def print_enhanced_table(self):
"""Parses CSV table already containing at least two columns with Spanish/English word pairs. The third column is optional and usually contains a 'checked' flag, which
declares whether a word has been already validated. The generated table will contain an extra row for a normalized version of the original Spanish word, an extra row
for translation (from SpanishDict.com) and an extra column for the word type (e.g. noun).
Keyword arguments:
src -- path to input CSV file
out -- output stream
"""
thread_pool = ThreadPool(self.__print_enhanced_row)
rows = self._parse_src()
self.print_header_row(rows[0].get_column_format() if len(rows) > 0 else self._column_format.split('|'))
for row in rows:
if len(row) < 2:
print('Skip incomplete row')
else:
p = Processable(lambda word: Wordanalyzer.get_translation_es(word), row.original_word, row)
p.start()
thread_pool.add(p)
#end if
#end for
thread_pool.finish()
def get_cats_thread(self, cat):
subcats = self.get_sub_cats("http://top.taobao.com/level2.php?cat=%s" % cat["id"], "cat", 2)
if len(subcats) == 1:
cat["children"] = self.get_sub_cats_thread(subcats[0])
return cat
threadPool = ThreadPool(len(subcats) if len(subcats) <= 5 else 5)
for sc in subcats:
threadPool.run(self.get_sub_cats_thread, callback=None, sc=sc)
cat["children"] = threadPool.killAllWorkers(None)
return cat
def get_top_keywords(self, cats=None, parent=None, up=True):
"""Get top keywords for all the categories"""
if not cats:
cats = self.get_cats()
if not cats:
return []
threadPool = ThreadPool(len(cats) if len(cats) <= 5 else 5)
for cat in cats:
threadPool.run(self.cat_top_keywords_thread, callback=None, cat=cat, parent=parent, up=up)
cats = threadPool.killAllWorkers(None)
return cats
def get_cats_thread(self, cat):
print cat['id']
subcats = self.get_sub_cats('http://top.taobao.com/level2.php?cat=%s'%cat['id'], 'cat', 2)
if len(subcats) == 1:
cat['children'] = self.get_sub_cats_thread(subcats[0])
return cat
threadPool = ThreadPool(len(subcats) if len(subcats)<=5 else 5)
for sc in subcats:
threadPool.run(self.get_sub_cats_thread, callback=None, sc=sc)
cat['children'] = threadPool.killAllWorkers(None)
return cat
def cat_top_keywords(self, cat, level3="", up=True, offset=0, offsets=[]):
"""Get top keywords in a specific category"""
# print 'CAT:%s, level:%s'%(str(cat), str(level3))
# print 'OFFSET: %d'%offset
response = []
if not offsets or offset == 0:
url = "http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d" % (
str(cat),
str(level3),
"true" if up else "",
offset,
)
rs = self.fetch(url)
if not rs:
return response
soup = BeautifulSoup(rs.content)
response = self.parse_cat_top_keywords(soup, offset)
if offset == 0:
offsets = self.get_cat_top_keywords_pages(soup, offset)
# print 'OFFSETS: %s'%offsets
if offsets:
rs = []
threadPool = ThreadPool(len(offsets) if len(offsets) <= 5 else 5)
for idx, page_offset in enumerate(offsets):
page_url = "http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d" % (
str(cat),
str(level3),
"true" if up else "",
page_offset,
)
next_page = "True" if idx == (len(offsets) - 1) else "False"
threadPool.run(
self.fetch, callback=None, url=page_url, config=dict(get_next=next_page, offset=page_offset)
)
pages = threadPool.killAllWorkers(None)
# print 'RESPONSES: %s'%pages
for p in pages:
if not p:
continue
soup2 = BeautifulSoup(p.content)
offset2 = int(p.config["offset"])
response += self.parse_cat_top_keywords(soup2, offset2)
# print 'GOT: %d'%offset2
if p.config["get_next"] != "True":
continue
offsets = self.get_cat_top_keywords_pages(soup2, offset2)
# print offsets
if not offsets:
continue
response += self.cat_top_keywords(cat, level3, up, offset2, offsets)
# return sorted(response, key=itemgetter('pos')) if response else []
# print "RETURN:%d"%offset
return response
def get_cats(self):
'''Get top keywords categories'''
start_url = 'http://top.taobao.com/index.php?from=tbsy'
rs = self.fetch(start_url)
if not rs: return None
soup = BeautifulSoup(rs.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage)
