I am working on a task in which I have to get details from a web page using python request library. I have successfully got the details from the page but it has a button “Show Details” which fetches more details using ajax call, now I need to fetch those extra details also. can anyone help me in doing so?
here’s the link to website:- http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx
and a screen shot of website here:
Here’s my code which i have made.
JavaScript
x
60
60
1
from bs4 import BeautifulSoup2
import requests,json3
4
def returnJson(wordmark, page_class):5
url = "http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx"6
r_init = requests.get(url)7
soup = BeautifulSoup(r_init.text, 'html.parser')8
event_validation = soup.find("input", attrs={"name" : "__EVENTVALIDATION"})['value']9
view_state = soup.find("input", attrs={"name" : "__VIEWSTATE"})['value']10
search_type = 'WM'11
postdata = {12
'ctl00$ContentPlaceHolder1$DDLFilter' : '0',13
'ctl00$ContentPlaceHolder1$DDLSearchType' : search_type,14
'ctl00$ContentPlaceHolder1$TBWordmark' : wordmark,15
'ctl00$ContentPlaceHolder1$TBClass' : page_class,16
'__EVENTVALIDATION' : event_validation,17
"__EVENTTARGET" : "ctl00$ContentPlaceHolder1$BtnSearch",18
"__VIEWSTATE" : view_state,19
}20
21
r = requests.post(url, data=postdata)22
return r23
24
def scraping(r):25
soup = BeautifulSoup(r.text, 'html.parser')26
27
28
counter=len(soup.findAll('tr',attrs={'class':'row'}))29
counter+=len(soup.findAll('tr',attrs={'class':'alt'}))30
wordmark_idvalue='ContentPlaceHolder1_MGVSearchResult_lblsimiliarmark_'31
proprietor_idvalue='ContentPlaceHolder1_MGVSearchResult_LblVProprietorName_'32
applicationno_idvalue='ContentPlaceHolder1_MGVSearchResult_lblapplicationnumber_'33
class_idvalue='ContentPlaceHolder1_MGVSearchResult_lblsearchclass_'34
status_idvalue='ContentPlaceHolder1_MGVSearchResult_Label6_'35
words_list=[]36
for i in range(0,counter):37
words_dict={}38
row=soup.find('span',attrs={'id':(wordmark_idvalue+str(i))})39
words_dict['Wordmark']=row.text40
row=soup.find('span',attrs={'id':(proprietor_idvalue+str(i))})41
words_dict['Proprietor']=row.text42
row=soup.find('span',attrs={'id':(applicationno_idvalue+str(i))})43
words_dict['Application Number']=row.text44
row=soup.find('span',attrs={'id':(class_idvalue+str(i))})45
words_dict['Class ']=row.text46
row=soup.find('span',attrs={'id':(status_idvalue+str(i))})47
words_dict['Status']=row.text48
words_list.append(words_dict)49
return words_list50
51
52
def showDetails(wordmark, page_class):53
if(len(wordmark)>2 and page_class.isalnum()==1):54
var=json.dumps(scraping(returnJson(wordmark, page_class)))55
return var56
else:57
print("Please Enter Valid Parametersn")58
59
showDetails('AIWA','2')60
Advertisement
Answer
You need to create another POST request using information from the first POST request. The following shows how the Goods & Services Description could be extracted from the returned data:
JavaScript
1
96
96
1
from operator import itemgetter2
from bs4 import BeautifulSoup3
import requests,json4
5
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'}6
7
def get_input_value(soup, name):8
return soup.find("input", attrs={"name" : name})['value']9
10
11
def returnJson(wordmark, page_class):12
url = "http://ipindiaonline.gov.in/tmrpublicsearch/frmmain.aspx"13
r_init = requests.get(url)14
soup = BeautifulSoup(r_init.text, 'html.parser')15
16
postdata = {17
"ctl00$ContentPlaceHolder1$DDLFilter" : "0",18
"ctl00$ContentPlaceHolder1$DDLSearchType" : "WM",19
"ctl00$ContentPlaceHolder1$TBWordmark" : wordmark,20
"ctl00$ContentPlaceHolder1$TBClass" : page_class,21
