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
| import os
import random
import openpyxl
import csv
import time
import requests
from bs4 import BeautifulSoup
import re
os.chdir('C:/Users/Administrator/Desktop')
with open('temp.txt','r') as f:
for line in f:
acuce_gene_id = line.split('\t')[1].split('.')[0]
acuce_prot_id = line.split('\t')[1]
match_uniprot_id = line.split('\t')[2]
uniprot_link = 'https://www.uniprot.org/uniprot/' + match_uniprot_id.split('.')[0]
res = requests.get(uniprot_link)
soup = BeautifulSoup(res.text,'html.parser')
organism = soup.find('div',id = 'content-organism', class_ = 'entry-overview-content').get_text()
gene = soup.find('div',id = 'content-gene', class_ = 'entry-overview-content').get_text()
protein = soup.find('div',id = 'content-protein', class_ = 'entry-overview-content').get_text()
res_temp = {'Q9UUH7':[organism,gene,protein]}
function = soup.find('div', class_ = 'annotation').find('span').get_text().replace('By similarity','')
go_mol = soup.find('ul', class_ = 'noNumbering molecular_function')
if str(type(go_mol)) != "<class 'NoneType'>":
for i in go_mol.find_all('a'):
link = i['href']
link_split = link.split('/')
go_item_id = link_split[len(link_split)-1]
if go_item_id.split(':')[0] != 'GO':
continue
else:
go_item = i.get_text()
res_excel = openpyxl.Workbook()
sheet = res_excel.active
sheet.title = '爬虫结果'
col_name = ['月亮谷基因编号','月亮谷转录本编号','匹配的UniProt编号','蛋白名称','物种','基因','功能','GO ID','GO Description','Link']
sheet.append(col_name)
res_new = [acuce_gene_id,acuce_prot_id,match_uniprot_id,protein,organism,gene,function,go_item_id,go_item_id,link]
sheet.append(res_new)
file_name = os.getcwd() + '/results/' + 'GO_Biological_process_' + acuce_prot_id + '_' + match_uniprot_id + '_' +go_item_id.replace(':','_') + '.xlsx'
res_excel.save(file_name)
go_bio = soup.find('ul', class_ = 'noNumbering biological_process')
if str(type(go_bio)) != "<class 'NoneType'>":
for i in go_bio.find_all('li'):
link = i.find('a')['href']
link_split = link.split('/')
go_item_id = link_split[len(link_split)-1]
if go_item_id.split(':')[0] != 'GO':
continue
else:
go_item = i.find('a').get_text()
res_excel = openpyxl.Workbook()
sheet = res_excel.active
sheet.title = '爬虫结果'
col_name = ['月亮谷基因编号','月亮谷转录本编号','匹配的UniProt编号','蛋白名称','物种','基因','功能','GO ID','GO Description','Link']
sheet.append(col_name)
res_new = [acuce_gene_id,acuce_prot_id,match_uniprot_id,protein,organism,gene,function,go_item_id,go_item,link]
sheet.append(res_new)
file_name = os.getcwd() + '/results/' + 'GO_Biological_process_' + acuce_prot_id + '_' + match_uniprot_id + '_' +go_item_id.replace(':','_') + '.xlsx'
res_excel.save(file_name)
|