update

crawler_sys/site_crawler_test/crawler_weibo.py

@@ -27,7 +27,7 @@ from crawler.crawler_sys.utils import connect_with_redis
 from crawler.crawler_sys.utils.trans_duration_str_to_second import trans_duration
 from crawler.crawler_sys.utils.util_logging import logged
 from crawler.crawler_sys.proxy_pool.func_get_proxy_form_kuaidaili import get_proxy
-
+from crawler.crawler_sys.utils.html_to_str import dehtml
 
 from write_data_into_es.func_get_releaser_id import *
 
@@ -70,7 +70,7 @@ class Crawler_weibo():
         page_res = retry_get_url(url,headers=headers,proxies=0)
         page_json_context = re.findall(r"render_data = (.*)\[0\]", page_res.text,flags=re.DOTALL)[0]
         page_json = json.loads(page_json_context)
-        text = page_json[0]["status"]["text"]
+        text = dehtml(page_json[0]["status"]["text"])
         repost_count = trans_play_count(page_json[0]["status"]["reposts_count"])
         comment_count = trans_play_count(page_json[0]["status"]["comments_count"])
         favorite_count = trans_play_count(page_json[0]["status"]["attitudes_count"])
@@ -204,7 +204,7 @@ class Crawler_weibo():
 
 if __name__ == '__main__':
     test = Crawler_weibo()
-    url = 'https://weibo.com/p/1003061669879400/home?from=page_100306&mod=TAB#place'
+    url = 'https://weibo.com/p/1644114654/home?from=page_100306&mod=TAB#place'
     # releaserUrl = 'http://v.qq.com/vplus/cfa34d96d1b6609f1dccdea65b26b83d'
     # nnn = test.video_page(url)
     # kw = '任正非 BBC'

crawler_sys/utils/HTMLParser.py

+"""A parser for HTML and XHTML."""
+
+# This file is based on sgmllib.py, but the API is slightly different.
+
+# XXX There should be a way to distinguish between PCDATA (parsed
+# character data -- the normal case), RCDATA (replaceable character
+# data -- only char and entity references and end tags are special)
+# and CDATA (character data -- only end tags are special).
+
+
+import _markupbase as markupbase
+import re
+
+# Regular expressions used for parsing
+
+interesting_normal = re.compile('[&<]')
+incomplete = re.compile('&[a-zA-Z#]')
+
+entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
+charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
+
+starttagopen = re.compile('<[a-zA-Z]')
+piclose = re.compile('>')
+commentclose = re.compile(r'--\s*>')
+tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
+# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
+# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
+tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
+
+attrfind = re.compile(
+    r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
+
+locatestarttagend = re.compile(r"""
+  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
+  (?:[\s/]*                          # optional whitespace before attribute name
+    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
+      (?:\s*=+\s*                    # value indicator
+        (?:'[^']*'                   # LITA-enclosed value
+          |"[^"]*"                   # LIT-enclosed value
+          |(?!['"])[^>\s]*           # bare value
+         )
+       )?(?:\s|/(?!>))*
+     )*
+   )?
+  \s*                                # trailing whitespace
+""", re.VERBOSE)
+endendtag = re.compile('>')
+# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
+# </ and the tag name, so maybe this should be fixed
+endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
+
+
+class HTMLParseError(Exception):
+    """Exception raised for all parse errors."""
+
+    def __init__(self, msg, position=(None, None)):
+        assert msg
+        self.msg = msg
+        self.lineno = position[0]
+        self.offset = position[1]
+
+    def __str__(self):
+        result = self.msg
+        if self.lineno is not None:
+            result = result + ", at line %d" % self.lineno
+        if self.offset is not None:
+            result = result + ", column %d" % (self.offset + 1)
+        return result
+
+
+class HTMLParser(markupbase.ParserBase):
+    """Find tags and other markup and call handler functions.
+
+    Usage:
+        p = HTMLParser()
+        p.feed(data)
+        ...
+        p.close()
+
+    Start tags are handled by calling self.handle_starttag() or
+    self.handle_startendtag(); end tags by self.handle_endtag().  The
+    data between tags is passed from the parser to the derived class
+    by calling self.handle_data() with the data as argument (the data
+    may be split up in arbitrary chunks).  Entity references are
+    passed by calling self.handle_entityref() with the entity
+    reference as the argument.  Numeric character references are
+    passed to self.handle_charref() with the string containing the
+    reference as the argument.
+    """
+
+    CDATA_CONTENT_ELEMENTS = ("script", "style")
+
+
+    def __init__(self):
+        """Initialize and reset this instance."""
+        self.reset()
+
+    def reset(self):
+        """Reset this instance.  Loses all unprocessed data."""
+        self.rawdata = ''
+        self.lasttag = '???'
+        self.interesting = interesting_normal
+        self.cdata_elem = None
+        markupbase.ParserBase.reset(self)
+
+    def feed(self, data):
+        r"""Feed data to the parser.
+
+        Call this as often as you want, with as little or as much text
+        as you want (may include '\n').
+        """
+        self.rawdata = self.rawdata + data
+        self.goahead(0)
+
+    def close(self):
+        """Handle any buffered data."""
+        self.goahead(1)
+
+    def error(self, message):
+        raise HTMLParseError(message, self.getpos())
+
+    __starttag_text = None
+
+    def get_starttag_text(self):
+        """Return full source of start tag: '<...>'."""
+        return self.__starttag_text
+
+    def set_cdata_mode(self, elem):
+        self.cdata_elem = elem.lower()
+        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
+
+    def clear_cdata_mode(self):
+        self.interesting = interesting_normal
+        self.cdata_elem = None
+
+    # Internal -- handle data as far as reasonable.  May leave state
+    # and data to be processed by a subsequent call.  If 'end' is
+    # true, force handling all data as if followed by EOF marker.
+    def goahead(self, end):
+        rawdata = self.rawdata
+        i = 0
+        n = len(rawdata)
+        while i < n:
+            match = self.interesting.search(rawdata, i) # < or &
+            if match:
+                j = match.start()
+            else:
+                if self.cdata_elem:
+                    break
+                j = n
+            if i < j: self.handle_data(rawdata[i:j])
+            i = self.updatepos(i, j)
+            if i == n: break
+            startswith = rawdata.startswith
+            if startswith('<', i):
+                if starttagopen.match(rawdata, i): # < + letter
+                    k = self.parse_starttag(i)
+                elif startswith("</", i):
+                    k = self.parse_endtag(i)
+                elif startswith("<!--", i):
+                    k = self.parse_comment(i)
+                elif startswith("<?", i):
+                    k = self.parse_pi(i)
+                elif startswith("<!", i):
+                    k = self.parse_html_declaration(i)
+                elif (i + 1) < n:
+                    self.handle_data("<")
+                    k = i + 1
+                else:
+                    break
+                if k < 0:
+                    if not end:
+                        break
+                    k = rawdata.find('>', i + 1)
+                    if k < 0:
+                        k = rawdata.find('<', i + 1)
+                        if k < 0:
+                            k = i + 1
+                    else:
+                        k += 1
+                    self.handle_data(rawdata[i:k])
+                i = self.updatepos(i, k)
+            elif startswith("&#", i):
+                match = charref.match(rawdata, i)
+                if match:
+                    name = match.group()[2:-1]
+                    self.handle_charref(name)
+                    k = match.end()
+                    if not startswith(';', k-1):
+                        k = k - 1
+                    i = self.updatepos(i, k)
+                    continue
+                else:
+                    if ";" in rawdata[i:]: #bail by consuming &#
+                        self.handle_data(rawdata[0:2])
+                        i = self.updatepos(i, 2)
+                    break
+            elif startswith('&', i):
+                match = entityref.match(rawdata, i)
+                if match:
+                    name = match.group(1)
+                    self.handle_entityref(name)
+                    k = match.end()
+                    if not startswith(';', k-1):
+                        k = k - 1
+                    i = self.updatepos(i, k)
+                    continue
+                match = incomplete.match(rawdata, i)
+                if match:
+                    # match.group() will contain at least 2 chars
+                    if end and match.group() == rawdata[i:]:
+                        self.error("EOF in middle of entity or char ref")
+                    # incomplete
+                    break
+                elif (i + 1) < n:
+                    # not the end of the buffer, and can't be confused
+                    # with some other construct
+                    self.handle_data("&")
+                    i = self.updatepos(i, i + 1)
+                else:
+                    break
+            else:
+                assert 0, "interesting.search() lied"
+        # end while
+        if end and i < n and not self.cdata_elem:
+            self.handle_data(rawdata[i:n])
+            i = self.updatepos(i, n)
+        self.rawdata = rawdata[i:]
+
+    # Internal -- parse html declarations, return length or -1 if not terminated
+    # See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
+    # See also parse_declaration in _markupbase
+    def parse_html_declaration(self, i):
+        rawdata = self.rawdata
+        if rawdata[i:i+2] != '<!':
+            self.error('unexpected call to parse_html_declaration()')
+        if rawdata[i:i+4] == '<!--':
+            # this case is actually already handled in goahead()
+            return self.parse_comment(i)
+        elif rawdata[i:i+3] == '<![':
+            return self.parse_marked_section(i)
+        elif rawdata[i:i+9].lower() == '<!doctype':
+            # find the closing >
+            gtpos = rawdata.find('>', i+9)
+            if gtpos == -1:
+                return -1
+            self.handle_decl(rawdata[i+2:gtpos])
+            return gtpos+1
+        else:
+            return self.parse_bogus_comment(i)
+
+    # Internal -- parse bogus comment, return length or -1 if not terminated
+    # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
+    def parse_bogus_comment(self, i, report=1):
+        rawdata = self.rawdata
+        if rawdata[i:i+2] not in ('<!', '</'):
+            self.error('unexpected call to parse_comment()')
+        pos = rawdata.find('>', i+2)
+        if pos == -1:
+            return -1
+        if report:
+            self.handle_comment(rawdata[i+2:pos])
+        return pos + 1
+
+    # Internal -- parse processing instr, return end or -1 if not terminated
+    def parse_pi(self, i):
+        rawdata = self.rawdata
+        assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
+        match = piclose.search(rawdata, i+2) # >
+        if not match:
+            return -1
+        j = match.start()
+        self.handle_pi(rawdata[i+2: j])
+        j = match.end()
+        return j
+
+    # Internal -- handle starttag, return end or -1 if not terminated
+    def parse_starttag(self, i):
+        self.__starttag_text = None
+        endpos = self.check_for_whole_start_tag(i)
+        if endpos < 0:
+            return endpos
+        rawdata = self.rawdata
+        self.__starttag_text = rawdata[i:endpos]
+
+        # Now parse the data between i+1 and j into a tag and attrs
+        attrs = []
+        match = tagfind.match(rawdata, i+1)
+        assert match, 'unexpected call to parse_starttag()'
+        k = match.end()
+        self.lasttag = tag = rawdata[i+1:k].lower()
+
+        while k < endpos:
+            m = attrfind.match(rawdata, k)
+            if not m:
+                break
+            attrname, rest, attrvalue = m.group(1, 2, 3)
+            if not rest:
+                attrvalue = None
+            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
+                 attrvalue[:1] == '"' == attrvalue[-1:]:
+                attrvalue = attrvalue[1:-1]
+            if attrvalue:
+                attrvalue = self.unescape(attrvalue)
+            attrs.append((attrname.lower(), attrvalue))
+            k = m.end()
+
+        end = rawdata[k:endpos].strip()
+        if end not in (">", "/>"):
+            lineno, offset = self.getpos()
+            if "\n" in self.__starttag_text:
+                lineno = lineno + self.__starttag_text.count("\n")
