calvin.erfmann/WhatsApp-Chat-Exporter
1
0
Fork 0
mirror of https://github.com/KnugiHK/WhatsApp-Chat-Exporter.git synced 2026-05-31 13:33:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'dev'

Browse Source
This commit is contained in:
KnugiHK
2021-12-28 19:26:02 +08:00
parent d85c91fbdc 0dddb63c5e
commit fb5e4d5421
8 changed files with 205 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -12,6 +12,7 @@ A customizable Android and iPhone Whatsapp database parser that will give you th
First, install the exporter by: First, install the exporter by:
```shell ```shell
pip install whatsapp-chat-exporter pip install whatsapp-chat-exporter
pip install whatsapp-chat-exporter[android_backup] & :: Optional, if you want it to support decrypting Android WhatsApp backup.
``` ```
Then, create a working directory in somewhere you want Then, create a working directory in somewhere you want
```shell ```shell
@@ -56,7 +57,6 @@ Do an iPhone Backup with iTunes first.
If you want to work on an encrypted iPhone Backup, you should install iphone_backup_decrypt from [KnugiHK/iphone_backup_decrypt](https://github.com/KnugiHK/iphone_backup_decrypt) before you run the extract_iphone_media.py. If you want to work on an encrypted iPhone Backup, you should install iphone_backup_decrypt from [KnugiHK/iphone_backup_decrypt](https://github.com/KnugiHK/iphone_backup_decrypt) before you run the extract_iphone_media.py.
```sh ```sh
pip install biplist pycryptodome & :: Optional, since the pip will install these dependencies automatically.
pip install git+https://github.com/KnugiHK/iphone_backup_decrypt pip install git+https://github.com/KnugiHK/iphone_backup_decrypt
``` ```
### Extracting ### Extracting
@@ -88,13 +88,15 @@ Options:
-m MEDIA, --media=MEDIA -m MEDIA, --media=MEDIA
Path to WhatsApp media folder Path to WhatsApp media folder
-b BACKUP, --backup=BACKUP -b BACKUP, --backup=BACKUP
Path to iPhone/Android (must be used together with -k) Path to Android (must be used together with -k)/iPhone
WhatsApp backup WhatsApp backup
-o OUTPUT, --output=OUTPUT -o OUTPUT, --output=OUTPUT
Output to specific directory Output to specific directory
-j, --json Save the result to a single JSON file -j, --json Save the result to a single JSON file
-d DB, --db=DB Path to database file -d DB, --db=DB Path to database file
-k KEY, --key=KEY Path to key file -k KEY, --key=KEY Path to key file
-t TEMPLATE, --template=TEMPLATE
Path to custom HTML template
``` ```
# To do # To do

20
Whatsapp_Chat_Exporter/__main__.py
View File

@@ -1,5 +1,6 @@
from .__init__ import __version__ from .__init__ import __version__
from Whatsapp_Chat_Exporter import extract, extract_iphone, extract_iphone_media from Whatsapp_Chat_Exporter import extract, extract_iphone
from Whatsapp_Chat_Exporter import extract_iphone_media
from optparse import OptionParser from optparse import OptionParser
import os import os
import sqlite3 import sqlite3
@@ -40,7 +41,8 @@ def main():
"--backup", "--backup",
dest="backup", dest="backup",
default=None, default=None,
help="Path to Android (must be used together with -k)/iPhone WhatsApp backup") help="Path to Android (must be used together "
"with -k)/iPhone WhatsApp backup")
parser.add_option( parser.add_option(
"-o", "-o",
"--output", "--output",
@@ -67,6 +69,12 @@ def main():
default=None, default=None,
help="Path to key file" help="Path to key file"
) )
parser.add_option(
"-t",
"--template",
dest="template",
default=None,
help="Path to custom HTML template")
(options, args) = parser.parse_args() (options, args) = parser.parse_args()
if options.android and options.iphone: if options.android and options.iphone:
@@ -94,8 +102,10 @@ def main():
print("Decryption key specified, decrypting WhatsApp backup...") print("Decryption key specified, decrypting WhatsApp backup...")
