def _extract_biblio_efetch(self, page, id=None):
if "ArticleDate" in page:
dict_of_keylists = {"year": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Year"],
"month": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Month"],
"day": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Day"],
"title": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleTitle"],
"abstract": ["PubmedArticleSet", "MedlineCitation", "Article", "Abstract", "AbstractText"],
"issn": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "ISSN"],
"journal": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "Title"],
}
else:
dict_of_keylists = {"year": ["PubmedArticleSet", "MedlineCitation", "Article", "PubDate", "Year"],
"month": ["PubmedArticleSet", "MedlineCitation", "Article", "PubDate", "Month"],
"day": ["PubmedArticleSet", "MedlineCitation", "Article", "PubDate", "Day"],
"title": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleTitle"],
"abstract": ["PubmedArticleSet", "MedlineCitation", "Article", "Abstract", "AbstractText"],
"issn": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "ISSN"],
"journal": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "Title"],
}
biblio_dict = provider._extract_from_xml(page, dict_of_keylists)
dom_authors = provider._find_all_in_xml(page, "LastName")
try:
biblio_dict["authors"] = ", ".join([author.firstChild.data for author in dom_authors])
except (AttributeError, TypeError):
pass
mesh_list = provider._find_all_in_xml(page, "DescriptorName")
try:
if mesh_list:
biblio_dict["keywords"] = "; ".join([mesh_term.firstChild.data for mesh_term in mesh_list])
except (AttributeError, TypeError):
pass
try:
biblio_dict["issn"] = biblio_dict["issn"].replace("-", "")
except (AttributeError, KeyError):
pass
try:
datetime_published = datetime.datetime(year=biblio_dict["year"],
month=biblio_dict["month"],
day=biblio_dict["day"])
biblio_dict["date"] = datetime_published.isoformat()
biblio_dict["year"] = re.sub("\D", "", str(biblio_dict["year"]))
del biblio_dict["month"]
del biblio_dict["day"]
except (AttributeError, TypeError, KeyError):
logger.debug(u"%20s don't have full date information %s" % (self.provider_name, id))
pass
try:
biblio_dict["year"] = str(biblio_dict["year"])
except (KeyError):
pass
return biblio_dict
def _extract_biblio(self, page, id=None):
dict_of_keylists = {"year": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Year"],
"month": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Month"],
"day": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleDate", "Day"],
"title": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleTitle"],
"journal": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "Title"],
}
biblio_dict = provider._extract_from_xml(page, dict_of_keylists)
dom_authors = provider._find_all_in_xml(page, "LastName")
try:
biblio_dict["authors"] = ", ".join([author.firstChild.data for author in dom_authors])
except (AttributeError, TypeError):
pass
try:
datetime_published = datetime.datetime(year=biblio_dict["year"],
month=biblio_dict["month"],
day=biblio_dict["day"])
biblio_dict["date"] = datetime_published.isoformat()
del biblio_dict["month"]
del biblio_dict["day"]
except (AttributeError, TypeError, KeyError):
logger.debug("%20s don't have full date information %s" % (self.provider_name, id))
pass
return biblio_dict
def _extract_biblio(self, page, id=None):
dict_of_keylists = {
'title': ['entry', 'title'],
'date': ['entry', 'published'],
}
biblio_dict = provider._extract_from_xml(page, dict_of_keylists)
dom_authors = provider._find_all_in_xml(page, "name")
try:
authors = [author.firstChild.data for author in dom_authors]
biblio_dict["authors"] = ", ".join(
[author.split(" ")[-1] for author in authors])
except (AttributeError, TypeError):
pass
try:
biblio_dict["year"] = biblio_dict["date"][0:4]
except KeyError:
pass
biblio_dict["repository"] = "arXiv"
biblio_dict["free_fulltext_url"] = self._get_templated_url(
self.aliases_url_template, id, "aliases")
return biblio_dict
def _extract_biblio(self, page, id=None):
dict_of_keylists = {"year": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "PubDate", "Year"],
"title": ["PubmedArticleSet", "MedlineCitation", "Article", "ArticleTitle"],
"journal": ["PubmedArticleSet", "MedlineCitation", "Article", "Journal", "Title"],
}
biblio_dict = provider._extract_from_xml(page, dict_of_keylists)
dom_authors = provider._find_all_in_xml(page, "LastName")
try:
biblio_dict["authors"] = ", ".join([author.firstChild.data for author in dom_authors])
except (AttributeError, TypeError):
pass
return biblio_dict
def _extract_biblio(self, page, id=None):
dict_of_keylists = {
'title' : ['entry', 'title'],
'date' : ['entry', 'published'],
}
biblio_dict = provider._extract_from_xml(page, dict_of_keylists)
dom_authors = provider._find_all_in_xml(page, "name")
try:
authors = [author.firstChild.data for author in dom_authors]
biblio_dict["authors"] = ", ".join([author.split(" ")[-1] for author in authors])
except (AttributeError, TypeError):
pass
try:
biblio_dict["year"] = biblio_dict["date"][0:4]
except KeyError:
pass
biblio_dict["repository"] = "arXiv"
biblio_dict["free_fulltext_url"] = self._get_templated_url(self.aliases_url_template, id, "aliases")
return biblio_dict