def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
self.timeStr = '00:00'
val = j[0]
if val is not None:
if isinstance(val, str):
self.dtStr = val
elif isinstance(val, list):
self.dtStr = val[0]
m = re.search(r'(\d{1,2}:\d{2})', self.dtStr)
if m is not None:
self.timeStr = m.group(0)
if len(self.timeStr) == 4:
self.timeStr = '0'+self.timeStr
self.title = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
if len(self.title) > 1000:
self.title = self.title[:self.title.find('\n')] # get first line in long title
self.summary = ''
val = j[2]
if val is not None:
if isinstance(val, str):
self.summary = val.strip()
elif isinstance(val, list):
self.summary = val[0].strip()
self.author = ''
self.body = list()
val = j[3]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
if len(self.summary) > 0 and len(locText) > 0:
locText = locText.replace(self.summary,'',1).strip() # remove summary from the body, trim
text = locText.strip() # trim
if len(self.author) > 0:
text = text.replace(self.author,'')
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
def __init__(self, url, j):
super().__init__()
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
self.timeStr = '00:00'
val = j[0]
if val is not None:
if isinstance(val, str):
self.dtStr = val
elif isinstance(val, list):
self.dtStr = val[0]
self.title = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
if len(self.title) > 1000:
self.title = self.title[:self.title.find('\n')] # get first line in long title
self.source = ''
val = j[2]
if val is not None:
if isinstance(val, str):
self.source = val.strip()
elif isinstance(val, list):
self.source = val[0].strip()
self.author = ''
self.body = list()
val = j[3]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
#remove empty lines
for line in locText.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.coltype = ''
val = j[4]
if val is not None:
locText = ''
if isinstance(val, str):
self.coltype = val
elif isinstance(val, list):
self.coltype = val[0].strip()
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = None
if len(j) > 0:
val = j[0]
if val is not None:
self.dtStr = val
if len(self.dtStr) > 4:
matchObj = re.search(r'\d{2}:\d{2}', self.dtStr)
if matchObj:
self.timeStr = matchObj.group()
else:
self.timeStr = '00:00'
else:
self.timeStr = '00:00'
self.title = ''
val = None
if len(j) > 1:
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(
' '.join(val))
self.summary = ''
self.body = list()
val = None
if len(j) > 2:
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip() # trim
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.author = ''
if len(j) > 3:
val = j[3]
if val is not None:
self.author = val.strip()
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = None
if len(j) > 0:
val = j[0]
if val is not None:
if isinstance(val, str):
self.dtStr = val
elif isinstance(val, list):
self.dtStr = val[0]
if len(self.dtStr) > 4:
self.timeStr = self.dtStr[-5:] # extract time (last five char)
else:
self.timeStr = '00:00'
self.title = ''
val = None
if len(j) > 1:
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(
' '.join(val))
self.summary = ''
self.body = list()
val = None
if len(j) > 2:
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = val[0]
text = locText.strip() # trim
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.author = ''
if len(j) > 3:
val = j[3]
if val is not None:
self.author = val.strip()
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = j[0]
if val is not None:
self.dtStr = val
if len(self.dtStr) > 4:
self.timeStr = self.dtStr[-5:] # extract time (last five char)
else:
self.timeStr = '00:00'
self.title = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
self.summary = ''
self.body = list()
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = val[0]
text = locText.strip() # trim
# remove html comments
text = re.subn("(<!--.*?-->)",
"",
text,
flags=re.MULTILINE | re.DOTALL)[0]
if 'Версія для друку' in text:
text = text[:text.find('Версія для друку')]
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.author = ''
if len(j) > 3:
val = j[3]
if val is not None:
self.author = val.strip()
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
self.timeStr = '00:00'
self.title = ''
val = j[0]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
if len(self.title) > 1000:
self.title = self.title[:self.title.find(
'\n')] # get first line in long title
self.summary = ''
self.body = list()
cutStr = 'Підписуйтесь на новини "МБ" у соцмережах'
cutStr1 = 'Приєднуйтесь до "МБ" у соцмережах'
cutStr2 = '\nРейтинг:\n'
if len(j) > 1:
val = j[1]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip() # trim
if cutStr in text:
text = text[:text.find(cutStr)]
elif cutStr1 in text:
text = text[:text.find(cutStr1)]
elif cutStr2 in text:
text = text[:text.find(cutStr2)]
# remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(
line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.author = ''
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = j[0]
if val is not None:
self.dtStr = val
self.timeStr = '00:00'
self.title = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
self.summary = ''
self.author = ''
if len(j) > 3:
val = j[3]
if val is not None:
self.author = val.strip()
self.body = list()
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = val[0]