"__EVENTVALIDATION" : get_input_value(soup, "__EVENTVALIDATION"),22
"__EVENTTARGET" : "ctl00$ContentPlaceHolder1$BtnSearch",23
"__VIEWSTATE" : get_input_value(soup, "__VIEWSTATE"),24
}25
26
r = requests.post(url, headers=headers, data=postdata)27
return r28
29
30
def scraping(r):31
soup = BeautifulSoup(r.content, 'html.parser')32
33
counter = len(soup.find_all('tr', attrs={'class':'row'}))34
counter += len(soup.find_all('tr', attrs={'class':'alt'}))35
36
words_list = []37
38
fields = [39
("Wordmark", "ContentPlaceHolder1_MGVSearchResult_lblsimiliarmark_{}"),40
("Proprietor", "ContentPlaceHolder1_MGVSearchResult_LblVProprietorName_{}"),41
("Application Number", "ContentPlaceHolder1_MGVSearchResult_lblapplicationnumber_{}"),42
("Class", "ContentPlaceHolder1_MGVSearchResult_lblsearchclass_{}"),43
("Status", "ContentPlaceHolder1_MGVSearchResult_Label6_{}"),44
]45
46
for index in range(0, counter):47
words_dict = {}48
for key, field in fields:49
words_dict[key] = soup.find('span', attrs={'id' : field.format(index)}).text50
51
print("Wordmark: {}".format(words_dict["Wordmark"]))52
53
# Construct a POST request for the Show Details panel54
55
# Locate matching 'Show details' link56
span = soup.find('span', attrs={'id' : fields[0][1].format(index)})57
a = span.find_next('a', class_='LnkshowDetails')58
lnk_show_details = a['href'].split("'")[1]59
60
data = {61
"__EVENTTARGET" : lnk_show_details,62
"__VIEWSTATE" : get_input_value(soup, "__VIEWSTATE"),63
"__VIEWSTATEENCRYPTED" : "",64
"__EVENTVALIDATION" : get_input_value(soup, "__EVENTVALIDATION"),65
"__ASYNCPOST" : "true",66
}67
68
url = "http://ipindiaonline.gov.in/tmrpublicsearch" + soup.form["action"].strip(".")69
r_details = requests.post(url, headers=headers, data=data)70
html = b''.join(itemgetter(7, 8)(r_details.content.split(b"|")))71
soup_details = BeautifulSoup(html, "html.parser")72
73
details = {}74
75
for tr in soup_details.find_all('tr'):76
row = [td.text for td in tr.find_all('td')] # Note: Journal No and Used since would need more work77
details[row[0]] = row[1]78
79
# Copy description80
desc = 'Goods & Services Description'81
words_dict[desc] = details[desc]82
83
words_list.append(words_dict)84
85
return words_list86
87
88
def showDetails(wordmark, page_class):89
if len(wordmark) > 2 and page_class.isalnum() == 1:90
var = json.dumps(scraping(returnJson(wordmark, page_class)))91
return var92
else:93
print("Please Enter Valid Parametersn")94
95
print(showDetails('AIWA','2'))96
This would display:
JavaScript
1
5
1
Wordmark: AIWA2
Wordmark: AIWACEM 3
Wordmark: AIWAPRIME (LABEL)4
[{"Wordmark": "AIWA", "Proprietor": "AIWA CO. LTD.", "Application Number": "683935", "Class": "2", "Status": "Registered", "Goods & Services Description": "PAINTS, VARNISHES, LACQUERS, PRESERVATIVES AGAINST RUST AND AGAINST DESTRIORATION OF WOOD, COLOURING MATTERS, DYESTUFFS, MORDANTS, NATURAL RESINS, METALS IN FOIL AND POWDER FROM FOR PAINTERS AND DECORATORS."}, {"Wordmark": "AIWACEM ", "Proprietor": "AMITA B. MEHTA", "Application Number": "1108415", "Class": "2", "Status": "Registered", "Goods & Services Description": "waterproof cement paint."}, {"Wordmark": "AIWAPRIME (LABEL)", "Proprietor": "AMITA B. MEHTA", "Application Number": "1165809", "Class": "2", "Status": "Registered", "Goods & Services Description": "WATER BASED CEMENT PRIMER INCLUDED IN CLASS 2."}]5
Note: The data returned contains other fields which are separated by the | character. The HTML for the details also happens to contain this character so it is necessary to extract fields 7 and 8 to get just the HTML.