def postWordpress(item):
post = WordPressPost()
post.title = item.title
post.content = item.movieUrl
if item.category == "":
post.terms_names = {'post_tag': item.tags}
else:
category = []
category.append(item.category)
post.terms_names = {'post_tag': item.tags, 'category': category}
post.slug = '[input your prameter]'
# 投稿時間
# 現在時間で投稿
post.date = datetime.now()
# 予約投稿の場合（例：2017年2月2日0時0分0秒0マイクロ秒）
#month = random.randint(1,10)
#day = random.randint(1,22)
#post.date = datetime(2018, month, day, 0, 0, 0, 0)
# 投稿する。
# ステータスを公開済にする。
post.post_status = 'publish'
# これなら下書き指定
# post.post_status = 'draft'
post.thumbnail = getMediaId(item)
wp.call(NewPost(post))
def wordpress_artice(wppost_status, wp_title, wp_slug_title, wp_content,
wp_category, wp_post_tag, wp_host, wp_user, wp_password):
# 如果遇到错误就出试5次
success_num = 0
while success_num < 5:
try:
client = Client(wp_host, wp_user, wp_password)
newpost = WordPressPost() # 创建一个类实例，注意，它不是一个函数。只要在一个类名后面加上括号就是一个实例
# newpost.post_status = 'draft'
newpost.post_status = wppost_status
newpost.slug = wp_slug_title # 文章别名，固定链接形式为文章标题时需要
# 设置发布目录（一篇文章可以属于多个分类目录）
newpost.terms_names = {
'category': wp_category, # 目录
'post_tag': wp_post_tag # 标签
}
newpost.title = wp_title
newpost.content = wp_content
client.call(posts.NewPost(newpost)) #发布新建的文章，返回的是文章id
print("Wordpress发布成功：", wp_title)
except Exception as e:
print("正在重试:", e)
success_num = success_num + 1
continue
def testUpdate(pid):
client = initClient()
post = WordPressPost()
post.title = 'My new title update 2'
post.content = 'This is the body of my new post.'
post.slug = 'helloword'
post.post_type = 'post'
post.post_status = 'draft'
print client.call(posts.EditPost(pid, post))
def testUpdate(pid):
client = initClient()
post = WordPressPost()
post.title = 'My new title update 2'
post.content = 'This is the body of my new post.'
post.slug= 'helloword'
post.post_type = 'post'
post.post_status = 'draft'
print client.call(posts.EditPost(pid, post))
def import_application(data):
"""
Creates an Application post from a spreadsheet row.
:param data: Dict of imported row from csv via DictReader
:return:
"""
for app in data:
post = WordPressPost()
post.post_status = 'publish'
post.title = app['Application'].strip()
post.slug = slugify(post.title)
post.post_type = 'apps'
# Compile post body
content = html_format(app['Description'])
if app['CCX']:
content += html_format('CCX Page:' + app['CCX'])
if app['Website']:
content += html_format('Website: ' + app['Website'])
if app['POC']:
content += html_format('Contact: ' + app['POC'])
if content:
post.content = content
terms = {}
# Community terms
community = []
if app['SGC']:
community.append(app['SGC'])
if community:
terms['communities'] = community
# Status Terms
status = []
if app['Status']:
status.append(app['Status'])
if app['Sharing'] == 'Shareable':
status.append(app['Sharing'])
if status:
terms['status'] = status
# General Tags
tags = []
if app['Priority Area']:
tags.append(app['Priority Area'])
if tags:
terms['post_tag'] = tags
if terms:
post.terms_names = terms
API.call(NewPost(post))
def add_post():
post = WordPressPost()
ts = time.time()
title = 'Test Title' + datetime.datetime.fromtimestamp(ts).strftime(
'%Y-%m-%d %H:%M:%S')
post.title = title
post.content = 'This is a test post to see if the RPC call works.'
post.terms_names = {
'post_tag': ['test', 'firstpost'],
'category': ['Introductions', 'Test']
}
post.slug = slugify(title) # note this if final part of slug only
API.call(NewPost(post))
def post(wp, old_post, title, content, rtcprof, img_info):
from wordpress_xmlrpc import WordPressPost
from wordpress_xmlrpc.methods.posts import NewPost, EditPost
if old_post:
post = old_post
else:
post = WordPressPost()
post.title = title
post.content = content
post.terms_names = {
'post_tag': [rtcprof.name, 'RTC'],
'category': ['RTComponents', rtcprof.basicInfo.category]
}
post.slug = rtcprof.name
n = datetime.datetime.now()
year = n.year
month = n.month
day = n.day
hour = n.hour
if n.hour < 9:
day = day - 1
hour = hour + 24
if day == 0:
month = month - 1
if month == 0:
month = 12
year = year -1
if month in [4, 6, 9, 11]:
day = 30
elif month == 2:
day = 28
else:
day = 31
hour = hour - 9
post.date = datetime.datetime(year, month, day, hour, n.minute, n.second)
post.post_status = 'publish'
if img_info:
post.thumbnail = img_info['id']
else:
post.thumbnail = old_post.thumbnail
if old_post: # Edit Mode
wp.call(EditPost(post.id, post))
else:
wp.call(NewPost(post))
def process_post(self, content) -> Optional[WordPressPost]:
"""Create a wordpress post based on pelican content"""
if content.status == "draft":
return None
post = WordPressPost()
