33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
|
import http.client
|
||
|
|
import xml.etree.ElementTree as ET
|
||
|
|
|
||
|
|
conn = http.client.HTTPSConnection("www.sayweee.com")
|
||
|
|
payload = ''
|
||
|
|
headers = {}
|
||
|
|
conn.request("GET", "/en/product/Pete-and-Gerry-s-Organic-Large-Brown-Eggs/65902?category=dairy02", payload, headers)
|
||
|
|
res = conn.getresponse()
|
||
|
|
data = res.read()
|
||
|
|
|
||
|
|
# Parse the HTML page content using ElementTree
|
||
|
|
root = ET.fromstring(data.decode('utf-8'))
|
||
|
|
|
||
|
|
if root is not None:
|
||
|
|
# Find the script element with __NEXT_DATA__ data
|
||
|
|
next_data_element = None
|
||
|
|
for script_element in root.iter('script'):
|
||
|
|
if script_element.text is not None and '__NEXT_DATA__' in script_element.text:
|
||
|
|
next_data_element = script_element
|
||
|
|
break
|
||
|
|
|
||
|
|
# Extract the __NEXT_DATA__ data
|
||
|
|
if next_data_element is not None:
|
||
|
|
next_data_text = next_data_element.txt
|
||
|
|
next_data_start_index = next_data_text.index('{')
|
||
|
|
next_data_end_index = next_data_text.rindex('}') + 1
|
||
|
|
next_data_json = next_data_text[next_data_start_index:next_data_end_index]
|
||
|
|
print(next_data_json)
|
||
|
|
else:
|
||
|
|
print('__NEXT_DATA__ element not found')
|
||
|
|
else:
|
||
|
|
print('Failed to parse HTML content')
|