+                offset = len(self.__starttag_text) \
+                         - self.__starttag_text.rfind("\n")
+            else:
+                offset = offset + len(self.__starttag_text)
+            self.handle_data(rawdata[i:endpos])
+            return endpos
+        if end.endswith('/>'):
+            # XHTML-style empty tag: <span attr="value" />
+            self.handle_startendtag(tag, attrs)
+        else:
+            self.handle_starttag(tag, attrs)
+            if tag in self.CDATA_CONTENT_ELEMENTS:
+                self.set_cdata_mode(tag)
+        return endpos
+
+    # Internal -- check to see if we have a complete starttag; return end
+    # or -1 if incomplete.
+    def check_for_whole_start_tag(self, i):
+        rawdata = self.rawdata
+        m = locatestarttagend.match(rawdata, i)
+        if m:
+            j = m.end()
+            next = rawdata[j:j+1]
+            if next == ">":
+                return j + 1
+            if next == "/":
+                if rawdata.startswith("/>", j):
+                    return j + 2
+                if rawdata.startswith("/", j):
+                    # buffer boundary
+                    return -1
+                # else bogus input
+                self.updatepos(i, j + 1)
+                self.error("malformed empty start tag")
+            if next == "":
+                # end of input
+                return -1
+            if next in ("abcdefghijklmnopqrstuvwxyz=/"
+                        "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
+                # end of input in or before attribute value, or we have the
+                # '/' from a '/>' ending
+                return -1
+            if j > i:
+                return j
+            else:
+                return i + 1
+        raise AssertionError("we should not get here!")
+
+    # Internal -- parse endtag, return end or -1 if incomplete
+    def parse_endtag(self, i):
+        rawdata = self.rawdata
+        assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
+        match = endendtag.search(rawdata, i+1) # >
+        if not match:
+            return -1
+        gtpos = match.end()
+        match = endtagfind.match(rawdata, i) # </ + tag + >
+        if not match:
+            if self.cdata_elem is not None:
+                self.handle_data(rawdata[i:gtpos])
+                return gtpos
+            # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
+            namematch = tagfind_tolerant.match(rawdata, i+2)
+            if not namematch:
+                # w3.org/TR/html5/tokenization.html#end-tag-open-state
+                if rawdata[i:i+3] == '</>':
+                    return i+3
+                else:
+                    return self.parse_bogus_comment(i)
+            tagname = namematch.group().lower()
+            # consume and ignore other stuff between the name and the >
+            # Note: this is not 100% correct, since we might have things like
+            # </tag attr=">">, but looking for > after tha name should cover
+            # most of the cases and is much simpler
+            gtpos = rawdata.find('>', namematch.end())
+            self.handle_endtag(tagname)
+            return gtpos+1
+
+        elem = match.group(1).lower() # script or style
+        if self.cdata_elem is not None:
+            if elem != self.cdata_elem:
+                self.handle_data(rawdata[i:gtpos])
+                return gtpos
+
+        self.handle_endtag(elem)
+        self.clear_cdata_mode()
+        return gtpos
+
+    # Overridable -- finish processing of start+end tag: <tag.../>
+    def handle_startendtag(self, tag, attrs):
+        self.handle_starttag(tag, attrs)
+        self.handle_endtag(tag)
+
+    # Overridable -- handle start tag
+    def handle_starttag(self, tag, attrs):
+        pass
+
+    # Overridable -- handle end tag
+    def handle_endtag(self, tag):
+        pass
+
+    # Overridable -- handle character reference
+    def handle_charref(self, name):
+        pass
+
+    # Overridable -- handle entity reference
+    def handle_entityref(self, name):
+        pass
+
+    # Overridable -- handle data
+    def handle_data(self, data):
+        pass
+
+    # Overridable -- handle comment
+    def handle_comment(self, data):
+        pass
+
+    # Overridable -- handle declaration
+    def handle_decl(self, decl):
+        pass
+
+    # Overridable -- handle processing instruction
+    def handle_pi(self, data):
+        pass
+
+    def unknown_decl(self, data):
+        pass
+
+    # Internal -- helper to remove special character quoting
+    entitydefs = None
+    def unescape(self, s):
+        if '&' not in s:
+            return s
+        def replaceEntities(s):
+            s = s.groups()[0]
+            try:
+                if s[0] == "#":
+                    s = s[1:]
+                    if s[0] in ['x','X']:
+                        c = int(s[1:], 16)
+                    else:
+                        c = int(s)
+                    return unichr(c)
+            except ValueError:
+                return '&#'+s+';'
+            else:
+                # Cannot use name2codepoint directly, because HTMLParser supports apos,
+                # which is not part of HTML 4
+                import htmlentitydefs
+                if HTMLParser.entitydefs is None:
+                    entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
+                    for k, v in htmlentitydefs.name2codepoint.iteritems():
+                        entitydefs[k] = unichr(v)
+                try:
+                    return self.entitydefs[s]
+                except KeyError:
+                    return '&'+s+';'
+
+        return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)