post.title = content.title
post.slug = content.slug
post.content = content.content
# this conversion is required, as pelican uses a SafeDateTime
# that python-wordpress-xmlrpc doesn't recognize as a valid date.
post.date = datetime.fromisoformat(content.date.isoformat())
post.term_names = {
"category": [content.category.name],
}
if hasattr(content, "tags"):
post.term_names["post_tag"] = [tag.name for tag in content.tags]
return post
def parseDocument(filename):
lines = open(filename, 'r').readlines()
values = {'title':'', 'permalink':'', 'layout':'post', 'tags':'', 'categories':'default', 'published': 'false'}
start = False
config = False
for i in range(len(lines)):
line = lines[i].strip()
if config == False:
if line == '---':
if (start == False):
start = True
else: # end
if (values['title'] == '' or values['permalink'] == ''):
printf('title and permalink should not be null!\n'); exit()
else:# config ok
config = True
else:
try:
key = line[:line.find(':')]
value = line[line.find(':')+1:]
values[key] = value.strip()
except:
printf('config failed! (key, value) = (' + key + ', ' + value + ')\n');exit()
else: #config ok
while len(lines[i]) <= 1: #filter first blank lines
i+=1
rawcontent = parseMedia(lines[i:])
rawfilename = filename[:-3] + '.raw.id-'
open(rawfilename, 'w').writelines(rawcontent)
post = WordPressPost()
post.title = values['title']
post.slug = values['permalink']
post.content = pandocTool.md2html(rawfilename)
post.post_type = values['layout']
post.post_status = 'publish' if values['published'].lower() == 'true' else 'draft'
post.comment_status = 'open' #default
post.pint_status = 'open' #default
post.terms_names = {}
#values['tags'] = values['tags'].replace('，', ',') compatible with jekyll, use blank
#values['categories'] = values['categories'].replace('，', ',')
if len(values['tags']) > 0:
post.terms_names['post_tag'] = [ tag.strip() for tag in values['tags'].split() if len(tag) > 0]
if len(values['categories']) > 0:
post.terms_names['category'] = [ cate.strip() for cate in values['categories'].split() if len(cate) > 0]
return post
def article_handle(filename):
with open(filename, encoding='utf-8') as input_file:
md_file = input_file.readlines()
md_content = ''.join(md_file[1:]) # 配置第二行以后内容为正文
if '<!--more-->' not in md_content:
if input("文章内无分页符，确认请按‘y’，其他任意键取消： ") != 'y':
sys.exit(0)
html_content = markdown.markdown(md_content) # 转换markdown为html
post_title = ''.join(md_file[:1]) # 配置首行为标题
# 手动输入文章英文地址及标签
post_slug = input('请输入文章%s地址（英文）：\n' % (post_title.split()))
post_tag = input('请输入文章tag标签，以空格分隔：\n').encode('utf-8').decode(
'utf-8').split()
# 分类暂定为“随笔”
while True:
choice = int(input("请选择文章分类：\n1、随笔；2、产品工作\n"))
if choice == 1:
post_category = ['随笔']
break
elif choice == 2:
post_category = ['产品工作']
break
else:
print('输入错误！请重新输入')
# 定义post内容
post = WordPressPost()
post.title = post_title
post.content = html_content
post.terms_names = {'post_tag': post_tag, 'category': post_category}
post.slug = post_slug
post.post_status = 'publish'
print("Article Content: \n%s\n\n\n"
"Article Title: %s - %s\n"
"Article Category: %s\n"
"Article Tag: %s\n" %
(post.content, post.title, post.slug, post.terms_names['category'],
post.terms_names['post_tag']))
confirm = input("确认请按‘y’，其他任意键取消： ")
if confirm == 'y':
return post
else:
return None
def _add_blogpost(post_data):
'''
Adds a blog post parsed from blog.blogpost
Model published status codes are as follows: PUBLISHED = 1, DRAFT = 2, DELETED = 3
:param post_data: Python dict of post structure. See modelsamples/blogpost_sample.txt for structure.