cats = [{'id':'TR_%s'%li['id'].encode('utf-8').upper(), 'title':li.a.text.encode('utf-8').strip()} for li in soup.find('div', id='nav').findAll('li') if li['id']!='index']
threadPool = ThreadPool(len(cats) if len(cats)<=5 else 5)
for cat in cats:
threadPool.run(self.get_cats_thread, callback=None, cat=cat)
cats = threadPool.killAllWorkers(None)
return cats
def get_top_keywords(self, cats=None, parent=None, up=True):
'''Get top keywords for all the categories'''
if not cats: cats = self.get_cats()
if not cats: return []
threadPool = ThreadPool(len(cats) if len(cats) <= 5 else 5)
for cat in cats:
threadPool.run(self.cat_top_keywords_thread,
callback=None,
cat=cat,
parent=parent,
up=up)
cats = threadPool.killAllWorkers(None)
return cats
def cat_top_keywords(self, session, cat, up=True, offset=0, offsets=[]):
'''Get top keywords in a specific category'''
print 'CAT:%s, level:%s'%(str(cat), str(cat.level))
print 'OFFSET: %d'%offset
response = []
if not offsets or offset==0:
url = 'http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d'%(cat.parent.cid, '' if cat.level==2 else str(cat.cid), 'true' if up else '', offset)
print url
rs = self.fetch(url)
if not rs: return response
soup = BeautifulSoup(rs.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage)
response = self.parse_cat_top_keywords(soup, offset)
if offset==0:
offsets = self.get_cat_top_keywords_pages(soup, offset)
print 'OFFSETS: %s'%offsets
if offsets:
rs = []
threadPool = ThreadPool(len(offsets) if len(offsets)<=5 else 5)
for idx, page_offset in enumerate(offsets):
page_url = 'http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d'%(cat.parent.cid, '' if cat.level==2 else str(cat.cid), 'true' if up else '', page_offset)
next_page = 'True' if idx == (len(offsets)-1) else 'False'
threadPool.run(self.fetch, callback=None, url=page_url, config=dict(get_next=next_page, offset=page_offset))
pages = threadPool.killAllWorkers(None)
#print 'RESPONSES: %s'%pages
for p in pages:
if not p: continue
soup2 = BeautifulSoup(p.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage)
offset2 = int(p.config['offset'])
response += self.parse_cat_top_keywords(soup2, offset2)
print 'GOT: %d'%offset2
if p.config['get_next'] != 'True': continue
offsets = self.get_cat_top_keywords_pages(soup2, offset2)
print offsets
if not offsets: continue
response += self.cat_top_keywords(session, cat, up, offset2, offsets)
#return sorted(response, key=itemgetter('pos')) if response else []
#print "RETURN:%d"%offset
for k in response:
new_keyword = models.Keyword(k['name'].decode('utf-8'))
new_keyword.categories.append(cat)
session.add(new_keyword)
try:
session.commit()
except IntegrityError:
session.rollback()
new_keyword = session.query(models.Keyword).filter(models.Keyword.name == k['name']).first()
new_keyword.categories.append(cat)
session.commit()
print 'Duplicate %s'%new_keyword
return response
def get_cats(self):
"""Get top keywords categories"""
start_url = "http://top.taobao.com/index.php?from=tbsy"
rs = self.fetch(start_url)
if not rs:
return None
soup = BeautifulSoup(rs.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage)
cats = [
{"id": "TR_%s" % li["id"].encode("utf-8").upper(), "title": li.a.text.encode("utf-8").strip()}
for li in soup.find("div", id="nav").findAll("li")
if li["id"] != "index"
]
threadPool = ThreadPool(len(cats) if len(cats) <= 5 else 5)
for cat in cats:
threadPool.run(self.get_cats_thread, callback=None, cat=cat)
cats = threadPool.killAllWorkers(None)
return cats
def print_table_with_ipa_de(self):
"""TODO decribe what this method does."""
thread_pool = ThreadPool(self.__print_row_with_ipa)
rows = self._parse_src()
self.print_header_row(rows[0].get_column_format() if len(rows) > 0 else self._column_format.split('|'))
for row in rows:
if len(row) < 1:
print('Skip incomplete row')
else:
p = Processable(lambda word: Wordanalyzer.get_ipa_de(word), row[0], row)
p.start()
thread_pool.add(p)
#end if
#end for
thread_pool.finish()
def print_enhanced_table_en(self):
"""TODO decribe what this method does."""