key = open(options.key, "rb").read() key = open(options.key, "rb").read()
db = open(options.backup, "rb").read() db = open(options.backup, "rb").read()
if not extract.decrypt_backup(db, key, msg_db): is_crypt14 = False if "crypt12" in options.backup else True
print("Dependencies of decrypt_backup are not present. For details, see README.md") if not extract.decrypt_backup(db, key, msg_db, is_crypt14):
print("Dependencies of decrypt_backup are not "
"present. For details, see README.md")
return False return False
if options.wa is None: if options.wa is None:
contact_db = "wa.db" contact_db = "wa.db"
@@ -137,7 +147,7 @@ def main():
messages(db, data) messages(db, data)
media(db, data, options.media) media(db, data, options.media)
vcard(db, data) vcard(db, data)
create_html(data, options.output) create_html(data, options.output, options.template)
if not os.path.isdir(f"{options.output}/{options.media}"): if not os.path.isdir(f"{options.output}/{options.media}"):
shutil.move(options.media, f"{options.output}/") shutil.move(options.media, f"{options.output}/")

91
Whatsapp_Chat_Exporter/extract.py
View File

@@ -8,6 +8,9 @@ import requests
import shutil import shutil
import re import re
import pkgutil import pkgutil
from pathlib import Path
from bleach import clean as sanitize
from markupsafe import Markup
from datetime import datetime from datetime import datetime
from mimetypes import MimeTypes from mimetypes import MimeTypes
try: try:
@@ -19,6 +22,10 @@ else:
support_backup = True support_backup = True
def sanitize_except(html):
return Markup(sanitize(html, tags=["br"]))
def determine_day(last, current): def determine_day(last, current):
last = datetime.fromtimestamp(last).date() last = datetime.fromtimestamp(last).date()
current = datetime.fromtimestamp(current).date() current = datetime.fromtimestamp(current).date()
@@ -28,20 +35,27 @@ def determine_day(last, current):
return current return current
def decrypt_backup(database, key, output): def decrypt_backup(database, key, output, crypt14=True):
if not support_backup: if not support_backup:
return False return False
if len(key) != 158: if len(key) != 158:
raise ValueError("The key file must be 158 bytes") raise ValueError("The key file must be 158 bytes")
if len(database) < 191:
raise ValueError("The database file must be at least 191 bytes")
t1 = key[30:62] t1 = key[30:62]
t2 = database[15:47] if crypt14:
if len(database) < 191:
raise ValueError("The crypt14 file must be at least 191 bytes")
t2 = database[15:47]
iv = database[67:83]
db_ciphertext = database[191:]
else:
if len(database) < 67:
raise ValueError("The crypt12 file must be at least 67 bytes")
t2 = database[3:35]
iv = database[51:67]
db_ciphertext = database[67:-20]
if t1 != t2: if t1 != t2:
raise ValueError("The signature of key file and backup file mismatch") raise ValueError("The signature of key file and backup file mismatch")
iv = database[67:83]
db_ciphertext = database[191:]
main_key = key[126:] main_key = key[126:]
cipher = AES.new(main_key, AES.MODE_GCM, iv) cipher = AES.new(main_key, AES.MODE_GCM, iv)
db_compressed = cipher.decrypt(db_ciphertext) db_compressed = cipher.decrypt(db_ciphertext)
@@ -105,7 +119,9 @@ def messages(db, data):
"timestamp": content[3]/1000, "timestamp": content[3]/1000,
"time": datetime.fromtimestamp(content[3]/1000).strftime("%H:%M"), "time": datetime.fromtimestamp(content[3]/1000).strftime("%H:%M"),
"media": False, "media": False,
"key_id": content[13] "key_id": content[13],
"meta": False,
"data": None
} }
if "-" in content[0] and content[2] == 0: if "-" in content[0] and content[2] == 0:
name = None name = None
@@ -140,8 +156,9 @@ def messages(db, data):
try: try:
int(content[4]) int(content[4])
except ValueError: except ValueError:
msg = "{The group name changed to "f"{content[4]}"" }" msg = f"The group name changed to {content[4]}"
data[content[0]]["messages"][content[1]]["data"] = msg data[content[0]]["messages"][content[1]]["data"] = msg
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
del data[content[0]]["messages"][content[1]] del data[content[0]]["messages"][content[1]]
else: else:
@@ -160,15 +177,16 @@ def messages(db, data):
name_left = data[content[8]]["name"] name_left = data[content[8]]["name"]
else: else:
name_left = content[8].split('@')[0] name_left = content[8].split('@')[0]
msg = "{"f"{name_left}"f" added {name_right or 'You'}""}" msg = f"{name_left} added {name_right or 'You'}"
else: else:
msg = "{"f"Added {name_right or 'You'}""}" msg = f"Added {name_right or 'You'}"
elif b"\xac\xed\x00\x05\x74\x00" in thumb_image: elif b"\xac\xed\x00\x05\x74\x00" in thumb_image:
# Changed number # Changed number
original = content[8].split('@')[0] original = content[8].split('@')[0]
changed = thumb_image[7:].decode().split('@')[0] changed = thumb_image[7:].decode().split('@')[0]
msg = "{"f"{original} changed to {changed}""}" msg = f"{original} changed to {changed}"
data[content[0]]["messages"][content[1]]["data"] = msg data[content[0]]["messages"][content[1]]["data"] = msg
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
if content[4] is None: if content[4] is None:
del data[content[0]]["messages"][content[1]] del data[content[0]]["messages"][content[1]]
@@ -180,20 +198,34 @@ def messages(db, data):
else: else:
if content[2] == 1: if content[2] == 1:
if content[5] == 5 and content[6] == 7: if content[5] == 5 and content[6] == 7:
msg = "{Message deleted}" msg = "Message deleted"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
if content[9] == "5": if content[9] == "5":
msg = "{ Location shared: "f"{content[10], content[11]}"" }" msg = f"Location shared: {content[10], content[11]}"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
msg = content[4] msg = content[4]
if msg is not None:
if "\r\n" in msg:
msg = msg.replace("\r\n", "<br>")
if "\n" in msg:
msg = msg.replace("\n", "<br>")
else: else:
if content[5] == 0 and content[6] == 7: if content[5] == 0 and content[6] == 7:
msg = "{Message deleted}" msg = "Message deleted"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
if content[9] == "5": if content[9] == "5":
msg = "{ Location shared: "f"{content[10], content[11]}"" }" msg = f"Location shared: {content[10], content[11]}"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
msg = content[4] msg = content[4]
if msg is not None:
if "\r\n" in msg:
msg = msg.replace("\r\n", "<br>")
if "\n" in msg:
msg = msg.replace("\n", "<br>")
data[content[0]]["messages"][content[1]]["data"] = msg data[content[0]]["messages"][content[1]]["data"] = msg
@@ -201,8 +233,7 @@ def messages(db, data):
if i % 1000 == 0: if i % 1000 == 0:
print(f"Gathering messages...({i}/{total_row_number})", end="\r") print(f"Gathering messages...({i}/{total_row_number})", end="\r")
content = c.fetchone() content = c.fetchone()
print( print(f"Gathering messages...({total_row_number}/{total_row_number})", end="\r")
f"Gathering messages...({total_row_number}/{total_row_number})", end="\r")
def media(db, data, media_folder): def media(db, data, media_folder):
@@ -248,8 +279,9 @@ def media(db, data, media_folder):
# data[content[0]]["messages"][content[1]]["media"] = True # data[content[0]]["messages"][content[1]]["media"] = True
# data[content[0]]["messages"][content[1]]["mime"] = "media" # data[content[0]]["messages"][content[1]]["mime"] = "media"
# else: # else:
data[content[0]]["messages"][content[1]]["data"] = "{The media is missing}" data[content[0]]["messages"][content[1]]["data"] = "The media is missing"