:return:
'''
post = WordPressPost()
post.post_type = 'news'
post.title = post_data['fields']['title']
post.content = post_data['fields']['content']
post.date = _return_datetime(post_data['fields']['publish_date'])
post.date_modified = _return_datetime(post_data['fields']['updated'])
post.slug = post_data['fields']['slug']
if post_data['fields']['status'] == 2:
post.post_status = 'publish'
# Assign Author
if post_data['fields']['user']:
wp_userid = _get_wordpress_user_id_by_email(
_get_django_user_email_by_id(post_data['fields']['user']))
if wp_userid:
post.user = wp_userid
# TODO set catagories and tags to proper taxonomy
# post.terms_names = {
# 'category': ['Blogpost']
# }
# if post_data['fields']['categories']:
# categories = []
# for category in dp.get_content(DJANGO_DATA, 'blog.blogcategory'):
# if category['pk'] in post_data['fields']['categories']:
# categories.append(category['fields']['title'])
# post.terms_names['post_tag'] = categories
try:
if post_data['fields']['status'] != 3:
post.id = API.call(NewPost(post))
print("created post", post.id, post.title)
except Fault as err:
pprint(post)
print(err.faultCode, err.faultString)
def wordpress_artice(wppost_status, wp_title, wp_slug_title, wp_content,
wp_category, wp_post_tag, wp_host, wp_user, wp_password):
try: # 检测是否登录成功
client = Client(wp_host, wp_user, wp_password)
newpost = WordPressPost() # 创建一个类实例，注意，它不是一个函数。只要在一个类名后面加上括号就是一个实例
# newpost.post_status = 'draft'
newpost.post_status = wppost_status
newpost.slug = wp_slug_title # 文章别名，固定链接形式为文章标题时需要
# 设置发布目录（一篇文章可以属于多个分类目录）
newpost.terms_names = {
'category': wp_category, # 目录
'post_tag': wp_post_tag # 标签
}
newpost.title = wp_title
newpost.content = wp_content
client.call(posts.NewPost(newpost)) #发布新建的文章，返回的是文章id
print("Wordpress发布成功：", wp_title)
except ServerConnectionError:
print('WordPress登录失败')
def _add_application(app_data):
'''
Adds an application parse from apps.application
:param app_data: Python dict of application structure. See modelsamples/application_sample.txt
:return:
'''
post = WordPressPost()
post.post_type = 'application'
post.title = app_data['fields']['name']
post.slug = app_data['fields']['slug']
post.content = _format_app_content(app_data)
post.date = _return_datetime(app_data['fields']['created'])
post.date_modified = _return_datetime(app_data['fields']['updated'])
# TODO assign to proper taxonomies once those are in.
# Assign Author
if app_data['fields']['owner']:
wp_userid = _get_wordpress_user_id_by_email(
_get_django_user_email_by_id(app_data['fields']['owner']))
if wp_userid:
post.user = wp_userid
# Assign Categories and Tags
post.terms_names = _parse_taxonomies(app_data)
# Put the previous page url in a custom field.
legacy_url = "https://www.us-ignite.org/apps/%s/" % (
app_data['fields']['slug'])
post.custom_fields = [{'key': 'legacy_url', 'value': legacy_url}]
# Set publish status and push to site
if app_data['fields']['status'] == 1:
post.post_status = 'publish'
try:
if app_data['fields']['status'] != 3:
post.id = API.call(NewPost(post))
except Fault as err:
pprint(err.faultString)
def addItemsToWordpress( self ):
items = self.items
if items:
wp = Client('http://' + self.wpinfo['website'] + '/xmlrpc.php', self.wpinfo['user'], self.wpinfo['pass'])
pass
for item in items:
self.log.info("[ Scrapper {} ] - [ Publishing \"{}\" into WP ]".format( self.table, item["title"] ))
now = time.strftime("%c")
post = WordPressPost()
post.terms_names = {
'category': ['Scrapped'] # This need to be changed in next release
}
post.title = '{}'.format(item['title'])
if item['slug']:
post.slug = item['slug']
if item['image_url']:
call(['curl',item['image_url'].replace(' ','%20'),'-o','image.jpg.scrapper_data'])
filename = 'image.jpg.scrapper_data'
data = {
'name': 'image.jpg',
'type': 'image/jpeg', # mimetype
}
with open(filename, 'rb') as img:
data['bits'] = xmlrpc_client.Binary(img.read())
response = wp.call(media.UploadFile(data))
attachment_id = response['id']
post.thumbnail = attachment_id
content = ''
if item['content']:
content += '{}'.format(item['content'])
content += 'Source: <a href="{}">{}</a>\n\n'.format(item['url'],item['referer'])
post.content = content
wp.call(NewPost(post))
