def makeNote(noteStore, noteTitle, noteBody, sourceUrl='', resources=[], parentNotebook=None):
nBody = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"
nBody += "<!DOCTYPE en-note SYSTEM \"http://xml.evernote.com/pub/enml2.dtd\">"
nBody += "<en-note>" + noteBody + "</en-note>"
logger.info(nBody)
## Create note object
ourNote = Types.Note()
ourNote.title = noteTitle
ourNote.content = nBody
if resources:
ourNote.resources = resources
if sourceUrl:
note_attrs = Types.NoteAttributes()
note_attrs.sourceURL = sourceUrl
ourNote.attributes = note_attrs
## parentNotebook is optional; if omitted, default notebook is used
# if parentNotebook and hasattr(parentNotebook, 'guid'):
# ourNote.notebookGuid = parentNotebook.guid
if parentNotebook:
ourNote.notebookGuid = parentNotebook
## Attempt to create note in Evernote account
note = noteStore.createNote(ourNote)
## Something was wrong with the note data
## See EDAMErrorCode enumeration for error code explanation
## http://dev.evernote.com/documentation/reference/Errors.html#Enum_EDAMErrorCode
## Parent Notebook GUID doesn't correspond to an actual notebook
## Return created note object
return note
def get_content(self):
logger.info("get_content url %s" % self.url)
r = requests.get(self.url, headers=self.headers)
logger.info("get_content res %s " % r.text)
res_json = r.json()
content = res_json.get('content', '')
soup = BeautifulSoup(content, "html5lib")
soup.find_all(self.remove_attrs)
soup.html.unwrap()
soup.head.unwrap()
soup.body.unwrap()
title = res_json.get('title', '')
# question_id = res_json.get('question', {}).get('id', '')
id = res_json.get('id', '')
note_url = 'https://zhuanlan.zhihu.com/p/%s' % (id)
res = self.change_img(soup)
title_list = title.split('\n')
title = ''
for t in title_list:
title += t
logger.info("note_url %s" % note_url)
logger.info("title %s" % title)
html_content = str(soup)
res = EvernoteMethod.makeNote(self.noteStore, title.encode('utf8'), html_content, note_url, res, self.parent_note)
def get_list(self, url):
r = s.get(url, headers=self.headers)
res_json = r.json()
data_info = res_json.get('data', [])
next_url = None
if data_info and self.force_check:
paging_dict = res_json.get('paging', {})
next_url = paging_dict.get('next', None)
for data in data_info:
type_info = data.get('type', '')
if type_info == 'article':
data_url = data.get('url')
data_id = (data.get('id'))
data_title = data.get('title')
if not data_url or not data_id or not data_title:
logger.error("%s error" % data)
continue
if redis_obj.sismember('zhihu_zhuanlan_id', data_id):
logger.warning("%s %s %s exits" % (data_url, data_id, data_title))
continue
logger.info("+++++++++++++++++++++++++++++++++++++++++++")
logger.info(data_url)
logger.info(data_id)
logger.info(data_title)
self.push_fav(data)
logger.info("+++++++++++++++++++++++++++++++++++++++++++")
logger.info("\n")
# return
if next_url:
logger.info("next url %s" % next_url)
self.get_list(next_url)