crawler_sys/utils/_markupbase.py

+"""Shared support for scanning document type declarations in HTML and XHTML.
+
+This module is used as a foundation for the html.parser module.  It has no
+documented public API and should not be used directly.
+
+"""
+
+import re
+
+_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
+_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
+_commentclose = re.compile(r'--\s*>')
+_markedsectionclose = re.compile(r']\s*]\s*>')
+
+# An analysis of the MS-Word extensions is available at
+# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf
+
+_msmarkedsectionclose = re.compile(r']\s*>')
+
+del re
+
+
+class ParserBase:
+    """Parser base class which provides some common support methods used
+    by the SGML/HTML and XHTML parsers."""
+
+    def __init__(self):
+        if self.__class__ is ParserBase:
+            raise RuntimeError(
+                "_markupbase.ParserBase must be subclassed")
+
+    def error(self, message):
+        raise NotImplementedError(
+            "subclasses of ParserBase must override error()")
+
+    def reset(self):
+        self.lineno = 1
+        self.offset = 0
+
+    def getpos(self):
+        """Return current line number and offset."""
+        return self.lineno, self.offset
+
+    # Internal -- update line number and offset.  This should be
+    # called for each piece of data exactly once, in order -- in other
+    # words the concatenation of all the input strings to this
+    # function should be exactly the entire input.
+    def updatepos(self, i, j):
+        if i >= j:
+            return j
+        rawdata = self.rawdata
+        nlines = rawdata.count("\n", i, j)
+        if nlines:
+            self.lineno = self.lineno + nlines
+            pos = rawdata.rindex("\n", i, j) # Should not fail
+            self.offset = j-(pos+1)
+        else:
+            self.offset = self.offset + j-i
+        return j
+
+    _decl_otherchars = ''
+
+    # Internal -- parse declaration (for use by subclasses).
+    def parse_declaration(self, i):
+        # This is some sort of declaration; in "HTML as
+        # deployed," this should only be the document type
+        # declaration ("<!DOCTYPE html...>").
+        # ISO 8879:1986, however, has more complex
+        # declaration syntax for elements in <!...>, including:
+        # --comment--
+        # [marked section]
+        # name in the following list: ENTITY, DOCTYPE, ELEMENT,
+        # ATTLIST, NOTATION, SHORTREF, USEMAP,
+        # LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
+        rawdata = self.rawdata
+        j = i + 2
+        assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
+        if rawdata[j:j+1] == ">":
+            # the empty comment <!>
+            return j + 1
+        if rawdata[j:j+1] in ("-", ""):
+            # Start of comment followed by buffer boundary,
+            # or just a buffer boundary.
+            return -1
+        # A simple, practical version could look like: ((name|stringlit) S*) + '>'
+        n = len(rawdata)
+        if rawdata[j:j+2] == '--': #comment
+            # Locate --.*-- as the body of the comment
+            return self.parse_comment(i)
+        elif rawdata[j] == '[': #marked section
+            # Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
+            # Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
+            # Note that this is extended by Microsoft Office "Save as Web" function
+            # to include [if...] and [endif].
+            return self.parse_marked_section(i)
+        else: #all other declaration elements
+            decltype, j = self._scan_name(j, i)
+        if j < 0:
+            return j
+        if decltype == "doctype":
+            self._decl_otherchars = ''
+        while j < n:
+            c = rawdata[j]
+            if c == ">":
+                # end of declaration syntax
+                data = rawdata[i+2:j]
+                if decltype == "doctype":
+                    self.handle_decl(data)
+                else:
+                    # According to the HTML5 specs sections "8.2.4.44 Bogus
+                    # comment state" and "8.2.4.45 Markup declaration open
+                    # state", a comment token should be emitted.
+                    # Calling unknown_decl provides more flexibility though.
+                    self.unknown_decl(data)
+                return j + 1
+            if c in "\"'":
+                m = _declstringlit_match(rawdata, j)
+                if not m:
+                    return -1 # incomplete
+                j = m.end()
+            elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
+                name, j = self._scan_name(j, i)
+            elif c in self._decl_otherchars:
+                j = j + 1
+            elif c == "[":
+                # this could be handled in a separate doctype parser
+                if decltype == "doctype":
+                    j = self._parse_doctype_subset(j + 1, i)
+                elif decltype in {"attlist", "linktype", "link", "element"}:
+                    # must tolerate []'d groups in a content model in an element declaration
+                    # also in data attribute specifications of attlist declaration
+                    # also link type declaration subsets in linktype declarations
+                    # also link attribute specification lists in link declarations
+                    self.error("unsupported '[' char in %s declaration" % decltype)
+                else:
+                    self.error("unexpected '[' char in declaration")
+            else:
+                self.error(
+                    "unexpected %r char in declaration" % rawdata[j])
+            if j < 0:
+                return j
+        return -1 # incomplete
+
+    # Internal -- parse a marked section
+    # Override this to handle MS-word extension syntax <![if word]>content<![endif]>
+    def parse_marked_section(self, i, report=1):
+        rawdata= self.rawdata
+        assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
+        sectName, j = self._scan_name( i+3, i )
+        if j < 0:
+            return j
+        if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
+            # look for standard ]]> ending
+            match= _markedsectionclose.search(rawdata, i+3)
+        elif sectName in {"if", "else", "endif"}:
+            # look for MS Office ]> ending
+            match= _msmarkedsectionclose.search(rawdata, i+3)
+        else:
+            self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
+        if not match:
+            return -1
+        if report:
+            j = match.start(0)
+            self.unknown_decl(rawdata[i+3: j])
+        return match.end(0)
+
+    # Internal -- parse comment, return length or -1 if not terminated
+    def parse_comment(self, i, report=1):
+        rawdata = self.rawdata
+        if rawdata[i:i+4] != '<!--':
+            self.error('unexpected call to parse_comment()')
+        match = _commentclose.search(rawdata, i+4)
+        if not match:
+            return -1
+        if report:
+            j = match.start(0)
+            self.handle_comment(rawdata[i+4: j])
+        return match.end(0)
+
+    # Internal -- scan past the internal subset in a <!DOCTYPE declaration,
+    # returning the index just past any whitespace following the trailing ']'.
+    def _parse_doctype_subset(self, i, declstartpos):
+        rawdata = self.rawdata
+        n = len(rawdata)
+        j = i
+        while j < n:
+            c = rawdata[j]
+            if c == "<":
+                s = rawdata[j:j+2]
+                if s == "<":
+                    # end of buffer; incomplete
+                    return -1
+                if s != "<!":
+                    self.updatepos(declstartpos, j + 1)
+                    self.error("unexpected char in internal subset (in %r)" % s)
+                if (j + 2) == n:
+                    # end of buffer; incomplete
+                    return -1
+                if (j + 4) > n:
+                    # end of buffer; incomplete
+                    return -1
+                if rawdata[j:j+4] == "<!--":
+                    j = self.parse_comment(j, report=0)
+                    if j < 0:
+                        return j
+                    continue
+                name, j = self._scan_name(j + 2, declstartpos)
+                if j == -1:
+                    return -1
+                if name not in {"attlist", "element", "entity", "notation"}:
+                    self.updatepos(declstartpos, j + 2)
+                    self.error(
+                        "unknown declaration %r in internal subset" % name)
+                # handle the individual names
+                meth = getattr(self, "_parse_doctype_" + name)
+                j = meth(j, declstartpos)
+                if j < 0:
+                    return j
+            elif c == "%":
+                # parameter entity reference
+                if (j + 1) == n:
+                    # end of buffer; incomplete
+                    return -1
+                s, j = self._scan_name(j + 1, declstartpos)
+                if j < 0:
+                    return j
+                if rawdata[j] == ";":
+                    j = j + 1
+            elif c == "]":
+                j = j + 1
+                while j < n and rawdata[j].isspace():
+                    j = j + 1
+                if j < n:
+                    if rawdata[j] == ">":
+                        return j
+                    self.updatepos(declstartpos, j)
+                    self.error("unexpected char after internal subset")
+                else:
+                    return -1
+            elif c.isspace():
+                j = j + 1
+            else:
+                self.updatepos(declstartpos, j)
+                self.error("unexpected char %r in internal subset" % c)
+        # end of buffer reached
+        return -1
+
+    # Internal -- scan past <!ELEMENT declarations
+    def _parse_doctype_element(self, i, declstartpos):
+        name, j = self._scan_name(i, declstartpos)
+        if j == -1:
+            return -1
+        # style content model; just skip until '>'
+        rawdata = self.rawdata
+        if '>' in rawdata[j:]:
+            return rawdata.find(">", j) + 1
+        return -1
+
+    # Internal -- scan past <!ATTLIST declarations
+    def _parse_doctype_attlist(self, i, declstartpos):
+        rawdata = self.rawdata
+        name, j = self._scan_name(i, declstartpos)
+        c = rawdata[j:j+1]
+        if c == "":
+            return -1
+        if c == ">":
+            return j + 1
+        while 1:
+            # scan a series of attribute descriptions; simplified:
+            #   name type [value] [#constraint]
+            name, j = self._scan_name(j, declstartpos)
+            if j < 0:
+                return j
+            c = rawdata[j:j+1]
+            if c == "":
+                return -1
+            if c == "(":
+                # an enumerated type; look for ')'
+                if ")" in rawdata[j:]:
+                    j = rawdata.find(")", j) + 1
+                else:
+                    return -1
+                while rawdata[j:j+1].isspace():
+                    j = j + 1
+                if not rawdata[j:]:
+                    # end of buffer, incomplete
+                    return -1
+            else:
+                name, j = self._scan_name(j, declstartpos)
+            c = rawdata[j:j+1]
+            if not c:
+                return -1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if m:
+                    j = m.end()
+                else:
+                    return -1
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+            if c == "#":
+                if rawdata[j:] == "#":
+                    # end of buffer
+                    return -1
+                name, j = self._scan_name(j + 1, declstartpos)
+                if j < 0:
+                    return j
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+            if c == '>':
+                # all done
+                return j + 1
+
+    # Internal -- scan past <!NOTATION declarations
+    def _parse_doctype_notation(self, i, declstartpos):
+        name, j = self._scan_name(i, declstartpos)
+        if j < 0:
+            return j
+        rawdata = self.rawdata
+        while 1:
+            c = rawdata[j:j+1]
+            if not c:
+                # end of buffer; incomplete
+                return -1
+            if c == '>':
+                return j + 1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if not m:
+                    return -1
+                j = m.end()
+            else:
+                name, j = self._scan_name(j, declstartpos)
+                if j < 0:
+                    return j
+
+    # Internal -- scan past <!ENTITY declarations
+    def _parse_doctype_entity(self, i, declstartpos):
+        rawdata = self.rawdata
+        if rawdata[i:i+1] == "%":
+            j = i + 1
+            while 1:
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+                if c.isspace():
+                    j = j + 1
+                else:
+                    break
+        else:
+            j = i
+        name, j = self._scan_name(j, declstartpos)
+        if j < 0:
+            return j
+        while 1:
+            c = self.rawdata[j:j+1]
+            if not c:
+                return -1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if m:
+                    j = m.end()
+                else:
+                    return -1    # incomplete
+            elif c == ">":
+                return j + 1
+            else:
+                name, j = self._scan_name(j, declstartpos)
+                if j < 0:
+                    return j
+
+    # Internal -- scan a name token and the new position and the token, or
+    # return -1 if we've reached the end of the buffer.
+    def _scan_name(self, i, declstartpos):
+        rawdata = self.rawdata
+        n = len(rawdata)
+        if i == n:
+            return None, -1
+        m = _declname_match(rawdata, i)
+        if m:
+            s = m.group()
+            name = s.strip()
+            if (i + len(s)) == n:
+                return None, -1  # end of buffer
+            return name.lower(), m.end()
+        else:
+            self.updatepos(declstartpos, i)
+            self.error("expected name token at %r"
+                       % rawdata[declstartpos:declstartpos+20])
+
+    # To be overridden -- handlers for unknown objects
+    def unknown_decl(self, data):
+        pass

