import requests
import json
from lxml import etree
from lxml import html
import urllib.parse

coluns =  ["geneSymbol", "uniprotAC", "uniprotID", "proteinName","EentrezGeneID", "desc", "notes"]
q2 = pd.DataFrame(columns=coluns)
genes = ["BAT1","CCL2","CCR5","CxCL10","CXCL9","HLA-DPB1", "HLA-DRB1","IFNG","IL10","IL12B",
         "IL1B","IL1RN","IL4","IL4R","IL6","LTA","TGFB","TNF","TNFA","TNFB"]
#"HLA-DQB1",
url1 = "http://rest.genenames.org/search/symbol:"
url3 = "+AND+status:Approved"
url4 = "http://rest.genenames.org/fetch/hgnc_id/"
url6 = "https://www.ebi.ac.uk/proteins/api/proteins/"
ic = 0
for i in range(0,len(genes)):
    url2 = genes[i]
    r = requests.get(urllib.parse.urljoin(url1, url2,url3))
    rHTML = html.fromstring(r.content)
    resp = rHTML.xpath('//str/text()')
    url5 = resp[0][5:]

    r1 = requests.get(urllib.parse.urljoin(url4, url5))
    rHTML1 = html.fromstring(r1.content)
    d1 = rHTML1.xpath('//str[@name="symbol"]/text()')
    d2 = "x"#rHTML1.xpath('//str[@name="uniprotAC"]/text()')
    d3 = rHTML1.xpath('//arr[@name="uniprot_ids"]/str/text()')
    d4 = rHTML1.xpath('//str[@name="name"]/text()')
    d5 = rHTML1.xpath('//str[@name="entrez_id"]/text()')
    d6 = "x"#rHTML1.xpath('//str[@name="desc"]/text()')
    d7 = rHTML1.xpath('//str[@name="status"]/text()')

    q2.loc[i] = [d1[0],d2[0],d3[0],d4[0],d5[0],d6,d7[0]]
q2