def add_or_edit_wp_post(title, content, slug, more_info_url, local_img_file):
# first upload the image
if local_img_file:
data = {
'name': local_img_file.split('/')[-1],
'type': 'image/jpg', # mimetype
}
# read the binary file and let the XMLRPC library encode it into base64
with open(local_img_file, 'rb') as img:
data['bits'] = xmlrpc_client.Binary(img.read())
response = wp.call(media.UploadFile(data))
attachment_id = response['id']
# now post the post and the image
post = WordPressPost()
post.post_type = 'post' # stupid effing theme
post.title = title
post.content = content
post.post_status = 'publish'
post.slug = slug
if local_img_file:
post.thumbnail = attachment_id
if not get_wp_post_id(slug):
# this is a new post
wp.call(NewPost(post))
msg = "posted"
else:
# this post exists, update it
post.id = get_wp_post_id(slug)
wp.call(EditPost(post.id, post))
msg = "edited"
print "%s %s as %s" % (msg, title, post.slug)
def upload_file():
if request.method == 'POST':
url1=request.form['url']
#return(url1)
ydl_opts = {
'format': 'bestaudio/best',
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'mp3',
'preferredquality': '320',
}],
'outtmpl':'%(title)s-%(id)s.%(ext)s'
}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(url1, download=True)
mp3FileName = ydl.prepare_filename(info).replace(info['ext'], 'mp3')
print(mp3FileName)
newfile=mp3FileName.split(" ",1)[0]
identify=newfile + "mp3file"
newFileName=newfile + ".mp3"
os.rename(mp3FileName,newFileName)
audiofile=eyed3.load(newFileName)
Title= request.form['title']
if not (Title==""):
Title=Title
else:
Title="kanniyam"
Artist = request.form['artist']
if not (Artist==""):
Artist=Artist
else:
Artist="Kanniyam"
Album = request.form['album']
if not (Album==""):
Album=Album
else:
Album="Kanniyam"
Genre = request.form['genre']
if not (Genre==""):
Genre=Genre
else:
Genre="Podcast"
Source_url = bytes(request.form['source_url'],'utf-8')
if not (Source_url==""):
Source_url=Source_url
else:
Source_url=""
License = str(request.form['license'])
if not (License==""):
License=License
else:
License="https://creativecommons.org/licenses/by/4.0/"
Comments = str(request.form['comments'])
if not (Comments==""):
Comments=Comments
else:
Comments=""
Language = str(request.form['language'])
if not (Language==""):
Language=Language
else:
Language="Tamil"
Art_name = request.form['art_name']
if not (Art_name==""):
Art_name=Art_name
else:
Art_name="Kanniyam"
Publisher_url = bytes(request.form['publisher_url'],'utf-8')
if not (Publisher_url==""):
Publisher_url=Publisher_url
else:
Publisher_url="http://www.kaniyam.com"
print (type(Publisher_url))
print ("ssss")
audiofile.tag.title = u""+Title
audiofile.tag.artist = u""+Artist
audiofile.tag.album = u""+Album
audiofile.tag.genre = u""+Genre
audiofile.tag.source_url = b""+Source_url
audiofile.tag.license = u""+License
audiofile.tag.comments.set(u""+Comments, description=u"")
audiofile.tag.language = u""+Language
audiofile.tag.art_name = u""+Art_name
audiofile.tag.publisher_url = b""+Publisher_url
audiofile.tag.save()
print ("after save")
ia_upload = "ia upload " + identify + \
" -m collection:opensource -m mediatype:audio -m sponsor:Kaniyam -m language:ta " + \
newFileName
os.system(ia_upload)
audioURL = "https://archive.org/download/%s/%s" % (identify, newFileName)
print ("file uploaded")
print("Posting into WordPress")
client = Client(blog url,username,password)
post = WordPressPost()
content = "%s \n %s"% (audioURL, Comments)
post.title = Title
post.content = content
post.post_status = 'publish'
post.comment_status = 'open'
post.terms_names = {'category': ['Podcast']}
post.slug = newfile
post.id = client.call(posts.NewPost(post))
print("Posted into WordPress")
return "File updated"
def post_article(self, wpUrl, wpUserName, wpPassword, articleTitle,
articleCategories, articleContent, articleTags, PhotoUrl,
date, logo_name, post_name):
self.path = os.path.join(os.getcwd(), "00000001.jpg")
self.articlePhotoUrl = PhotoUrl
self.wpUrl = wpUrl
self.wpUserName = wpUserName
self.wpPassword = wpPassword
#Download File
print self.articlePhotoUrl
#r = requests.get(self.articlePhotoUrl,headers={'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:16.0) Gecko/20100101 Firefox/16.0,gzip(gfe)'})
