# get title from title
# get content from article
# finish requests while article

# difficult @ filter out the correct content from so many <p>...</p>
# and format different content.
import re
import requests
import time
import random
import urllib3
from bs4 import BeautifulSoup

#def getimg(link):
	

def run(filename,textString):
    src = open(filename,'a')
    # Solved
    # 1. bold
    # 2. img and figcaption
    # 3. title and contents
    # 4. italics
    # 5. code
    # 6. nonsense tags
    # 7. quote ### multi_quote TODO
    # 8. delete
    # 9. toc
    # 10.link
    # 11.p
    # 12.add toc
    # 13.formula ### TODO

    toc_flag = 0
    i = 0
    l = '- '
    quote_flag = 0
    code_flag = 0
    title_flag = 0
    #for line in src.readlines():
    for line in textString.split('\n'):
        if len(line) ==0:
            continue


        templine = line
        #### replace figcaption
        if re.search('</?(?<=figcaption)[^<]*>',templine):
            continue

        #### replace [toc]
        if re.search('(?<=<div)[^<]+?(?=toc)[^<]+?>',templine):
            toc_flag = toc_flag + 1
        elif re.search('</div>',line):
            toc_flag = toc_flag - 1
        if toc_flag:
            continue
        

        templine = re.sub('<code\s[^<]*inline[^<]*>', '<code>', templine)

        code_inline = re.search('(?<=<code>).*(?=</code>)',templine)
        if code_inline:
            #print('===========' + str(code_inline.group()))
            templine = re.sub('</?code>', '`', templine)

        if re.search('<code\s[^<]+?>',templine):
            code_flag = 1
            codetype = re.search('(?<=language-)([^\"]+?)(?=\")',templine)
            if codetype:    
                #titlelevel = re.search('(?<=<h)([0-9])(?=[^<]+?>$)',templine)
                #print(titlelevel.group())
                #print(codetype.group())
                templine = re.sub('<code\s[^<]+?>','```'+str(codetype.group())+"\n",templine).strip()
            else:
                templine = re.sub('<code\s[^<]+?>','```\n',templine).strip()

        templine = re.sub('</?code>','\n```',templine).strip()
        
   
        #### replace image
        try:
            full_img = re.search('(?<=<img).*(?=/>)',templine)
            #print(full_img.group())
            img_name_group = re.search('(?<=alt=\")[^\"]+?(?=\")',str(full_img.group()))
            img_group = re.search('(?<=src=\")([^\"]+?)(?=\")',str(full_img.group()))
            #print(img.group())
            #print(img_name.group())
            img_name = str(img_name_group.group())
            img = str(img_group.group())
            if len(img_name) <= 1 or img_name.startswith('im'):
                img_name = ''
            else:
                img_name = str(img_name_group.group())
            
            templine = re.sub('<img[^<]+?/>','\n!['+str(img_name)+']('+str(img)+')\n',templine).strip()
        except:
            templine = re.sub('<img[^<]+?/>','![load img faild]()',templine).strip()

            #templine = re.sub('<img[^<]+?/>','!['+str(img_name)+']('+str(img)+')',templine).strip()
        
        #### replace bold
        templine = re.sub('</?strong[^<]*>','**',templine).strip()
        templine = re.sub('</?(b>|b\s[^<]*>)','**',templine).strip() # conflict with blockquote
        templine = re.sub('</?em[^<]*>','**',templine).strip()

        #### replace italics
        templine = re.sub('</?i[^<]*>','*',templine).strip()
        
        #### replace delete
        templine = re.sub('</?del[^<]*>','~~',templine).strip()
        templine = re.sub('</?s>','~~',templine).strip()
                        
        #### replace list
        #if re.search('<ol[^<]*>',templine):
        #	i = 1
        #elif re.search('</ol[^<]*>',templine):
        #	i = 0
        #	l = '- '
                        
        if i != 0:
            if re.search('<li>',templine):
                l = str(i) + '. '
                templine = re.sub('<li>',str(i) + '. ',templine).strip()
                i = i + 1

        templine = re.sub('<li>',l,templine).strip()
        templine = re.sub('</li>','\n',templine).strip()


        #### replace link
        try:
            full_link_group = re.search('(?<=<a)[^<]+?(?=href)[^<]+?(?=</a>)',templine)
            full_link = str(full_link_group.group())
            link_href_group = re.search('(?<=href=\").*(?=\")',full_link)
            link_href = str(link_href_group.group())
            #print(link_href)
            link_text_group = re.search('(?<=>).*',full_link)
            link_text = str(link_text_group.group())
            #print(link_text)
            templine = re.sub('<a[^>]+?>.*</a>','['+link_text+']('+link_href+')',templine).strip()
        except:
            templine = templine
        