data[content[0]]["messages"][content[1]]["mime"] = "media" data[content[0]]["messages"][content[1]]["mime"] = "media"
data[content[0]]["messages"][content[1]]["meta"] = True
i += 1 i += 1
if i % 100 == 0: if i % 100 == 0:
print(f"Gathering media...({i}/{total_row_number})", end="\r") print(f"Gathering media...({i}/{total_row_number})", end="\r")
@@ -272,27 +304,34 @@ def vcard(db, data):
total_row_number = len(rows) total_row_number = len(rows)
print(f"\nGathering vCards...(0/{total_row_number})", end="\r") print(f"\nGathering vCards...(0/{total_row_number})", end="\r")
base = "WhatsApp/vCards" base = "WhatsApp/vCards"
if not os.path.isdir(base):
Path(base).mkdir(parents=True, exist_ok=True)
for index, row in enumerate(rows): for index, row in enumerate(rows):
if not os.path.isdir(base):
os.mkdir(base)
file_name = "".join(x for x in row[3] if x.isalnum()) file_name = "".join(x for x in row[3] if x.isalnum())
file_path = f"{base}/{file_name}.vcf" file_path = f"{base}/{file_name}.vcf"
if not os.path.isfile(file_path): if not os.path.isfile(file_path):
with open(file_path, "w", encoding="utf-8") as f: with open(file_path, "w", encoding="utf-8") as f:
f.write(row[2]) f.write(row[2])
data[row[1]]["messages"][row[0]]["data"] = row[3] + \ data[row[1]]["messages"][row[0]]["data"] = row[3] + \
"{ The vCard file cannot be displayed here, however it " \ "The vCard file cannot be displayed here, " \
"should be located at " + file_path + "}" f"however it should be located at {file_path}"
data[row[1]]["messages"][row[0]]["mime"] = "text/x-vcard" data[row[1]]["messages"][row[0]]["mime"] = "text/x-vcard"
data[row[1]]["messages"][row[0]]["meta"] = True
print(f"Gathering vCards...({index + 1}/{total_row_number})", end="\r") print(f"Gathering vCards...({index + 1}/{total_row_number})", end="\r")
def create_html(data, output_folder): def create_html(data, output_folder, template=None):
templateLoader = jinja2.FileSystemLoader(searchpath=os.path.dirname(__file__)) if template is None:
template_dir = os.path.dirname(__file__)
template_file = "whatsapp.html"
else:
template_dir = os.path.dirname(template)
template_file = os.path.basename(template)
templateLoader = jinja2.FileSystemLoader(searchpath=template_dir)
templateEnv = jinja2.Environment(loader=templateLoader) templateEnv = jinja2.Environment(loader=templateLoader)
templateEnv.globals.update(determine_day=determine_day) templateEnv.globals.update(determine_day=determine_day)
TEMPLATE_FILE = "whatsapp.html" templateEnv.filters['sanitize_except'] = sanitize_except
template = templateEnv.get_template(TEMPLATE_FILE) template = templateEnv.get_template(template_file)
total_row_number = len(data) total_row_number = len(data)
print(f"\nCreating HTML...(0/{total_row_number})", end="\r") print(f"\nCreating HTML...(0/{total_row_number})", end="\r")

58
Whatsapp_Chat_Exporter/extract_iphone.py
View File

@@ -7,12 +7,19 @@ import os
import requests import requests
import shutil import shutil
import pkgutil import pkgutil
from pathlib import Path
from bleach import clean as sanitize
from markupsafe import Markup
from datetime import datetime from datetime import datetime
from mimetypes import MimeTypes from mimetypes import MimeTypes
APPLE_TIME = datetime.timestamp(datetime(2001, 1, 1)) APPLE_TIME = datetime.timestamp(datetime(2001, 1, 1))
def sanitize_except(html):
return Markup(sanitize(html, tags=["br"]))
def determine_day(last, current): def determine_day(last, current):
last = datetime.fromtimestamp(last).date() last = datetime.fromtimestamp(last).date()
