a = newspaper.Article('http://answers.microsoft.com/en-us/windowslive/forum/moviemaker-files/corrupted-file/79292646-8d26-42a4-a9a3-742a101f70b3')
a.download()
a.parse()
/venv/lib/python3.4/site-packages/newspaper/article.py in parse(self)
208
209 # Before any computations on the body, clean DOM object
--> 210 self.doc = document_cleaner.clean(self.doc)
211
212 text = ''
/home/dan/edu/uni/projekty/bs/nourish/venv/lib/python3.4/site-packages/newspaper/cleaners.py in clean(self, doc_to_clean)
65 doc_to_clean = self.remove_nodes_regex(doc_to_clean, self.twitter_re)
66 doc_to_clean = self.clean_para_spans(doc_to_clean)
---> 67 doc_to_clean = self.div_to_para(doc_to_clean, 'div')
68 doc_to_clean = self.div_to_para(doc_to_clean, 'span')
69 return doc_to_clean
/home/dan/edu/uni/projekty/bs/nourish/venv/lib/python3.4/site-packages/newspaper/cleaners.py in div_to_para(self, doc, dom_type)
225 bad_divs += 1
226 elif div is not None:
--> 227 replaceNodes = self.get_replacement_nodes(doc, div)
228 div.clear()
229 for c, n in enumerate(replaceNodes):
/home/dan/edu/uni/projekty/bs/nourish/venv/lib/python3.4/site-packages/newspaper/cleaners.py in get_replacement_nodes(self, doc, div)
195 kid_text = self.parser.getText(kid)
196 self.replace_walk_left_right(kid, kid_text, replacement_text,
--> 197 nodes_to_remove)
198 else:
199 nodes_to_return.append(kid)
/home/dan/edu/uni/projekty/bs/nourish/venv/lib/python3.4/site-packages/newspaper/cleaners.py in replace_walk_left_right(self, kid, kid_text, replacement_text, nodes_to_remove)
158 and self.parser.getAttribute(
159 prev_node, 'grv-usedalready') != 'yes':
--> 160 outer = " " + self.parser.outerHtml(prev_node) + " "
161 replacement_text.append(outer)
162 nodes_to_remove.append(prev_node)
TypeError: Can't convert 'bytes' object to str implicitly
this is an easy fix, other lines are OK (e.g. line 173).
160 outer = " " + self.parser.outerHtml(prev_node) + " "
160 outer = " " + self.parser.outerHtml(prev_node).decode('utf-8') + " "
Hello,
I was getting this error when trying:
and this was error:
this is an easy fix, other lines are OK (e.g. line 173).
From this
to this: