sunlightlabs / pressley Goto Github PK

Traceback (most recent call last):
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 73, in handle
    self.scrape_releases(source)
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 47, in scrape_releases
    scrape_release(source, feed, entry, link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 26, in scrape_release
    body = get_link_content(link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 14, in get_link_content
    (title, body) = readability_extract(response.content)
File "/projects/pressley/src/pressley/pressley/util.py", line 25, in readability_extract
    title_text = unicode(lxml.html.fromstring(doc.short_title()).text_content())
File "/projects/pressley/virt/local/lib/python2.7/site-packages/lxml/html/__init__.py", line 634, in fromstring
    doc = document_fromstring(html, parser=parser, base_url=base_url, **kw)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/lxml/html/__init__.py", line 532, in document_fromstring
    value = etree.fromstring(html, parser, **kw)
File "lxml.etree.pyx", line 2753, in lxml.etree.fromstring (src/lxml/lxml.etree.c:54647)
File "parser.pxi", line 1578, in lxml.etree._parseMemoryDocument (src/lxml/lxml.etree.c:82764)
File "parser.pxi", line 1457, in lxml.etree._parseDoc (src/lxml/lxml.etree.c:81562)
File "parser.pxi", line 965, in lxml.etree._BaseParser._parseDoc (src/lxml/lxml.etree.c:78232)
File "parser.pxi", line 569, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/lxml.etree.c:74488)
File "parser.pxi", line 650, in lxml.etree._handleParseResult (src/lxml/lxml.etree.c:75379)
File "parser.pxi", line 599, in lxml.etree._raiseParseError (src/lxml/lxml.etree.c:74843)
XMLSyntaxError: line 1: htmlParseEntityRef: expecting ';'

Traceback (most recent call last):
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 73, in handle
    self.scrape_releases(source)
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 47, in scrape_releases
    scrape_release(source, feed, entry, link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 26, in scrape_release
    body = get_link_content(link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 14, in get_link_content
    (title, body) = readability_extract(response.content)
File "/projects/pressley/src/pressley/pressley/util.py", line 25, in readability_extract
    title_text = unicode(lxml.html.fromstring(doc.short_title()).text_content())
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 124, in short_title
    return shorten_title(self._html(True))
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/htmls.py", line 60, in shorten_title
    if title is None or len(title.text) == 0:
TypeError: object of type 'NoneType' has no len()

Traceback (most recent call last):
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 73, in handle
    self.scrape_releases(source)
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 47, in scrape_releases
    scrape_release(source, feed, entry, link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 26, in scrape_release
    body = get_link_content(link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 14, in get_link_content
    (title, body) = readability_extract(response.content)
File "/projects/pressley/src/pressley/pressley/util.py", line 25, in readability_extract
    title_text = unicode(lxml.html.fromstring(doc.short_title()).text_content())
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 124, in short_title
    return shorten_title(self._html(True))
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 104, in _html
    self.html = self._parse(self.input)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 108, in _parse
    doc = build_doc(input)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/htmls.py", line 18, in build_doc
    doc = lxml.html.document_fromstring(page_unicode.encode('utf-8', 'replace'), parser=utf8_parser)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/lxml/html/__init__.py", line 532, in document_fromstring
    value = etree.fromstring(html, parser, **kw)
File "lxml.etree.pyx", line 2753, in lxml.etree.fromstring (src/lxml/lxml.etree.c:54647)
File "parser.pxi", line 1578, in lxml.etree._parseMemoryDocument (src/lxml/lxml.etree.c:82764)
File "parser.pxi", line 1457, in lxml.etree._parseDoc (src/lxml/lxml.etree.c:81562)
File "parser.pxi", line 965, in lxml.etree._BaseParser._parseDoc (src/lxml/lxml.etree.c:78232)
File "parser.pxi", line 569, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/lxml.etree.c:74488)
File "parser.pxi", line 650, in lxml.etree._handleParseResult (src/lxml/lxml.etree.c:75379)
File "parser.pxi", line 599, in lxml.etree._raiseParseError (src/lxml/lxml.etree.c:74843)
XMLSyntaxError: line 404: Unexpected end tag : p

Traceback (most recent call last):
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 73, in handle
    self.scrape_releases(source)
File "/projects/pressley/src/pressley/pressley/releases/management/commands/scrape_releases.py", line 47, in scrape_releases
    scrape_release(source, feed, entry, link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 26, in scrape_release
    body = get_link_content(link)
File "/projects/pressley/src/pressley/pressley/releases/scrape.py", line 14, in get_link_content
    (title, body) = readability_extract(response.content)
File "/projects/pressley/src/pressley/pressley/util.py", line 25, in readability_extract
    title_text = unicode(lxml.html.fromstring(doc.short_title()).text_content())
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 124, in short_title
    return shorten_title(self._html(True))
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 104, in _html
    self.html = self._parse(self.input)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/readability.py", line 108, in _parse
    doc = build_doc(input)
File "/projects/pressley/virt/local/lib/python2.7/site-packages/readability/htmls.py", line 17, in build_doc
    page_unicode = page.decode(enc, 'replace')
TypeError: decode() argument 1 must be string, not None