current = datetime.fromtimestamp(current).date() current = datetime.fromtimestamp(current).date()
@@ -62,7 +69,9 @@ def messages(db, data):
"time": datetime.fromtimestamp(ts).strftime("%H:%M"), "time": datetime.fromtimestamp(ts).strftime("%H:%M"),
"media": False, "media": False,
"reply": None, "reply": None,
"caption": None "caption": None,
"meta": False,
"data": None
} }
if "-" in content[0] and content[2] == 0: if "-" in content[0] and content[2] == 0:
name = None name = None
@@ -87,8 +96,9 @@ def messages(db, data):
try: try:
int(content[4]) int(content[4])
except ValueError: except ValueError:
msg = "{The group name changed to "f"{content[4]}"" }" msg = f"The group name changed to {content[4]}"
data[content[0]]["messages"][content[1]]["data"] = msg data[content[0]]["messages"][content[1]]["data"] = msg
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
del data[content[0]]["messages"][content[1]] del data[content[0]]["messages"][content[1]]
else: else:
@@ -99,14 +109,26 @@ def messages(db, data):
# real message # real message
if content[2] == 1: if content[2] == 1:
if content[5] == 14: if content[5] == 14:
msg = "{Message deleted}" msg = "Message deleted"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
msg = content[4] msg = content[4]
if msg is not None:
if "\r\n" in msg:
msg = msg.replace("\r\n", "<br>")
if "\n" in msg:
msg = msg.replace("\n", "<br>")
else: else:
if content[5] == 14: if content[5] == 14:
msg = "{Message deleted}" msg = "Message deleted"
data[content[0]]["messages"][content[1]]["meta"] = True
else: else:
msg = content[4] msg = content[4]
if msg is not None:
if "\r\n" in msg:
msg = msg.replace("\r\n", "<br>")
if "\n" in msg:
msg = msg.replace("\n", "<br>")
data[content[0]]["messages"][content[1]]["data"] = msg data[content[0]]["messages"][content[1]]["data"] = msg
i += 1 i += 1
if i % 1000 == 0: if i % 1000 == 0:
@@ -138,7 +160,7 @@ def media(db, data, media_folder):
content = c.fetchone() content = c.fetchone()
mime = MimeTypes() mime = MimeTypes()
while content is not None: while content is not None:
file_path = f"Message/{content[2]}" file_path = f"{media_folder}/{content[2]}"
data[content[0]]["messages"][content[1]]["media"] = True data[content[0]]["messages"][content[1]]["media"] = True
if os.path.isfile(file_path): if os.path.isfile(file_path):
@@ -161,8 +183,9 @@ def media(db, data, media_folder):
# data[content[0]]["messages"][content[1]]["data"] = "{The media is missing}" # data[content[0]]["messages"][content[1]]["data"] = "{The media is missing}"
# data[content[0]]["messages"][content[1]]["mime"] = "media" # data[content[0]]["messages"][content[1]]["mime"] = "media"
# else: # else:
data[content[0]]["messages"][content[1]]["data"] = "{The media is missing}" data[content[0]]["messages"][content[1]]["data"] = "The media is missing"
data[content[0]]["messages"][content[1]]["mime"] = "media" data[content[0]]["messages"][content[1]]["mime"] = "media"
data[content[0]]["messages"][content[1]]["meta"] = True
if content[6] is not None: if content[6] is not None:
data[content[0]]["messages"][content[1]]["caption"] = content[6] data[content[0]]["messages"][content[1]]["caption"] = content[6]
i += 1 i += 1
@@ -190,28 +213,35 @@ def vcard(db, data):
total_row_number = len(rows) total_row_number = len(rows)
print(f"\nGathering vCards...(0/{total_row_number})", end="\r") print(f"\nGathering vCards...(0/{total_row_number})", end="\r")
base = "Message/vCards" base = "Message/vCards"
if not os.path.isdir(base):
Path(base).mkdir(parents=True, exist_ok=True)
for index, row in enumerate(rows): for index, row in enumerate(rows):
if not os.path.isdir(base):
os.mkdir(base)