text = locText.strip() # trim
if 'Друкована версія' in text:
text = text[:text.find('Друкована версія')]
if len(self.author) > 0:
text = text.replace(self.author, '')
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
self.timeStr = '00:00'
self.title = ''
val = j[0]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
if len(self.title) > 1000:
self.title = self.title[:self.title.find('\n')] # get first line in long title
self.summary = ''
val = j[1]
if val is not None:
self.summary = val.strip()
self.body = list()
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip() # trim
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
self.author = ''
val = j[3]
if val is not None:
if isinstance(val, str) and len(str(val).strip())>0:
self.author = str(val).strip()
if (self.author.endswith(",")):
self.author = self.author[:len(self.author)-1]
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = j[0]
if val is not None:
self.dtStr = val
self.author = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.author = val
elif isinstance(val, list):
self.author = ', '.join(val)
self.title = ''
val = j[2]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
self.summary = ''
self.body = list()
val = j[3]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip()
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0:
self.body.append(proLine)
def storeUrlToFile(self, url):
# store file locally and do encoding convertion (xidel can't mange it correctly)
f = urllib.request.urlopen(url)
myfile = f.read()
content = myfile.decode('windows-1251').replace(
'windows-1251', 'utf-8')
content = downloader_common.relpaceHtmlEntities(content)
fileName = '/tmp/' + url.replace('https://', '').replace('/',
'_') + '.html'
with open(fileName, "w") as fb2_file:
fb2_file.write(content)
return fileName
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
self.timeStr = '00:00:00'
if j[0] is not None:
if isinstance(j[0], str):
self.dtStr = j[0]
elif isinstance(j[0], list):
s = str(j[0][0])
self.dtStr = s[s.find(',') + 1:].strip() + ', ' + j[0][1]
self.timeStr = str(j[0][1]).strip()
self.title = ''
if j[1] is not None:
if isinstance(j[1], str):
self.title = downloader_common.relpaceHtmlEntities(j[1])
elif isinstance(j[1], list):
self.title = downloader_common.relpaceHtmlEntities(j[1][0])
self.body = list()
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip() # trim
#remove empty lines
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0 and 'ЧИТАЙТЕ ТАКОЖ:' not in proLine:
self.body.append(proLine)
def __init__(self, url, j):
super().__init__()
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
val = j[0]
if val is not None:
self.dtStr = val
self.timeStr = '00:00'
self.title = ''
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(val[0])
self.body = list()
val = j[2]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
locText = '\n'.join(val)
text = locText.strip() # trim
#remove HTML comments
text = re.sub("(<!--.*?-->)", "", text, flags=re.MULTILINE|re.DOTALL)
#remove empty lines and "Читайте також:"
for line in text.split('\n'):
proLine = downloader_common.relpaceHtmlEntities(line.strip())
if len(proLine) > 0 and not proLine.startswith('Читайте також:'):
if (proLine.startswith('Відповідно до угоди, статті the Economist')):
self.body.append('content deleted')
else:
self.body.append(proLine)
self.summary = ''
if len(j) > 3:
val = j[3]
if val is not None:
self.summary = val.strip()
self.author = ''
if len(j) > 4:
val = j[4]
if val is not None:
if isinstance(val, list):
val = '; '.join(val)
if 'Версія для друку' not in val:
self.author = val.strip()
if len(j) > 5 and len(self.author) < 1:
val = j[5]
if val is not None:
if isinstance(val, list):
val = '; '.join(val)
self.author = val.strip()
def __init__(self, url, j):
self.url = ''
if url is not None:
self.url = url
self.dtStr = ''
if j[0] is not None:
self.dtStr = j[0]
if len(self.dtStr) > 4:
self.timeStr = self.dtStr[-5:] # extract time (last five char)
else:
self.timeStr = '00:00'
self.title = ''
val = None
if len(j) > 1:
val = j[1]
if val is not None:
if isinstance(val, str):
self.title = downloader_common.relpaceHtmlEntities(val)
elif isinstance(val, list):
self.title = downloader_common.relpaceHtmlEntities(
' '.join(val))
self.summary = ''
val = None
if len(j) > 2:
val = j[2]
if val is not None:
if isinstance(val, str):
self.summary = downloader_common.relpaceHtmlEntities(
val).strip()
elif isinstance(val, list):
self.summary = downloader_common.relpaceHtmlEntities(
' '.join(val)).strip()
self.body = list()
val = None
if len(j) > 3:
val = j[3]
if val is not None:
locText = ''
if isinstance(val, str):
locText = val
elif isinstance(val, list):
for line in val:
if 'За матеріалами:' in line:
line = line.replace('\n', '')
line = ' '.join(
line.split()
) #substitute multiple whitespace with single whitespace
line = '@@@ ' + line
locText = locText + '\n' + line
if len(self.summary) > 0 and len(locText) > 0:
text = locText.replace(
self.summary, '',
1).strip() # remove summary from the body, trim
else:
#no summary
text = locText.strip() # trim
#remove empty lines
for line in text.split('\n'):
proLine = line.strip()
if 'Читайте також:' in proLine:
break
if len(proLine) > 0:
self.body.append(
downloader_common.relpaceHtmlEntities(proLine))
