Python-103 获取文献列表和输出词云 2021-03-

• 下载文献列表并输出worldcloud:

#python -m ensurepip

from Bio import Entrez
from Bio import Medline
import csv
import numpy as np
from PIL import Image #pip install pillow
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator #pip install wordcloud

import matplotlib.pyplot as plt

#获取
# 参数设置
Entrez.email = "abc@zju.edu.cn"
Entrez.max_tries=6
Entrez.sleep_between_tries = 500
Entrez.api_key="1620334c97028769f1779fa9078fac18f108"
# 搜索
paper_counts =1000
serch_term = 'Lachnospiraceae'#对excel提取的词进行搜索
hd_esearch = Entrez.esearch(db="pubmed", term=serch_term,retmax=paper_counts, usehistory="y")
read_esearch = Entrez.read(hd_esearch)
hd_esearch.close()
eftech_id_list = read_esearch["IdList"]
efetch_step = 1000
articleInfo = []
wordcloud_abstract =""
wordcloud_keywords =""
wordcloud_jounals  =""

for efetch_start in range(0, paper_counts, efetch_step):
    print("Download records %i to %i" % (efetch_start + 1, int(efetch_start+efetch_step)))
    flag = False
    n=2
    while (flag != True):
         head_efetch = Entrez.efetch(db="pubmed", id=eftech_id_list, rettype="medline", retmode="text", retstart=efetch_start, retmax=efetch_step)
         records = Medline.parse(head_efetch)
         records = list(records)
         if ("TI" in records[0]):
              # print(records[0].get("TI"))
              # print("success")
              flag = True
              for record in records:
                   # print(record)
                   # print("title:", record.get("TI", "?"))
                   # print("authors:", record.get("AU", "?"))
                   # print("source:", record.get("SO", "?"))
                   temp_dict = {u'pubmed_id':record.get("PMID", "?"),
                                       u'journal':record.get("JT", "?"),
                                       u'title':record.get("TI", "?"),
                                       u'keywords':str(record.get("OT", "?")).replace(']','').replace('[','').replace("'", ""),
                                       u'abstract':record.get("AB", "?"),}
                   wordcloud_abstract = wordcloud_abstract +"\n"+record.get("AB", "?")
                   wordcloud_keywords = wordcloud_keywords + "\t"+str(record.get("OT", "?")).replace(']','').replace('[','').replace("'", "")
                   wordcloud_jounals =  wordcloud_jounals +"\n"+record.get("JT", "?")
                   # print(temp_dict)
                   articleInfo.append(temp_dict.copy())
                   # print(articleInfo)
                   temp_dict.clear()

         else:

              print(" fatal error", "第", n, "次尝试")
         n = n + 1

# print(articleInfo)
# print(wordcloud_abstract)

# journal wordcloud
text_journal = wordcloud_jounals
wordcloud_jounals_plt = WordCloud().generate(text_journal)
plt.figure(figsize=(20,30))
plt.imshow(wordcloud_jounals_plt, interpolation='bilinear')
plt.axis("off")
plt.savefig('C:\\Users\\Mr.R\\Desktop\\1\\'+serch_term+"_"+"journals"+".png", dpi=300, bbox_inches='tight')

# abstract wordcloud
text_abstract = wordcloud_abstract
wordcloud_abstract_plt = WordCloud().generate(text_abstract)
plt.figure(figsize=(20,30))
plt.imshow(wordcloud_abstract_plt, interpolation='bilinear')
plt.axis("off")
plt.savefig('C:\\Users\\Mr.R\\Desktop\\1\\'+serch_term+"_"+"abstract"+".png", dpi=300, bbox_inches='tight')


file_name = 'C:\\Users\\Mr.R\\Desktop\\1\\' + serch_term +"4.csv"
field_names = ['pubmed_id', 'title','keywords','journal','abstract','year']
with open(file_name, 'w') as csvfile:
    writer = csv.DictWriter(csvfile, fieldnames = field_names)
    writer.writeheader()
    writer.writerows(articleInfo)

image.png image.png