thread_pool = ThreadPool(self.__print_enhanced_row_en)
rows = self._parse_src()
self.print_header_row(rows[0].get_column_format() if len(rows) > 0 else self._column_format.split('|'))
for row in rows:
if len(row) < 2:
print('Skip incomplete row')
else:
p = Processable(lambda word: Wordanalyzer.get_translation_en(word), row.original_word, row)
p.start()
thread_pool.add(p)
#end if
#end for
thread_pool.finish()
def cat_top_keywords(self, cat, level3='', up=True, offset=0, offsets=[]):
'''Get top keywords in a specific category'''
#print 'CAT:%s, level:%s'%(str(cat), str(level3))
#print 'OFFSET: %d'%offset
response = []
if not offsets or offset == 0:
url = 'http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d' % (
str(cat), str(level3), 'true' if up else '', offset)
rs = self.fetch(url)
if not rs: return response
soup = BeautifulSoup(rs.content)
response = self.parse_cat_top_keywords(soup, offset)
if offset == 0:
offsets = self.get_cat_top_keywords_pages(soup, offset)
#print 'OFFSETS: %s'%offsets
if offsets:
rs = []
threadPool = ThreadPool(len(offsets) if len(offsets) <= 5 else 5)
for idx, page_offset in enumerate(offsets):
page_url = 'http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d' % (
str(cat), str(level3), 'true' if up else '', page_offset)
next_page = 'True' if idx == (len(offsets) - 1) else 'False'
threadPool.run(self.fetch,
callback=None,
url=page_url,
config=dict(get_next=next_page,
offset=page_offset))
pages = threadPool.killAllWorkers(None)
#print 'RESPONSES: %s'%pages
for p in pages:
if not p: continue
soup2 = BeautifulSoup(p.content)
offset2 = int(p.config['offset'])
response += self.parse_cat_top_keywords(soup2, offset2)
#print 'GOT: %d'%offset2
if p.config['get_next'] != 'True': continue
offsets = self.get_cat_top_keywords_pages(soup2, offset2)
#print offsets
if not offsets: continue
response += self.cat_top_keywords(cat, level3, up, offset2,
offsets)
#return sorted(response, key=itemgetter('pos')) if response else []
#print "RETURN:%d"%offset
return response
def print_conjugation_table(self, tenses):
"""TODO decribe what this method does.
Keyword arguments:
tenses -- TODO describe what this argument is about
"""
thread_pool = ThreadPool(self.__print_conjugation_table)
rows = self._parse_src()
self.print_csv_row(['[Infinitive]', '[yo]', '[tú]', '[el/ella/usted]', '[nosotros, -as]', '[vosotros, -as]', '[ellos/ellas/ustedes]', '[Tense]']) # print header
for row in rows:
if len(row) < 1:
print('Skip incomplete row')
else:
for tense in tenses:
p = Processable(lambda word: Wordanalyzer.get_conjugation_es(word, tense), row.original_word, row)
p.start()
thread_pool.add(p)
#end for
#end if
#end for
thread_pool.finish()
def saveEn(self, notebook, title, html):
#clear html
root = lxml.html.fromstring(html)
# delete unnecessary tag
for tag in self.remove_tags:
for node in root.xpath('//' + tag):
node.drop_tree()
#replace with div
for tag in self.replace_with_div_tags:
for node in root.xpath('//' + tag):
node.tag = "div"
#remove unnecessary attribute
for node in root.iter():
for att in node.attrib.keys():
if att not in self.allow_attributes:
del node.attrib[att]
#remove javascirpt in href
if att == "href":
url = node.attrib[att]
urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', url)
if len(urls) == 0:
del node.attrib[att]
img_node = root.xpath('//img')
if len(img_node) > 0:
pool = ThreadPool(THREAD_NUM_WORKERS)
#add task
for img in img_node:
pool.add_task(img)
# Wait for completion
pool.wait_completion()
#get result
resources = pool.get_reuslt()
content = lxml.etree.tostring(root, encoding="UTF-8")
#create notebook
note_store = self.get_note_store()
#get notebook guid
nbGuid = self.get_or_create_notebook(note_store, notebook)
result = self.save_note(title, content, nbGuid, note_store, resources)
return result
def start_ui(test=False):
from PyQt5.QtWidgets import QApplication
import sys
from src.ui.tab_reorder import TabReorder
from src.ui.tab_log import TabLog
from src.ui.tab_config import TabConfig
from src.ui.tab_skins import TabSkins
logger.debug('starting QtApp object')
global_.QT_APP = QApplication([])
global_.MAIN_UI = MainUi()
global_.MAIN_UI.add_tab(TabLog(), helpers={'write_log': 'write'})
global_.MAIN_UI.add_tab(TabReorder(),
helpers={
'tab_reorder_update_view_after_remote_scan':
'tab_reorder_update_view_after_remote_scan'
})
from src.misc import dcs_installs
dcs_installs.discover_dcs_installations()
global_.MAIN_UI.add_tab(TabSkins(), helpers={})
global_.MAIN_UI.add_tab(TabConfig(),
helpers={'update_config_tab': 'update_config_tab'})
global_.MAIN_UI.show()
def pre_update_hook():
if not hasattr(sys, 'frozen'):
logger.warning('skipping update on script run')
return False
else:
I.hide()
return True
def cancel_update_hook():
I.show()
from utils import Progress
# noinspection PyTypeChecker
Progress.register_adapter(I)
from src.updater import updater
updater.find_and_install_latest_release(
current_version=global_.APP_VERSION,
executable_path='emft.exe',
channel=Config().update_channel,
cancel_update_hook=cancel_update_hook,
pre_update_hook=pre_update_hook,
)
global_.MAIN_UI.update_config_tab()
if test:
logger.critical('RUNNING IN TEST MODE')
import time
from utils import ThreadPool, nice_exit
def test_hook():
time.sleep(10)
nice_exit()
pool = ThreadPool(1, 'test')
pool.queue_task(test_hook)
sys.exit(global_.QT_APP.exec())
def cat_top_keywords(self, session, cat, up=True, offset=0, offsets=[]):
"""Get top keywords in a specific category"""
print "CAT:%s, level:%s" % (str(cat), str(cat.level))
print "OFFSET: %d" % offset
response = []
if not offsets or offset == 0:
url = "http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d" % (
cat.parent.cid,
"" if cat.level == 2 else str(cat.cid),
"true" if up else "",
offset,
)
print url
rs = self.fetch(url)
if not rs:
return response
soup = BeautifulSoup(
rs.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage
)
response = self.parse_cat_top_keywords(soup, offset)
if offset == 0:
offsets = self.get_cat_top_keywords_pages(soup, offset)
print "OFFSETS: %s" % offsets
if offsets:
rs = []
threadPool = ThreadPool(len(offsets) if len(offsets) <= 5 else 5)
for idx, page_offset in enumerate(offsets):
page_url = "http://top.taobao.com/level3.php?cat=%s&level3=%s&show=focus&up=%s&offset=%d" % (
cat.parent.cid,
"" if cat.level == 2 else str(cat.cid),
"true" if up else "",
page_offset,
)
next_page = "True" if idx == (len(offsets) - 1) else "False"
threadPool.run(
self.fetch, callback=None, url=page_url, config=dict(get_next=next_page, offset=page_offset)
)
pages = threadPool.killAllWorkers(None)
# print 'RESPONSES: %s'%pages
for p in pages:
if not p:
continue
soup2 = BeautifulSoup(
p.content, convertEntities=BeautifulSoup.HTML_ENTITIES, markupMassage=hexentityMassage
)
offset2 = int(p.config["offset"])
response += self.parse_cat_top_keywords(soup2, offset2)
print "GOT: %d" % offset2
if p.config["get_next"] != "True":
continue
offsets = self.get_cat_top_keywords_pages(soup2, offset2)
print offsets
if not offsets:
continue
response += self.cat_top_keywords(session, cat, up, offset2, offsets)
# return sorted(response, key=itemgetter('pos')) if response else []
# print "RETURN:%d"%offset
for k in response:
new_keyword = models.Keyword(k["name"].decode("utf-8"))
new_keyword.categories.append(cat)
session.add(new_keyword)
try:
session.commit()
except IntegrityError:
session.rollback()
new_keyword = session.query(models.Keyword).filter(models.Keyword.name == k["name"]).first()
new_keyword.categories.append(cat)
session.commit()
print "Duplicate %s" % new_keyword
return response