Python encodeValue示例

示例#1

文件： parsers.py 项目： albertian/python-goose

 def fromstring(self, html):
     html = encodeValue(html)
     try:
         self.doc = lxml.html.fromstring(html)
     except:
         html = html.encode('utf-8','replace')
         self.doc = lxml.html.fromstring(html)
     return self.doc

示例#2

文件： parsers.py 项目： muggot/python-goose

 def fromstring(self, html):
     html = encodeValue(html)
     try:
         self.doc = lxml.html.fromstring(html)
     except:
         html = html.encode("ascii", "replace")
         self.doc = lxml.html.fromstring(html)
     return self.doc

示例#3

文件： parsers.py 项目： chyt/gisty-goose

 def fromstring(self, html):
     encoding = get_encodings_from_content(html)
     encoding = encoding and encoding[0] or None
     if not encoding:
         html = encodeValue(html)
         self.doc = lxml.html.fromstring(html)
     else:
         html = smart_str(html, encoding=encoding)
         parser = lxml.html.HTMLParser(encoding=encoding)
         self.doc = lxml.html.fromstring(html, parser=parser)
     return self.doc

示例#4

 def fromstring(self, html):
     encoding = get_encodings_from_content(html)
     encoding = encoding and encoding[0] or None
     if not encoding:
         html = encodeValue(html)
         self.doc = lxml.html.fromstring(html)
     else:
         html = smart_str(html, encoding=encoding)
         parser = lxml.html.HTMLParser(encoding=encoding)
         self.doc = lxml.html.fromstring(html, parser=parser)
     return self.doc

示例#5

文件： parsers.py 项目： gowthamrang/webnews_extraction

 def fromstring(self, html):
     html = encodeValue(html)
     self.doc = lxml.html.fromstring(html)
     return self.doc

示例#6

文件： parsers.py 项目： gowthamrang/webnews_extraction

 def fromstring(self, html):
     html = encodeValue(html)
     self.doc = soupparser.fromstring(html)
     return self.doc

示例#7

文件： parsers.py 项目： toddwilson/python-goose

 def fromstring(self, html):
     html = encodeValue(html)
     self.doc = lxml.html.fromstring(html)
     return self.doc

示例#8

文件： parsers.py 项目： chyt/gisty-goose

 def fromstring(self, html):
     from lxml.html import soupparser
     html = encodeValue(html)
     self.doc = soupparser.fromstring(html)
     return self.doc

示例#9

 def fromstring(self, html):
     from lxml.html import soupparser
     html = encodeValue(html)
     self.doc = soupparser.fromstring(html)
     return self.doc

示例#10

文件： parsers.py 项目： gowthamrang/webnews_extraction

 def fromstring(self, html):
     html = encodeValue(html)
     self.doc = soupparser.fromstring(html)
     return self.doc