File size: 3,780 Bytes
c680313 |
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 |
import json
import xml.etree.ElementTree as ET
from bs4 import BeautifulSoup
import requests
import tools
import threading
def fetch_links(category):
links = []
xml_data = tools.fetch_page(f"https://www.sciencedaily.com/rss/top/{category.lower()}.xml")
items = ET.fromstring(xml_data).findall('channel/item')
for item in items:
link = item.find('link').text
links.append(link)
return links
def fetch_all_links():
categories = ["Science", "Health", "Environment", "Technology", "Society"]
sd_links_data = {}
for category in categories:
links = fetch_links(category)
sd_links_data[category] = links
data = json.dumps(sd_links_data, indent=4, ensure_ascii=False)
return data
def fetch_dois():
doi_data = {}
data = json.loads(fetch_all_links())
for topic, links in data.items():
doi_list = []
for link in links:
page_content = tools.fetch_page(link)
page_datas = BeautifulSoup(page_content, 'html.parser').find_all("div", id="journal_references")
for page_data in page_datas:
doi = page_data.find("a", href=True).text
if doi.startswith('10.'):
doi_list.append(doi)
else:
continue
doi_data[topic] = doi_list
data = json.dumps(doi_data, indent=4, ensure_ascii=False)
return data
def fetch_doi_data():
result = []
def fetch_and_store():
result.append(fetch_dois())
thread = threading.Thread(target=fetch_and_store)
thread.start()
thread.join()
return result[0]
def doi_to_pmc():
data = json.loads(fetch_doi_data())
pmc_data = {}
for topic, dois in data.items():
if len(dois) > 0:
doi_list = ""
for doi in dois:
doi_list += doi + ","
doi_list = doi_list.rstrip(',')
try:
url = f"https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/[email protected]&ids={doi_list}&format=json"
doi_pmc_data = requests.get(url).json()
except Exception as e:
print(f"Error: {str(e)}")
if doi_pmc_data['status'] == 'ok':
pmc_list = []
for record in doi_pmc_data['records']:
if 'pmcid' in record:
if 'live' in record and record['live'] == False:
continue
pmc_list.append(record['pmcid'])
else:
continue
pmc_data[topic] = pmc_list
else:
continue
else:
continue
data = json.dumps(pmc_data, indent=4, ensure_ascii=False)
return data
def extract_pmc_data():
if not tools.download_datafile('pmc.txt'):
raise Exception("Failed to download datafile")
pmc_data ={}
pmcid_data = json.loads(doi_to_pmc())
for topic, pmcids in pmcid_data.items():
pmc_ids = []
for id in pmcids:
if tools.check_data_in_file(id, 'pmc.txt'):
continue
else:
tools.write_data_to_file(id, 'pmc.txt')
pmc_ids.append(id)
pmc_data[topic] = {}
pmc_data[topic]['count'] = len(pmc_ids)
pmc_data[topic]['ids'] = pmc_ids
data = json.dumps(pmc_data, indent=4, ensure_ascii=False)
if not tools.upload_datafile('pmc.txt'):
raise Exception("Failed to upload datafile")
return data
if __name__ == "__main__":
data = extract_pmc_data()
with open('pmc_data.json', 'w') as f:
f.write(data) |