#with open('test.jpg', "wb") as f:
# f.write(r.content)
from PIL import Image
from StringIO import StringIO
import urllib2
#content = r.content
self.articlePhotoUrl = self.articlePhotoUrl.replace(
'www.macappdownload.net', 'www.macbed.com')
print self.articlePhotoUrl
print 'vvvvvvvvvvvvvvvvvvvvv'
r = requests.get(
self.articlePhotoUrl,
headers={
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:16.0) Gecko/20100101 Firefox/16.0,gzip(gfe)'
})
#content = urllib2.urlopen(self.articlePhotoUrl).read()
im = Image.open(StringIO(r.content))
#im.seek(0)
#im.verify()
rgb_im = im.convert('RGB')
self.path = os.path.join(os.getcwd(), 'image', logo_name)
print self.path
rgb_im.save(self.path)
#Upload to WordPress
client = Client(self.wpUrl, self.wpUserName, self.wpPassword)
filename = self.path
# prepare metadata
data = {'name': logo_name, 'type': 'image/jpeg'}
# read the binary file and let the XMLRPC library encode it into base64
print filename
with open(filename, 'rb') as img:
data['bits'] = xmlrpc_client.Binary(img.read())
response = client.call(media.UploadFile(data))
print 'aaaaaaaaaaaa'
attachment_id = response['id']
#Post
post = WordPressPost()
post.title = articleTitle
try:
post.date = datetime.datetime.strptime(date, "%Y-%m-%d %H:%M")
post.date_modified = datetime.datetime.strptime(
date, "%Y-%m-%d %H:%M")
except:
post.date = datetime.datetime.strptime(date, "%Y-%m-%d")
post.date_modified = datetime.datetime.strptime(date, "%Y-%m-%d")
post.slug = post_name
post.comment_status = "open"
post.content = articleContent
post.terms_names = {
'post_tag': articleTags,
'category': articleCategories
}
post.post_status = 'publish'
post.thumbnail = attachment_id
post.id = client.call(posts.NewPost(post))
print 'Post Successfully posted. Its Id is: ', post.id
if post.content.find('https://nmac.to') != -1:
image = client.call(media.GetMediaItem(attachment_id))
import re
post.content = re.sub(r'https://nmac.to(\S+).png', image.link,
post.content)
client.call(posts.EditPost(post.id, post))
print 'Post Successfully updated. Its Id is: ', post.id
def upload_text(wp, repo_name, rtcprof, html, img_info = None, test=False, build_report_filename="build_report.yaml"):
from wordpress_xmlrpc.methods import posts, taxonomies, media
sys.stdout.write(' - Uploading %s\n' % rtcprof.name)
editFlag = False
post = None
for p in all_posts:
if p.title == title:
editFlag = True
post = p
break
html = update_build_status(html, build_report_filename)
if not editFlag:
post = WordPressPost()
post.title = title
post.content = apply_language_setting(html)
post.terms_names = {
'post_tag': [rtcprof.name, 'RTC'],
'category': ['RTComponents', rtcprof.basicInfo.category]
}
post.slug = rtcprof.name
n = datetime.datetime.now()
year = n.year
month = n.month
day = n.day
hour = n.hour
if n.hour < 9:
day = day - 1
hour = hour + 24
if day == 0:
month = month - 1
if month == 0:
month = 12
year = year -1
if month in [4, 6, 9, 11]:
day = 30
elif month == 2:
day = 28
else:
day = 31
hour = hour - 9
post.date = datetime.datetime(year, month, day, hour, n.minute, n.second)
post.post_status = 'publish'
post.thumbnail = img_info['id']
post.id = wp.call(NewPost(post))
return
else: # Edit Flag
#post = WordPressPost()
post.title = title
post.content = apply_language_setting(html)
post.terms_names = {
'post_tag': [rtcprof.name, 'RTC'],
'category': ['RTComponents']
}
post.slug = rtcprof.name
n = datetime.datetime.now()
year = n.year
month = n.month
day = n.day
hour = n.hour
if n.hour < 9:
day = day - 1
hour = hour + 24
if day == 0:
month = month - 1
if month == 0:
month = 12
year = year -1
if month in [4, 6, 9, 11]:
day = 30
elif month == 2:
day = 28
else:
day = 31
hour = hour - 9
post.date = datetime.datetime(year, month, day, hour, n.minute, n.second)
post.post_status = 'publish'
post.thumbnail = img_info['id']
wp.call(posts.EditPost(post.id, post))
"""!!! EDIT THESE VALUES, MAKE SURE TO LEAVE /XMLRPC.PHP AT THE END !!!"""
xmlrpc_endpoint = 'http://eidmantas.com/xmlrpc.php'
username = '******'
password = '******'
wp = Client(xmlrpc_endpoint, username, password)
"""!!! DONT FORGET TO UPLOAD YOUR FILE AND CHANGE ITS NAME, OR THE VARIABLE HERE !!!"""
