Spaces:
Sleeping
Sleeping
File size: 9,317 Bytes
79899c0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
import xml.etree.ElementTree as ET
import re
class PubmedXmlParse:
def __init__(self):
pass
def remove_xml_tags(self, text):
"""移除XML标签，返回纯文本"""
clean = re.compile('<.*?>')
return re.sub(clean, '', text)
# 解析 XML 数据
def parse_pubmed_xml(self, xml_data):
tree = ET.ElementTree(ET.fromstring(xml_data))
root = tree.getroot()
articles = []
# 遍历每个 PubmedArticle 元素
for article in root.findall(".//PubmedArticle"):
# 提取文章信息
article_title_elem = article.find(".//ArticleTitle")
article_title = ""
if article_title_elem is not None:
# Convert element to string and decode to handle tags
title_text = ET.tostring(article_title_elem, encoding='unicode', method='xml')
# Remove the ArticleTitle tags but keep inner content and tags
title_text = title_text.replace('<ArticleTitle>', '').replace('</ArticleTitle>', '')
# Remove all XML tags to get plain text
article_title = self.remove_xml_tags(title_text).strip()
pmid = (
article.find(".//ArticleId[@IdType='pubmed']").text
if article.find(".//ArticleId[@IdType='pubmed']") is not None
else ""
)
abstract_texts = article.findall(".//AbstractText")
abstract_text = (
" ".join(
[
abstract.text if abstract.text is not None else ""
for abstract in abstract_texts
]
)
if abstract_texts
else ""
)
# 提取作者信息
authors = []
for author in article.findall(".//Author"):
authors.append(
{
"lastname": (
author.find(".//LastName").text
if author.find(".//LastName") is not None
else ""
),
"forename": (
author.find(".//ForeName").text
if author.find(".//ForeName") is not None
else ""
),
"initials": (
author.find(".//Initials").text
if author.find(".//Initials") is not None
else ""
),
"affiliation": (
author.find(".//AffiliationInfo/Affiliation").text
if author.find(".//AffiliationInfo/Affiliation") is not None
else ""
),
}
)
journal = {
"issn": (
article.find(".//Journal/ISSN").text
if article.find(".//Journal/ISSN") is not None
else ""
),
"title": (
article.find(".//Journal/Title").text
if article.find(".//Journal/Title") is not None
else ""
),
"abbreviation": (
article.find(".//Journal/ISOAbbreviation").text
if article.find(".//Journal/ISOAbbreviation") is not None
else ""
),
"startPage": (
article.find(".//Pagination/StartPage").text
if article.find(".//Pagination/StartPage") is not None
else ""
),
"endPage": (
article.find(".//Pagination/EndPage").text
if article.find(".//Pagination/EndPage") is not None
else ""
),
"volume": (
article.find(".//Journal/JournalIssue/Volume").text
if article.find(".//Journal/JournalIssue/Volume") is not None
else ""
),
"issue": (
article.find(".//Journal/JournalIssue/Issue").text
if article.find(".//Journal/JournalIssue/Issue") is not None
else ""
),
"year": (
article.find(".//Journal/JournalIssue/PubDate/Year").text
if article.find(".//Journal/JournalIssue/PubDate/Year") is not None
else ""
),
}
medline = article.find("MedlineCitation")
references = article.findall(".//PubmedData/ReferenceList/Reference")
# 将每篇文章的信息添加到列表中
articles.append(
{
"pmid": pmid,
"pmcid": (
article.find(
".//PubmedData/ArticleIdList/ArticleId[@IdType='pmc']"
).text
if article.find(
".//PubmedData/ArticleIdList/ArticleId[@IdType='pmc']"
)
is not None
else ""
),
"title": article_title,
"abstract": abstract_text,
"journal": journal,
"authors": authors,
"pub_date": {
"year": (
article.find(".//Journal/JournalIssue/PubDate/Year").text
if article.find(".//Journal/JournalIssue/PubDate/Year")
is not None
else ""
),
"month": (
article.find(".//Journal/JournalIssue/PubDate/Month").text
if article.find(".//Journal/JournalIssue/PubDate/Month")
is not None
else ""
),
"day": (
article.find(".//Journal/JournalIssue/PubDate/Day").text
if article.find(".//Journal/JournalIssue/PubDate/Day")
is not None
else ""
),
},
"keywords": (
[k.text for k in medline.findall(".//KeywordList/Keyword")]
if medline.findall(".//KeywordList/Keyword") is not None
else ""
),
"doi": self.parse_doi(medline.find("Article"), article),
"mesh_terms": [
self.parse_mesh(m)
for m in medline.findall("MeshHeadingList/MeshHeading")
],
"references": [self.parse_reference(r) for r in references],
}
)
return articles
def parse_doi(self, article, article_elem) -> str:
if article.find(".//ELocationID[@EIdType='doi']") is not None:
doi = article.find(".//ELocationID[@EIdType='doi']").text
if doi is not None and doi != "":
return doi
elif article_elem.find(".//ArticleIdList/ArticleId[@IdType='doi']") is not None:
doi = article_elem.find(".//ArticleIdList/ArticleId[@IdType='doi']").text
if doi is not None and doi != "":
return doi
else:
return ""
def parse_mesh(self, mesh_elem):
"""解析MeSH主题词"""
return {
"descriptor": (
mesh_elem.find(".//DescriptorName").text
if mesh_elem.find(".//DescriptorName") is not None
else ""
),
"qualifiers": [
(
q.find(".//QualifierName").text
if q.find(".//QualifierName") is not None
else ""
)
for q in mesh_elem.findall(".//QualifierName")
],
}
def parse_reference(self, reference_elem):
"""解析参考文献"""
return {
"citation": (
reference_elem.find("Citation").text
if reference_elem.find("Citation") is not None
else ""
),
"doi": (
reference_elem.find(".//ArticleId[@IdType='doi']").text
if reference_elem.find(".//ArticleId[@IdType='doi']") is not None
else ""
),
"pmid": (
reference_elem.find(".//ArticleId[@IdType='pubmed']").text
if reference_elem.find(".//ArticleId[@IdType='pubmed']") is not None
else ""
),
"pmcid": (
reference_elem.find(".//ArticleId[@IdType='pmcid']").text
if reference_elem.find(".//ArticleId[@IdType='pmcid']") is not None
else ""
),
}
|