crawler_sys/utils/html_to_str.py

+# -*- coding:UTF-8 -*-
+# @Time  : 2020/7/22 19:53
+# @File  : html_to_str.py
+# @email : litao@igengmei.com
+# @author : litao
+
+from .HTMLParser import HTMLParser
+from re import sub
+from sys import stderr
+from traceback import print_exc
+
+
+class _DeHTMLParser(HTMLParser):
+    def __init__(self):
+        HTMLParser.__init__(self)
+        self.__text = []
+
+    def handle_data(self, data):
+        text = data.strip()
+        if len(text) > 0:
+            text = sub('[ \t\r\n]+', ' ', text)
+            self.__text.append(text + ' ')
+
+    def handle_starttag(self, tag, attrs):
+        if tag == 'p':
+            self.__text.append('\n\n')
+        elif tag == 'br':
+            self.__text.append('\n')
+
+    def handle_startendtag(self, tag, attrs):
+        if tag == 'br':
+            self.__text.append('\n\n')
+
+    def text(self):
+        return ''.join(self.__text).strip()
+
+
+def dehtml(text):
+    try:
+        parser = _DeHTMLParser()
+        parser.feed(text)
+        parser.close()
+        return parser.text()
+    except:
+        print_exc(file=stderr)
+        return text
+

requirements.txt

@@ -5,3 +5,4 @@ absl-py==0.9.0
 dkl=0.2.15
 redis=3.5.3
 elasticsearch=7.8.0
+HTMLParser=0.0.2
\ No newline at end of file