Difference between revisions of "Update bookmarks from file"

From MythTV Official Wiki
Jump to: navigation, search
m
(from scratch rewrite to use the Python bindings)
Line 1: Line 1:
This is some very basic [http://www.python.org Python] code to simply remove all the existing websites and replace them with ones from your bookmarks file.
+
This script is part of a number of example scripts, intended to serve as a guide to using the new [[Python bindings]] rewritten for MythTV 0.23.
  
I'm not sure where to send this to make it available, hopefully this page will get spotted and shuffled off into the right place.
+
This script will flush the existing list of websites from the MythBrowser, and supplement it with websites from an HTML file, as generated by Firefox's export utility. It accepts a filename on the command line, otherwise using '~/bookmarks.html'.
{{Python|bookmarks.py|
+
 
 +
{{Python|myth_video_scan.py|
 
<pre>
 
<pre>
#Assumes you're using MySQL
+
#!/usr/bin/env python
import MySQLdb
+
# -*- coding: UTF-8 -*-
 +
#----------------------
 +
 
 +
import os
 +
import sys
 +
from HTMLParser import HTMLParser
 +
try:
 +
    from MythTV import MythDB, DBDataWrite
 +
except:
 +
    print 'ERROR: The python bindings are not installed'
 +
    sys.exit(-1)
 +
 
 +
class Bookmark( DBDataWrite ):
 +
    table = 'websites'
 +
    where = 'id=%s'
 +
    setwheredat = 'self.id,'
 +
    defaults = {'id':None, 'category':'Bookmark', 'name':u'', 'url':u''}
 +
 
 +
    def create(self, data=None):
 +
        DBDataWrite.create(self, data)
 +
        self.wheredat = (self.id,)
 +
        self._pull()
 +
        return self
 +
 
 +
class Parser( HTMLParser ):
 +
    def __init__(self):
 +
        HTMLParser.__init__(self)
 +
        self.stack = []
 +
    def handle_starttag(self, tag, attrs):
 +
        if tag == 'h3':
 +
            # new category, push to stack
 +
            self.stack.append('h3')
 +
        elif not len(self.stack):
 +
            # no categories, refuse links
 +
            return
 +
        elif tag == 'a':
 +
            # new bookmark, push to stack
 +
            d = dict(attrs)
 +
            self.stack.append(d['href'])
 +
            self.stack.append('a')
 +
    def handle_endtag(self, tag):
 +
        if not len(self.stack):
 +
            # empty stack, do nothing
 +
            return
 +
        elif tag == 'dl':
 +
            # drop out of category, pop from stack
 +
            self.stack.pop()
 +
    def handle_data(self, data):
 +
        if not len(self.stack):
 +
            # empty stack, do nothing
 +
            return
 +
        elif self.stack[-1] == 'h3':
 +
            # new category name, swap on stack
 +
            self.stack[-1] = data
 +
        elif self.stack[-1] == 'a':
 +
            # new link name, swap on stack
 +
            self.stack[-1] = data
 +
            # create new bookmark in database
 +
            b = Bookmark(db=db)
 +
            b.name = self.stack.pop()
 +
            b.url = self.stack.pop()
 +
            b.category = self.stack[-1]
 +
            b.create()
 +
 
 +
# select file
 +
bookmark_file = '~/bookmarks.html'
 +
if len(sys.argv) == 2:
 +
    bookmark_file = sys.argv[1]
 +
 
 +
# check if file exists
 +
if not os.access(os.path.expanduser(bookmark_file), os.F_OK):
 +
    print 'ERROR: bookmark file could not be found'
 +
    sys.exit(-1)
  
#------ Settings ---------
+
# connect to database
bookmarksFile = "~/bookmarks.html"
+
try:
db = MySQLdb.connect(host="mythdbserver", user="mythtv", passwd="mythtv", db="mythconverg")
+
    db = MythDB()
#-------------------------
+
except:
 +
    print 'ERROR: database could not be accessed'
 +
    sys.exit(-1)
  