        #### replace p
        #lineval = re.sub('<p[^<]*>','',templine).strip()
        #if re.search('</p[^<]*>',templine):
                        #print("")
        templine = re.sub('<p[^<]*>','',templine).strip()
        templine = re.sub('</p[^<]*>','\n',templine).strip()+'\n'
        
        #### 1. replace quote
        if re.search('<blockquote[^<]*>',templine):
            quote_flag = quote_flag + 1
            print("> ",end="")
            #templine = re.sub('<blockquote[^<]*>', '>  ', templine).strip()
            templine = re.sub('<blockquote[^<]*>', '', templine).strip()
            src.write('> ')
        elif re.search('</blockquote[^<]*>',templine):
            quote_flag = quote_flag - 1
            templine = re.sub('</blockquote[^<]*>', '', templine).strip()
                            
        if quote_flag:
            print(templine,end=" ")
            src.write(templine)
            continue

        #### replace different level title
        #templine = re.sub('<h1[^<]*>','# ',templine).strip()
        templine = re.sub('<h1[^<]*>','## ',templine).strip()
        templine = re.sub('<h2[^<]*>','## ',templine).strip()
        templine = re.sub('<h3[^<]*>','### ',templine).strip()
        templine = re.sub('<h4[^<]*>','#### ',templine).strip()
        templine = re.sub('<h5[^<]*>','##### ',templine).strip()
        templine = re.sub('<h6[^<]*>','###### ',templine).strip()
        templine = re.sub('</h[0-9].*>','',templine).strip()
        if re.search('</?title[^<]*>',templine):
            templine = re.sub('</?title[^<]*>','',templine).strip()
            #### replace all tags
            templine = re.sub('<[^<]+?>', '', templine).strip()

            print('# '+templine+'\n[toc]\n')
            src.write('# '+templine+'\n[toc]\n')
            continue

        #### replace h1 and title
        #if re.search('</?title[^<]*>',templine):
        #	title_flag = 1
        #	templine = re.sub('</?title[^<]+?>','',templine).strip() + '\n[toc]\n'
        #	src.write('# ')
        #	if re.search('<h1[^<]*>',templine):
        #		templine = re.sub('<h1[^<]*>','## ',templine).strip()
        #		title_flag = 0
                
        #if title_flag and re.search('<h1[^<]*>',templine):
        #	templine = re.sub('<h1[^<]*>','## ',templine).strip()
        #else:
        #	templine = '# ' + re.sub('</?h1[^<]+?>','',templine).strip() + '\n[toc]\n'
        

        #### replace all tags
        templine = re.sub('</?code>', '`', templine).strip()
        templine = re.sub('<[^<]+?>', '', templine).strip()

        
        lineval = templine + '\n'
        
        print(lineval)
        if len(lineval) == 0:
            continue
        else:
            src.write(lineval+'\n')

    src.close()

if __name__ == '__main__':
#   hi = '# '
#   hii = '## '
#   hiii = '### '
#   hiv = '#### '
#   hv = '##### '
#   hvi = '###### '
#   code_inline = '`'
#   code_inblock = '```'
#   bold = '**'
#   italics = '*'
#   delete_line = '~~'

    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

    heads = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'} 
    des = open("blog.md","w")
    des.write('')
    des.close()
    #des = open('blog.md','a')
    
    url = input("Please input a legal URL: ")
    while not url.startswith('http'):
        url = input("Please input a legal URL again : \n")
    
    try:
        res = requests.get(url,timeout=30,headers=heads,verify=False)
        res.encoding = 'UTF-8'
        content = res.text
        #print(content)

        soup = BeautifulSoup(content,'html.parser')
        if 'zhihu.com' in url:
            temp_article = soup.find('div',class_='Post-RichTextContainer')
        elif 'csdn.net' in url:
            temp_article = soup.article
        elif 'cnblogs.com' in url:
            temp_article = soup.find('div',class_='markdown-here-wrapper')

        article = str(temp_article)
    except:
        print("request error")
        exit(1)

    try:
        title = soup.find('title')
        target_head = str(soup.title)
        #print("%s\n" % ("# "+title.text+"\n"+"[toc]"))
        #title_text = '# '+title.text+'\n[toc]\n'
        #des.write("# "+title.text+"\n"+"[toc]\n")

    except:
        print("===== title not found =====")
        h1 = soup.find('h1')
        target_head = str(soup.h1)
        #print("%s\n" % ("#"+h1.text+"\n"+"[toc]"))
        #des.write("# "+h1.text+"\n"+"[toc]\n")
    #run(article)
    target_text = target_head + article
    #print(target_text)
    #des.write(article)
    #des.close()
    run('blog.md',target_text)
    #run('blog.md')