filename = 'your-ghost-export-file.json'
with open(filename) as f:
text = f.read()
data = json.loads(text)
for p in data['db'][0]['data']['posts']:
print p['title']
date = p.get('published_at', None)
if date is None:
p.get('created_at')
post = WordPressPost()
post.slug = p['slug']
post.content = p['html']
post.title = p['title']
post.post_status = 'publish'
try:
post.date = parse(date)
except:
exit
wp.call(NewPost(post))
#!/usr/bin/env python3
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import GetPosts, NewPost
from config import blog_url, username, password
wp = Client(blog_url, username, password)
post = WordPressPost()
post.title = 'Testing post.title.'
post.content = 'Testing post.content. This is a test.'
post.slug = 'Testing post.slug'
post.terms_names = {
'post_tag': ['IPA', 'UK'],
'category': ['BeerBods cheat sheets']
}
wp.call(NewPost(post))
import sys
import markdown2
from markdown2 import Markdown
import frontmatter
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import GetPosts, NewPost
from wordpress_xmlrpc.methods.users import GetUserInfo
dir = sys.argv[1]
post = frontmatter.load(dir)
post_title = post.metadata['title']
markdowner = Markdown()
post_content_html = markdowner.convert(post.content)
post_content_html = post_content_html.encode("utf-8")
wp = Client('https://finrodchen.net/xmlrpc.php', 's02260441', 'simontp6nm06')
post = WordPressPost()
post.post_status = 'draft'
post.title = post_title
post.content = post_content_html
post.slug = post_title
post.terms_names = {'category': ['特管辦法']}
wp.call(NewPost(post))
xmlrpc_endpoint = 'http://eidmantas.com/xmlrpc.php'
username = '******'
password = '******'
wp = Client(xmlrpc_endpoint, username, password)
"""!!! DONT FORGET TO UPLOAD YOUR FILE AND CHANGE ITS NAME, OR THE VARIABLE HERE !!!"""
filename = 'your-ghost-export-file.json'
with open(filename) as f:
text = f.read()
data = json.loads(text)
for p in data['db'][0]['data']['posts']:
print p['title']
date = p.get('published_at', None)
if date is None:
p.get('created_at')
post = WordPressPost()
post.slug = p['slug']
post.content = p['html']
post.title = p['title']
post.post_status = 'publish'
try:
post.date = parse(date)
except:
exit
wp.call(NewPost(post))
பிற வடிவங்களில் படிக்க – ''' + book_url + '''
புத்தக எண் - ''' + str(book_number) + '''
'''
print("Publising the Ebook")
content = content + extra
post.title = book_title + " - " + category + " - " + author
post.slug = book_title_in_english
post.post_type = 'ebooks'
post.content = content
post.thumbnail = attachment_id
post.comment_status = 'open'
post.post_status = 'publish'
#post.post_status = 'draft'
if artist:
post.terms_names = {
'genres': [category],
'contributors': [artist, ebook_maker],
'authors': [author]
# 認証する
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import GetPosts, NewPost
from wordpress_xmlrpc.methods.users import GetUserInfo
wp = Client('http://thisissample.wp.xdomain.jp/xmlrpc.php', 'sample007', 'vvq1meoczwc7')
# 投稿する
post = WordPressPost()
# タイトル
post.title = 'My new title'
post.content = 'This is the body of my new post.'
# タグ
post.terms_names = {
'post_tag': ['test', 'firstpost'],
'category': ['Introductions', 'Tests']
}
# 投稿URL
post.slug = 'sample'
# 投稿日時
# 投稿状態 指定なしで下書き
post.post_status="publish"
# 投稿する。
wp.call(NewPost(post))
def parseDocument(filename):
lines = open(filename, 'r').readlines()
values = {
'title': '',
'permalink': '',
'layout': 'post',
'tags': '',
'categories': 'default',
'published': 'false'
}
start = False
config = False
for i in range(len(lines)):
line = lines[i].strip()
if config == False:
if line == '---':
if (start == False):
start = True
else: # end
if (values['title'] == '' or values['permalink'] == ''):
printf('title and permalink should not be null!\n')
exit()
else: # config ok
config = True
else:
try:
key = line[:line.find(':')]
value = line[line.find(':') + 1:]
values[key] = value.strip()
except:
printf('config failed! (key, value) = (' + key + ', ' +
value + ')\n')
exit()
else: #config ok
while len(lines[i]) <= 1: #filter first blank lines
i += 1
rawcontent = parseMedia(lines[i:])
rawfilename = filename[:-3] + '.raw.id-'
open(rawfilename, 'w').writelines(rawcontent)
post = WordPressPost()
