.replace('<a href', '<span href') \
.replace('</a>', '</span>')
def get_name(link):
fname = link.split('/')[-1]
return fname.split('.')[0]
for child in root[0]:
if child.tag != 'item':
continue
link = child.find('link').text
title = child.find('title').text.encode('utf-8')
name = get_name(link) + '.md'
file_path = '../pages/' + channel + '/' + name
#if True:
if not os.path.exists(file_path):
print file_path
content = get_content(title, link)
macros.write_page(channel, name, file_path, title, link, content)
index_page += '#### [' + title + '](' + file_path + ') \n'
index_file = open('../indexes/' + channel + '.md', 'w')
index_file.write(index_page)
index_file.close()
.replace('src="//img3.', 'src="https://img3.') \
.replace('src="//img4.', 'src="https://img4.') \
.replace('<a href', '<span href') \
.replace('</a>', '</span>')
def get_name(link):
fname = link.split('/')[-1]
return fname.split('.')[0]
# sync single page
if len(sys.argv) > 3 :
print sys.argv[5]
content = get_content(sys.argv[4], sys.argv[5])
macros.write_page(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5], content)
sys.exit(1)
tree = ET.parse(xml_file)
root = tree.getroot()
for child in root[0]:
if child.tag != 'item':
continue
link = child.find('link').text
title = child.find('title').text.encode('utf-8')
name = get_name(link) + '.md'
file_path = '../pages/' + channel + '/' + name
aid = fname.split('.')[0]
return aid
index_text = requests.get(channel_url).text.encode('utf-8')
index_html = BeautifulSoup(index_text, 'html.parser')
articles = index_html.find('div', attrs={
'class': 'list_wrapper'
}).find_all('div', attrs={'class': 'one_post'})
for article in articles:
a_links = article.find_all('a')
if len(a_links) < 2:
continue
link = a_links[1]
a_url = link.get('href').encode('utf-8')
a_title = link.text.encode('utf-8').strip()
name = get_name(a_url) + '.md'
file_path = '../pages/' + channel + '/' + name
#content = get_content(a_url)
if not os.path.exists(file_path):
#if True:
print file_path
content = get_content(a_url)
macros.write_page(channel, name, file_path, a_title, a_url, content)
index_page += '#### [' + a_title + '](' + file_path + ') \n'
index_file = open('../indexes/' + channel + '.md', 'w')
index_file.write(index_page)
index_file.close()