add thriftbooks; f ix homedepot; fix generic

README.md

@@ -38,6 +38,7 @@ Supported Emails
 - Sony
 - Swiss Post
 - Target
+- Thriftbooks
 - Timeless
 - The Smartest House
 - Ubiquiti

custom_components/email/manifest.json

@@ -11,5 +11,5 @@
         "imapclient==2.3.1",
         "mail-parser==3.9.3"
     ],
-    "version": "3.5.0"
+    "version": "3.12.0"
 }

custom_components/email/parsers/generic.py

@@ -29,4 +29,4 @@ def parse_generic(email):
         if tracking_number not in tracking_numbers:
             tracking_numbers.append(tracking_number)
 
-    return tracking_numbers,
+    return tracking_numbers

custom_components/email/parsers/home_depot.py

@@ -11,6 +11,9 @@
 EMAIL_DOMAIN_HOME_DEPOT = 'homedepot.com'
 
 
+track_copy_pattern = re.compile(r"track my order", re.IGNORECASE)
+order_number_pattern = re.compile(r"^[A-Za-z]{2}\d{8}$")
+
 def parse_home_depot(email):
     """Parse home depot tracking numbers."""
     tracking_numbers = []
@@ -27,15 +30,14 @@ def parse_home_depot(email):
         if 'link.order.homedepot.com' not in link:
             continue
 
-        try:
-            tracking_number = element.text
-            isNan = math.isnan(int(tracking_number))
+        match = re.search(order_number_pattern, element.text)
 
-            stripped_number = tracking_number.rstrip()
+        if match:
+            tracking_numbers.append({
+                'link': link,
+                'tracking_number': match.group()
+            })
 
-            if not isNan and stripped_number not in tracking_numbers:
-                tracking_numbers.append(stripped_number)
-        except:
-            pass
 
+    _LOGGER.error({ "tracking_numbers" : tracking_numbers})
     return tracking_numbers

custom_components/email/parsers/thriftbooks.py

@@ -0,0 +1,43 @@
+import logging
+import re
+import math
+
+from bs4 import BeautifulSoup
+from ..const import EMAIL_ATTR_BODY
+
+
+_LOGGER = logging.getLogger(__name__)
+ATTR_THRIFT_BOOKS = 'thrift_books'
+EMAIL_DOMAIN_THRIFT_BOOKS = 'thriftbooks'
+
+track_copy_pattern = re.compile(r"track my package", re.IGNORECASE)
+order_number_pattern = re.compile(r"Order #:\s+(\d+)")
+
+def parse_thrift_books(email):
+    """Parse thrift books tracking numbers."""
+    tracking_numbers = []
+
+    soup = BeautifulSoup(email[EMAIL_ATTR_BODY], 'html.parser')
+    elements = soup.find_all('a')
+
+    for element in elements:
+        link = element.get('href')
+
+        if not link:
+            continue
+
+        if 'spmailtechno' not in link:
+            continue
+
+        try:
+            if re.search(track_copy_pattern, element.text):
+              match = re.search(order_number_pattern, email[EMAIL_ATTR_BODY])
+              if match:
+                tracking_numbers.append({
+                  'link': link,
+                  'tracking_number': match.group(1)
+                })
+        except:
+            pass
+
+    return tracking_numbers

custom_components/email/sensor.py

@@ -61,6 +61,7 @@
 from .parsers.sony import ATTR_SONY, EMAIL_DOMAIN_SONY, parse_sony
 from .parsers.sylvane import ATTR_SYLVANE, EMAIL_DOMAIN_SYLVANE, parse_sylvane
 from .parsers.adafruit import ATTR_ADAFRUIT, EMAIL_DOMAIN_ADAFRUIT, parse_adafruit
+from .parsers.thriftbooks import ATTR_THRIFT_BOOKS, EMAIL_DOMAIN_THRIFT_BOOKS, parse_thrift_books
 
 from .parsers.generic import ATTR_GENERIC, EMAIL_DOMAIN_GENERIC, parse_generic
 
@@ -110,7 +111,7 @@
     (ATTR_SONY, EMAIL_DOMAIN_SONY, parse_sony),
     (ATTR_SYLVANE, EMAIL_DOMAIN_SYLVANE, parse_sylvane),
     (ATTR_ADAFRUIT, EMAIL_DOMAIN_ADAFRUIT, parse_adafruit),
-
+    (ATTR_THRIFT_BOOKS, EMAIL_DOMAIN_THRIFT_BOOKS, parse_thrift_books),
     (ATTR_GENERIC, EMAIL_DOMAIN_GENERIC, parse_generic),
 ]
 
@@ -234,7 +235,7 @@ def find_carrier(tracking_number, email_domain):
     return {
         'tracking_number': tracking_number,
         'carrier': carrier,
-        'origin': email_domain,
+        'origin': email_domain or carrier,
         'link': f'{link}{tracking_number}',
     }