post.title = values['title']
post.slug = values['permalink']
post.content = pandocTool.md2html(rawfilename)
post.post_type = values['layout']
post.post_status = 'publish' if values['published'].lower(
) == 'true' else 'draft'
post.comment_status = 'open' #default
post.pint_status = 'open' #default
post.terms_names = {}
#values['tags'] = values['tags'].replace('，', ',') compatible with jekyll, use blank
#values['categories'] = values['categories'].replace('，', ',')
if len(values['tags']) > 0:
post.terms_names['post_tag'] = [
tag.strip() for tag in values['tags'].split()
if len(tag) > 0
]
if len(values['categories']) > 0:
post.terms_names['category'] = [
cate.strip() for cate in values['categories'].split()
if len(cate) > 0
]
return post
os.system(ia_upload)
audioURL = "https://archive.org/download/%s/%s" % (
ia_identifier, audioTitleInEnglish + ".mp3")
print("Uploaded to " + audioURL)
print("Posting into WordPress")
wp_username = audio_info['wp_username']
wp_password = audio_info['wp_password']
wpBlogUrl = audio_info['wp_blog_url'] + '/xmlrpc.php'
client = Client(wpBlogUrl, wp_username, wp_password)
post = WordPressPost()
content = "%s \n %s" % (audioURL, audioComments)
post.title = title
post.content = content
post.post_status = 'publish'
post.comment_status = 'open'
post.terms_names = {'category': ['Podcast']}
post.slug = audioTitleInEnglish
if "kaniyam.com" in wpBlogUrl:
post.post_type = 'podcast'
post.terms_names = ""
print("Publishing to Kaniyam")
post.id = client.call(posts.NewPost(post))
print("Posted into WordPress")
def post():
#get id
post_id = re.search(':wp_id:((.*)|\n)', asc_file_read_str).group(1).strip()
#get status
post_status = re.search(':wp_status:((.*)|\n)', asc_file_read_str)
#get title
post_title = re.search(':wp_title:((.*)|\n)', asc_file_read_str)
#get slug
post_slug = re.search(':wp_slug:((.*)|\n)', asc_file_read_str)
#get category
post_category = re.search(':wp_category:((.*)|\n)', asc_file_read_str)
post_category_str = post_category.group(1).strip().split(", ")
if len(post_category_str) == 0:
post_category_str = []
elif post_category.group(1).strip() == '':
post_category_str = []
elif len(post_category_str) == 1:
post_category_str = post_category.group(1).strip(),
#get tag
post_tag = re.search(':wp_tag:((.*)|\n)', asc_file_read_str)
post_tag_str = post_tag.group(1).strip().split(", ")
if len(post_tag_str) == 0:
post_tag_str = []
elif post_tag.group(1).strip() == '':
post_tag_str = []
elif len(post_tag_str) == 1:
post_tag_str = post_tag.group(1).strip(),
#get excerpt
post_excerpt = re.search(':wp_excerpt:((.*)|\n)', asc_file_read_str)
#get thumbnail
post_thumbnail = re.search(':wp_thumbnail:((.*)|\n)', asc_file_read_str)
#post to wordpress
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods import posts
client = Client(xmlrpc_url, username, password)
post = WordPressPost()
date_ = datetime.now()
#id New or Edit
if not post_id:
post.date = date_.strftime("%s")
post.id = client.call(posts.NewPost(post))
mode = "New"
asc_file_re = re.sub(r':wp_id:((.*)|\n)', ':wp_id: ' + post.id , asc_file_read_str)
asc_file_write = open(filepath, 'w')
try:
asc_file_write.write( asc_file_re )
finally:
asc_file_write.close()
else:
post.date_modified = date_.strftime("%s")
post.id = post_id
mode = "Edit"
post.post_status = post_status.group(1).strip()
try:
post.title = post_title.group(1).strip()
except:
print 'Title is not exist'
try:
post.slug = post_slug.group(1).strip()
except:
print 'Slug is not exist'
post.content = html
try:
post.excerpt = post_excerpt.group(1).strip()
except:
post.excerpt = ''
post.terms_names = {
'category': post_category_str,
'post_tag': post_tag_str,
}
try:
post.thumbnail = post_thumbnail.group(1).strip()
except:
post.thumbnail = ''
client.call(posts.EditPost(post.id, post))
post_info = client.call(posts.GetPost(post.id, post))
#get post info from wordpress
asc_file_read_slug = open(filepath, 'r')
asc_file_read_slug_str = asc_file_read_slug.read()
if post_info:
asc_file_read_slug_str = re.sub(r':wp_slug:((.*)|\n)', ':wp_slug: ' + post_info.slug, asc_file_read_slug_str)
if mode == "New":
new_date = int(post_info.date.strftime("%s"))+(timezone___*60*60)
new_date = datetime.fromtimestamp(new_date).strftime("%Y-%m-%d %H:%M:%S")
