I’ve now tried everything for the past few hours but I can’t extract a specific thing from the HTML below. I want to grab the “sessionCartId” but I can’t figure out how….
Thats what i tried so far :
JavaScript
x
4
1
sessioncartid = BeautifulSoup(response.text, "html.parser").findAll("script", {"type":"text/javascript"})[2]2
data = json.loads(sessioncartid.text)3
print(data)4
^^ This gives me the correct script tag but i cant transform it into a json nor get the sessioncarId
JavaScript
1
60
60
1
<script type="text/javascript">2
/*<![CDATA[*/3
4
var ACC = {config: {}};5
ACC.config.contextPath = "";6
ACC.config.encodedContextPath = "/de/web";7
ACC.config.commonResourcePath = "/_ui/20220811221438/responsive/common";8
ACC.config.themeResourcePath = "/_ui/20220811221438/responsive/theme-gh";9
ACC.config.siteResourcePath = "/_ui/20220811221438/responsive/site-ghstore";10
ACC.config.rootPath = "/_ui/20220811221438/responsive";11
ACC.config.CSRFToken = "81b0156a-5a78-4969-b52e-e5080473fb83";12
ACC.pwdStrengthVeryWeak = 'password.strength.veryweak';13
ACC.pwdStrengthWeak = 'password.strength.weak';14
ACC.pwdStrengthMedium = 'password.strength.medium';15
ACC.pwdStrengthStrong = 'password.strength.strong';16
ACC.pwdStrengthVeryStrong = 'password.strength.verystrong';17
ACC.pwdStrengthUnsafePwd = 'password.strength.unsafepwd';18
ACC.pwdStrengthTooShortPwd = 'password.strength.tooshortpwd';19
ACC.pwdStrengthMinCharText = 'password.strength.minchartext';20
ACC.accessibilityLoading = 'aria.pickupinstore.loading';21
ACC.accessibilityStoresLoaded = 'aria.pickupinstore.storesloaded';22
ACC.config.googleApiKey = "";23
ACC.config.googleApiVersion = "3.7";24
25
26
ACC.autocompleteUrl = '/de/web/search/autocompleteSecure';27
28
29
ACC.config.loginUrl = '/de/web/login';30
31
32
ACC.config.authenticationStatusUrl = '/de/web/authentication/status';33
34
35
/*]]>*/36
37
var OCC = 38
39
40
{41
42
"token": "1799248c-8de0-4199-b5fe-1d610452010a",43
44
"currentUser": "test@gmail.com",45
"sessionCartGuid": "2323121232323",46
"sessionCartId": "121212123435324",47
"sessionLanguageIso": "de",48
"sessionCountryIso": "DE",49
"urlPosCode": "web",50
"isASM": false,51
"intermediaryID": "",52
"isASMCustomerEmulated": false,53
"siteId": "ghstore",54
"OCCBaseUrl": "/ghcommercewebservices/v2/ghstore",55
"availablePointsOfService": "BUD,FRA,DTM,HAM,GRZ,HAJ,SZG,VIE,WEB,BER",56
"primaryPointOfSevice": "WEB",57
"clientChannel": "web-eu"58
};59
</script>60
Advertisement
Answer
This is how you can extract that dictionary:
JavaScript
1
73
73
1
from bs4 import BeautifulSoup2
import json3
import re4
5
html = '''6
<script type="text/javascript">7
/*<![CDATA[*/8
9
var ACC = {config: {}};10
ACC.config.contextPath = "";11
ACC.config.encodedContextPath = "/de/web";12
ACC.config.commonResourcePath = "/_ui/20220811221438/responsive/common";13
ACC.config.themeResourcePath = "/_ui/20220811221438/responsive/theme-gh";14
ACC.config.siteResourcePath = "/_ui/20220811221438/responsive/site-ghstore";15
ACC.config.rootPath = "/_ui/20220811221438/responsive";16
ACC.config.CSRFToken = "81b0156a-5a78-4969-b52e-e5080473fb83";17
ACC.pwdStrengthVeryWeak = 'password.strength.veryweak';18
ACC.pwdStrengthWeak = 'password.strength.weak';19
ACC.pwdStrengthMedium = 'password.strength.medium';20
ACC.pwdStrengthStrong = 'password.strength.strong';21
ACC.pwdStrengthVeryStrong = 'password.strength.verystrong';22
ACC.pwdStrengthUnsafePwd = 'password.strength.unsafepwd';23
ACC.pwdStrengthTooShortPwd = 'password.strength.tooshortpwd';24
ACC.pwdStrengthMinCharText = 'password.strength.minchartext';25
ACC.accessibilityLoading = 'aria.pickupinstore.loading';26
ACC.accessibilityStoresLoaded = 'aria.pickupinstore.storesloaded';27
ACC.config.googleApiKey = "";28
ACC.config.googleApiVersion = "3.7";29
30
31
ACC.autocompleteUrl = '/de/web/search/autocompleteSecure';32
33
34
ACC.config.loginUrl = '/de/web/login';35
36
37
ACC.config.authenticationStatusUrl = '/de/web/authentication/status';38
39
40
/*]]>*/41
42
var OCC = 43
44
45
{46
47
"token": "1799248c-8de0-4199-b5fe-1d610452010a",48
49
"currentUser": "test@gmail.com",50
"sessionCartGuid": "2323121232323",51
"sessionCartId": "121212123435324",52
"sessionLanguageIso": "de",53
"sessionCountryIso": "DE",54
"urlPosCode": "web",55
"isASM": false,56
"intermediaryID": "",57
"isASMCustomerEmulated": false,58
"siteId": "ghstore",59
"OCCBaseUrl": "/ghcommercewebservices/v2/ghstore",60
"availablePointsOfService": "BUD,FRA,DTM,HAM,GRZ,HAJ,SZG,VIE,WEB,BER",61
"primaryPointOfSevice": "WEB",62
"clientChannel": "web-eu"63
};64
</script>65
'''66
soup = BeautifulSoup(html, 'html.parser')67
info = soup.select_one('script', string = re.compile('sessionCartGuid'))68
json_obj = json.loads(info.text.split('var OCC =')[1].split(';')[0])69
# print(json_obj)70
print(json_obj['token'])71
print(json_obj['currentUser'])72
print(json_obj['sessionCartId'])73
Result:
JavaScript
1
4
1
1799248c-8de0-4199-b5fe-1d610452010a2
test@gmail.com3
1212121234353244
BeautifulSoup docs: https://beautiful-soup-4.readthedocs.io/en/latest/index.html