#Remove all existing website entries
+
# flush old entries and reset counter
deleter = db.cursor()
+
c = db.cursor()
deleter.execute("DELETE FROM websites")
+
c.execute("""TRUNCATE TABLE websites""")
 +
c.close()
  
bookmarks = open(bookmarksFile,"r+t")
+
# read in file
cursor = db.cursor()
+
fp = open(os.path.expanduser(bookmark_file))
urls=[]
+
data = ''.join(fp.readlines())
currentGroupName = "Auto"
+
fp.close()
for line in bookmarks:
 
urlStart=line.find("http")
 
if urlStart !=-1:
 
urlEnd= line.find('"',urlStart)
 
url = line[urlStart:urlEnd]
 
if url not in urls:
 
descStart=line.find('>',urlEnd)
 
descEnd = line.find('<',descStart)
 
dsc=line[descStart+1:descEnd]
 
cursor.execute("INSERT INTO websites (grp, dsc, url) VALUES ('" + currentGroupName + "','" + dsc + "','" + url + "')")
 
urls.append(url)
 
  
groupNameFound = line.startswith("    <DT><H3")
+
# parse file for bookmarks
if groupNameFound:
+
parser = Parser()
groupNameStarts=line.find(">",11)
+
parser.feed(data)
groupNameEnds=line.find("<",groupNameStarts)
 
currentGroupName=line[groupNameStarts+1:groupNameEnds]
 
 
</pre>
 
</pre>
 
}}
 
}}
 
+
[[Category:Scripts]]
 
[[Category:Python Scripts]]
 
[[Category:Python Scripts]]

Revision as of 08:31, 30 March 2010

This script is part of a number of example scripts, intended to serve as a guide to using the new Python bindings rewritten for MythTV 0.23.

This script will flush the existing list of websites from the MythBrowser, and supplement it with websites from an HTML file, as generated by Firefox's export utility. It accepts a filename on the command line, otherwise using '~/bookmarks.html'.


PythonIcon.png myth_video_scan.py

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
#----------------------

import os
import sys
from HTMLParser import HTMLParser
try:
    from MythTV import MythDB, DBDataWrite
except:
    print 'ERROR: The python bindings are not installed'
    sys.exit(-1)

class Bookmark( DBDataWrite ):
    table = 'websites'
    where = 'id=%s'
    setwheredat = 'self.id,'
    defaults = {'id':None, 'category':'Bookmark', 'name':u'', 'url':u''}

    def create(self, data=None):
        DBDataWrite.create(self, data)
        self.wheredat = (self.id,)
        self._pull()
        return self

class Parser( HTMLParser ):
    def __init__(self):
        HTMLParser.__init__(self)
        self.stack = []
    def handle_starttag(self, tag, attrs):
        if tag == 'h3':
            # new category, push to stack
            self.stack.append('h3')
        elif not len(self.stack):
            # no categories, refuse links
            return
        elif tag == 'a':
            # new bookmark, push to stack
            d = dict(attrs)
            self.stack.append(d['href'])
            self.stack.append('a')
    def handle_endtag(self, tag):
        if not len(self.stack):
            # empty stack, do nothing
            return
        elif tag == 'dl':
            # drop out of category, pop from stack
            self.stack.pop()
    def handle_data(self, data):
        if not len(self.stack):
            # empty stack, do nothing
            return
        elif self.stack[-1] == 'h3':
            # new category name, swap on stack
            self.stack[-1] = data
        elif self.stack[-1] == 'a':
            # new link name, swap on stack
            self.stack[-1] = data
            # create new bookmark in database
            b = Bookmark(db=db)
            b.name = self.stack.pop()
            b.url = self.stack.pop()
            b.category = self.stack[-1]
            b.create()

# select file
bookmark_file = '~/bookmarks.html'
if len(sys.argv) == 2:
    bookmark_file = sys.argv[1]

# check if file exists
if not os.access(os.path.expanduser(bookmark_file), os.F_OK):
    print 'ERROR: bookmark file could not be found'
    sys.exit(-1)

# connect to database
try:
    db = MythDB()
except:
    print 'ERROR: database could not be accessed'
    sys.exit(-1)

# flush old entries and reset counter
c = db.cursor()
c.execute("""TRUNCATE TABLE websites""")
c.close()

# read in file
fp = open(os.path.expanduser(bookmark_file))
data = ''.join(fp.readlines())
fp.close()

# parse file for bookmarks
parser = Parser()
parser.feed(data)