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
|
import requests,re
import pandas as pd
from functools import reduce
from bs4 import BeautifulSoup
def checkEn(strs):
for _char in strs:
if '\u4e00' <= _char <= '\u9fd5':
return True
return False
def getInfoFromPubmed(strs):
url = "https://pubmed.ncbi.nlm.nih.gov/?term="+strs
session = requests.Session()
response = session.get(url)
soup = BeautifulSoup(response.text,'lxml')
cite = soup.find("span", class_="cit").get_text().strip()
authors = soup.find_all("a", class_="full-name")
authors = [item.get_text().strip() for item in authors]
func = lambda authors,i: authors if i in authors else authors + [i]
authors_set = reduce(func, [[], ] + authors)
author = ','.join(authors_set)
doi = soup.find("span", class_="citation-doi").get_text().strip()
journal = soup.find("button", class_="journal-actions-trigger trigger").get_text().strip()
year = cite.split(";")[0]
vol = cite.split(";")[1].split(":")[0]
if "(" in vol:
pat = re.compile('\((.*?)\)')
no = re.findall(pat,vol)[0]
vol = vol.split("(")[0]
else:
no = None
page = cite.split(":")[-1].strip(".")
return author,year,vol,no,page,doi,journal
def getInfoFromJustscience(journal):
url = "http://sci.justscience.cn/?q="+journal
session = requests.Session()
response = session.get(url)
form = pd.read_html(response.text)[1]
for index in form.index:
target = form.loc[index,'期刊缩写']
if target == journal:
impact = form.loc[index,'影响因子']
else:
impact = None
return impact
if __name__ == '__main__':
data = pd.read_excel("论文成果.xls",index_col=0,header=1)
for index in data.index:
title = data.loc[index,"论文名称"]
status = checkEn(title)
try:
if not status:
author,year,vol,no,page,doi,journal = getInfoFromPubmed(title)
impact = getInfoFromjustscience(journal)
data.loc[index,'作者名称'] = author
data.loc[index,'发表时间'] = year
data.loc[index,'卷号'] = vol
data.loc[index,'期号'] = no
data.loc[index,'页面范围'] = page
data.loc[index,'DOI码'] = doi
data.loc[index,'影响因子'] = impact
except:
pass
data.to_excel("result.xlsx")
|
