pattern, handler.sub(name), block) self.filters.append(filter) def parse(self, file): """ 解析 """ self.handler.start('document') for block in blocks(file): for filter in self.filters: block = filter(block, self.handler) for rule in self.rules: if rule.condition(block): last = rule.action(block, self.handler) if last: break self.handler.end('document') class BasicTextParser(Parser): """ 純文字解析器 """ def __init__(self, handler): Parser.__init__(self, handler) self.addRule(ListRule()) self.addRule(ListItemRule()) self.addRule(TitleRule()) self.addRule(HeadingRule()) self.addRule(ParagraphRule()) self.addFilter(r'\*(.+?)\*', 'emphasis') self.addFilter(r'(http://[\.a-zA-Z/]+)', 'url') self.addFilter(r'([\.a-zA-Z][email protected][\.a-zA-Z]+[a-zA-Z]+)', 'mail') """ 執行測試程式 """ handler = HTMLRenderer() parser = BasicTextParser(handler) parser.parse(sys.stdin)
三、利用Python3將文字轉化成pdf檔案
命令>python md2pdf.py 原始檔 目標檔案 [options]
Options: -h --help show help document. -v --version show version information. -o --output translate sourcefile into html file. -p --print translate sourcefile into pdf file and html file respectively. -P --Print translate sourcefile into pdf file only.
import os,re import sys,getopt from enum import Enum from subprocess import call from functools import reduce from docopt import docopt __version__ = '1.0' # 定義三個列舉類 # 定義表狀態 class TABLE(Enum): Init = 1 Format = 2 Table = 3 # 有序序列狀態 class ORDERLIST(Enum): Init = 1 List = 2 # 塊狀態 class BLOCK(Enum): Init = 1 Block = 2 CodeBlock = 3 # 定義全域性狀態，並初始化狀態 table_state = TABLE.Init orderList_state = ORDERLIST.Init block_state = BLOCK.Init is_code = False is_normal = True temp_table_first_line = [] temp_table_first_line_str = "" need_mathjax = False def test_state(input): global table_state, orderList_state, block_state, is_code, temp_table_first_line, temp_table_first_line_str Code_List = ["python\n", "c++\n", "c\n"] result = input # 構建正則表示式規則 # 匹配塊標識 pattern = re.compile(r'```(\s)*\n') a = pattern.match(input) # 普通塊 if a and block_state == BLOCK.Init: result = "<blockquote>" block_state = BLOCK.Block is_normal = False # 特殊程式碼塊 elif len(input) > 4 and input[0:3] == '```' and (input[3:9] == "python" or input[3:6] == "c++" or input[3:4]== "c") and block_state == BLOCK.Init: block_state = BLOCK.Block result = "<code></br>" is_code = True is_normal = False # 塊結束 elif block_state == BLOCK.Block and input == '```\n': if is_code: result = "</code>" else: result = "</blockquote>" block_state = BLOCK.Init is_code = False is_normal = False elif block_state == BLOCK.Block: pattern = re.compile(r'[\n\r\v\f\ ]') result = pattern.sub(" ", result) pattern = re.compile(r'\t') result = pattern.sub(" " * 4, result) result = "<span>" + result + "</span></br>" is_normal = False # 解析有序序列 if len(input) > 2 and input[0].isdigit() and input[1] == '.' and orderList_state == ORDERLIST.Init: orderList_state = ORDERLIST.List result = "<ol><li>" + input[2:] + "</li>" is_normal = False elif len(input) > 2 and input[0].isdigit() and input[1] == '.' and orderList_state == ORDERLIST.List: result = "<li>" + input[2:] + "</li>" is_normal = False elif orderList_state == ORDERLIST.List and (len(input) <= 2 or input[0].isdigit() == False or input[1] != '.'): result = "</ol>" + input orderList_state = ORDERLIST.Init # 解析表格 pattern = re.compile(r'^((.+)\|)+((.+))$') match = pattern.match(input) if match: l = input.split('|') l[-1] = l[-1][:-1] # 將空字元彈出列表 if l[0] == '': l.pop(0) if l[-1] == '': l.pop(-1) if table_state == TABLE.Init: table_state = TABLE.Format temp_table_first_line = l temp_table_first_line_str = input result = "" elif table_state == TABLE.Format: # 如果是表頭與表格主題的分割線 if reduce(lambda a, b: a and b, [all_same(i,'-') for i in l], True): table_state = TABLE.Table result = "<table><thread><tr>" is_normal = False # 新增表頭 for i in temp_table_first_line: result += "<th>" + i + "</th>" result += "</tr>" result += "</thread><tbody>" is_normal = False else: result = temp_table_first_line_str + "</br>" + input table_state = TABLE.Init elif table_state == TABLE.Table: result = "<tr>" for i in l: result += "<td>" + i + "</td>" result += "</tr>" elif table_state == TABLE.Table: table_state = TABLE.Init result = "</tbody></table>" + result elif table_state == TABLE.Format: pass return result # 判斷 lst 是否全由字元 sym 構成 def all_same(lst, sym): return not lst or sym * len(lst) == lst # 處理標題 def handleTitle(s, n): temp = "<h" + repr(n) + ">" + s[n:] + "</h" + repr(n) + ">" return temp # 處理無序列表 def handleUnorderd(s): s = "<ul><li>" + s[1:] s += "</li></ul>" return s def tokenTemplate(s, match): pattern = "" if match == '*': pattern = "\*([^\*]*)\*" if match == '~~': pattern = "\~\~([^\~\~]*)\~\~" if match == '**': pattern = "\*\*([^\*\*]*)\*\*" return pattern # 處理特殊標識，比如 **, *, ~~ def tokenHandler(s): l = ['b', 'i', 'S'] j = 0 for i in ['**', '*', '~~']: pattern = re.compile(tokenTemplate(s,i)) match = pattern.finditer(s) k = 0 for a in match: if a: content = a.group(1) x,y = a.span() c = 3 if i == '*': c = 5 s = s[:x+c*k] + "<" + l[j] + ">" + content + "</" + l[j] + ">" + s[y+c*k:] k += 1 pattern = re.compile(r'\$([^\$]*)\$') a = pattern.search(s) if a: global need_mathjax need_mathjax = True j += 1 return s # 處理連結 def link_image(s): # 超連結 pattern = re.compile(r'\\\[(.*)\]\((.*)\)') match = pattern.finditer(s) for a in match: if a: text, url = a.group(1,2) x, y = a.span() s = s[:x] + "<a href=" + url + " target=\"_blank\">" + text + "</a>" + s[y:] # 影象連結 pattern = re.compile(r'!\[(.*)\]\((.*)\)') match = pattern.finditer(s) for a in match: if a: text, url = a.group(1,2) x, y = a.span() s = s[:x] + "<img src=" + url + " target=\"_blank\">" + "</a>" + s[y:] # 角標 pattern = re.compile(r'(.)\^\[([^\]]*)\]') match = pattern.finditer(s) k = 0 for a in match: if a: sym,index = a.group(1,2) x, y = a.span() s = s[:x+8*k] + sym + "<sup>" + index + "</sup>" + s[y+8*k:] k += 1 return s def parse(input): global block_state, is_normal is_normal = True result = input # 檢測當前 input 解析狀態 result = test_state(input) if block_state == BLOCK.Block: return result # 分析標題標記 # title_rank = 0 for i in range(6, 0, -1): if input[:i] == '#'*i: title_rank = i break if title_rank != 0: # 處理標題，轉化為相應的 HTML 文字 result = handleTitle(input, title_rank) return result # 分析分割線標記 -- if len(input) > 2 and all_same(input[:-1], '-') and input[-1] == '\n': result = "<hr>" return result # 解析無序列表 unorderd = ['+', '-'] if result != "" and result[0] in unorderd : result = handleUnorderd(result) is_normal = False f = input[0] count = 0 sys_q = False while f == '>': count += 1 f = input[count] sys_q = True if sys_q: result = "<blockquote style=\"color:#8fbc8f\"> "*count + "<b>" + input[count:] + "</b>" + "</blockquote>"*count is_normal = False # 處理特殊標記，比如 ***, ~~~ result = tokenHandler(result) # 解析影象連結 result = link_image(result) pa = re.compile(r'^(\s)*$') a = pa.match(input) if input[-1] == "\n" and is_normal == True and not a : result+="</br>" return result def run(source_file, dest_file, dest_pdf_file, only_pdf): # 獲取檔名 file_name = source_file # 轉換後的 HTML 檔名 dest_name = dest_file # 轉換後的 PDF 檔名 dest_pdf_name = dest_pdf_file # 獲取檔案字尾 _, suffix = os.path.splitext(file_name) if suffix not in [".md",".markdown",".mdown","mkd"]: print('Error: the file should be in markdown format') sys.exit(1) if only_pdf: dest_name = ".~temp~.html" f = open(file_name, "r") f_r = open(dest_name, "w") # 往檔案中填寫 HTML 的一些屬性 f_r.write("""<style type="text/css">div {display: block;font-family: "Times New Roman",Georgia,Serif}\ #wrapper { width: 100%;height:100%; margin: 0; padding: 0;}#left { float:left; \ width: 10%; height: 100%; }#second { float:left; width: 80%;height: 100%; \ }#right {float:left; width: 10%; height: 100%; \ }</style><div id="wrapper"> <div id="left"></div><div id="second">""") f_r.write("""<meta charset="utf-8"/>""") # 逐行解析 markdwon 檔案 for eachline in f: result = parse(eachline) if result != "": f_r.write(result) f_r.write("""</br></br></div><div id="right"></div></div>""") # 公式支援 global need_mathjax if need_mathjax: f_r.write("""<script type="text/x-mathjax-config">\ MathJax.Hub.Config({tex2jax: {inlineMath: [['$','$'], ['\\(','\\)']]}});\ </script><script type="text/javascript" \ src="http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>""") # 檔案操作完成之後記得關閉！！！ f_r.close() f.close() # 呼叫擴充套件 wkhtmltopdf 將 HTML 檔案轉換成 PDF if dest_pdf_name != "" or only_pdf: call(["wkhtmltopdf", dest_name, dest_pdf_name]) # 如果有必要，刪除中間過程生成的 HTML 檔案 if only_pdf: call(["rm", dest_name]) # 主函式 def main(): dest_file = "translation_result.html" dest_pdf_file = "translation_result.pdf" only_pdf = False args = docopt(__doc__, version=__version__) dest_file = args['<outputfile>'] if args['--output'] else dest_file dest_pdf_file = args['<outputfile>'] if args['--print'] or args['--Print'] else "" run(args['<sourcefile>'], dest_file, dest_pdf_file, args['--Print']) if __name__=="__main__": main()