asc_file_read_slug_str = re.sub(r':wp_date:((.*)|\n)', ':wp_date: ' + new_date, asc_file_read_slug_str)
elif mode == "Edit":
edit_date = int(post_info.date_modified.strftime("%s"))+(timezone___*60*60)
edit_date = datetime.fromtimestamp(edit_date).strftime("%Y-%m-%d %H:%M:%S")
asc_file_read_slug_str = re.sub(r':wp_modified:((.*)|\n)', ':wp_modified: ' + edit_date, asc_file_read_slug_str)
asc_file_re_slug_write = open(filepath, 'w')
try:
asc_file_re_slug_write.write( asc_file_read_slug_str )
finally:
asc_file_re_slug_write.close()
print '==========================\n' + mode + ' Post ID: ' + post.id + ' \nStatus: ' + post.post_status + '\nTitle: ' + post.title + '\nSlug: ' + post_info.slug + '\nCategory: ' + post_category.group(1).strip() + '\nTag: ' + post_tag.group(1).strip() + '\n'
def main():
fileName = '2000.txt'
base_url = 'https://law.justia.com'
url_list = []
# Source file with links to scrape and upload
with open(fileName, 'r') as f:
url_list = f.readlines()
# Main loop
for page in url_list[:]:
full_link = base_url + page.strip()
soup = connect(full_link)
cat_list = []
# Navigation elements:
nav = soup.find('nav',
{'class': 'breadcrumbs small-font font-helvetica'})
print '\nStarting with url:', base_url + page.strip()
if not nav.contents[-1].strip().encode('utf-8'):
c = nav.prettify().split('<span class="breadcrumb-separator">')
soup2 = BeautifulSoup(
''.join(c).replace("\n", '').replace('<em>', ''),
'html.parser')
tmp = []
for i in soup2:
tmp.append(i)
tag = tmp[-1].replace(' ', ' ').strip().encode('utf-8')
print 'Tag:', tag
else:
tag = nav.contents[-1].strip().encode('utf-8')
print 'Tag:', tag
# Getting categories:
for i in nav.findAll('a'):
if not i.text == None and not i.text == 'Justia':
cat_list.append(i.text)
print 'Category:', cat_list
# Getting Title
title = soup.find('h1').get_text(' ')
title2 = soup.find('h1').get_text('<br>')
print 'Title:', title.encode('utf-8')
# Getting rid of Title(h1), Metadata links, Download PDF links, Front Matter links
[x.extract() for x in soup.findAll('h1')]
try:
[x.extract() for x in soup.find('a', {'id': 'metadata-link'})]
[x.extract() for x in soup.find('div', {'id': 'metadata'})]
except TypeError:
'Possible type error when trying to remove "metadata" references.'
try:
[x.extract() for x in soup('li', text=re.compile('Front Matter'))]
except AttributeError:
"Probably element 'Front Matter' wasn't found"
try:
[x.extract() for x in soup.find('div', {'class': 'downloadlink'})]
except TypeError:
'Possible type error when trying to remove "downloadLink"'
[x.extract() for x in soup('a', text=re.compile('Download PDF'))]
# Remove tags that don't contain any text
[x.extract() for x in soup.findAll() if x.text.isspace()]
results = soup.find('div',
{'class': 'wrapper jcard has-padding-30 blocks'})
# Body of page
body = unicode(results).replace('\\n',
'').replace('<br>',
'').replace("</br>", "")
# Dealing with internal navigation
try:
for a in soup.findAll('a'):
a['href'] = a['href'].replace('index.html', '')
a['href'] = a['href'].replace('/', '')
except KeyError:
print 'Some key error when dealing with internal link navigation;'
cat_list.append(tag)
for i in range(len(cat_list)):
cat_list[i] = cat_list[i][:180]
# Wordpress procedures:
# Used for retrying if there was an error while uploading
retries = 0
retries_bool = False
while retries < 4:
try:
client = Client('https://www.statutebase.com/xmlrpc.php',
'<USERNAME>', '<PASSWORD')
body = unicode(results).replace('\\n', '').replace(
'<br>', '').replace("</br>", "")
post = WordPressPost()
post.title = title2[:100]
post.slug = page.replace('/', '')
post.post_status = 'publish'
post.content = body
post.terms_names = {
'post_tag': cat_list[2:],
'category': cat_list[:2],
}
post.id = client.call(posts.NewPost(post))
retries = 5
retries_bool = True
print 'Article uploaded!'
except Exception as e:
time.sleep(5)
retries = retries + 1
retries_bool = False
if '500' in e:
print 'Error 500 detected. Skipping current article'
retries = True
print 'Error while trying to upload:', e
pass
if retries_bool == False:
with open(fileName[:fileName.find('.txt')] + '_errors.txt',
'a') as f:
f.write(page.strip() +
'\n') # Write url on which error occured
time.sleep(0.5)