file_name = "".join(x for x in row[3] if x.isalnum()) file_name = "".join(x for x in row[3] if x.isalnum())
file_path = f"{base}/{file_name[:200]}.vcf" file_path = f"{base}/{file_name[:200]}.vcf"
if not os.path.isfile(file_path): if not os.path.isfile(file_path):
with open(file_path, "w", encoding="utf-8") as f: with open(file_path, "w", encoding="utf-8") as f:
f.write(row[4]) f.write(row[4])
data[row[2]]["messages"][row[1]]["data"] = row[3] + \ data[row[2]]["messages"][row[1]]["data"] = row[3] + \
"{ The vCard file cannot be displayed here, however it " \ "The vCard file cannot be displayed here, " \
"should be located at " + file_path + "}" f"however it should be located at {file_path}"
data[row[2]]["messages"][row[1]]["mime"] = "text/x-vcard" data[row[2]]["messages"][row[1]]["mime"] = "text/x-vcard"
data[row[2]]["messages"][row[1]]["media"] = True data[row[2]]["messages"][row[1]]["media"] = True
data[row[2]]["messages"][row[1]]["meta"] = True
print(f"Gathering vCards...({index + 1}/{total_row_number})", end="\r") print(f"Gathering vCards...({index + 1}/{total_row_number})", end="\r")
def create_html(data, output_folder): def create_html(data, output_folder, template=None):
templateLoader = jinja2.FileSystemLoader(searchpath=os.path.dirname(__file__)) if template is None:
template_dir = os.path.dirname(__file__)
template_file = "whatsapp.html"
else:
template_dir = os.path.dirname(template)
template_file = os.path.basename(template)
templateLoader = jinja2.FileSystemLoader(searchpath=template_dir)
templateEnv = jinja2.Environment(loader=templateLoader) templateEnv = jinja2.Environment(loader=templateLoader)
templateEnv.globals.update(determine_day=determine_day) templateEnv.globals.update(determine_day=determine_day)
TEMPLATE_FILE = "whatsapp.html" templateEnv.filters['sanitize_except'] = sanitize_except
template = templateEnv.get_template(TEMPLATE_FILE) template = templateEnv.get_template(template_file)
total_row_number = len(data) total_row_number = len(data)
print(f"\nCreating HTML...(0/{total_row_number})", end="\r") print(f"\nCreating HTML...(0/{total_row_number})", end="\r")

17
Whatsapp_Chat_Exporter/extract_iphone_media.py
View File

@@ -6,21 +6,24 @@ import os
import getpass import getpass
try: try:
from iphone_backup_decrypt import EncryptedBackup, RelativePath from iphone_backup_decrypt import EncryptedBackup, RelativePath
except: except ModuleNotFoundError:
support_encrypted = False support_encrypted = False
else: else:
support_encrypted = True support_encrypted = True
def extract_encrypted(base_dir, password): def extract_encrypted(base_dir, password):
backup = EncryptedBackup(backup_directory=base_dir, passphrase=password) backup = EncryptedBackup(backup_directory=base_dir, passphrase=password)
print("Decrypting WhatsApp database...") print("Decrypting WhatsApp database...")
backup.extract_file(relative_path=RelativePath.WHATSAPP_MESSAGES, output_filename="7c7fba66680ef796b916b067077cc246adacf01d") backup.extract_file(relative_path=RelativePath.WHATSAPP_MESSAGES,
backup.extract_file(relative_path=RelativePath.WHATSAPP_CONTACTS, output_filename="ContactsV2.sqlite") output_filename="7c7fba66680ef796b916b067077cc246adacf01d")
backup.extract_file(relative_path=RelativePath.WHATSAPP_CONTACTS,
output_filename="ContactsV2.sqlite")
data = backup.execute_sql("""SELECT count() data = backup.execute_sql("""SELECT count()
FROM Files FROM Files
WHERE relativePath WHERE relativePath
LIKE 'Message/Media/%'""" LIKE 'Message/Media/%'"""
) )
total_row_number = data[0][0] total_row_number = data[0][0]
print(f"Gathering media...(0/{total_row_number})", end="\r") print(f"Gathering media...(0/{total_row_number})", end="\r")
data = backup.execute_sql("""SELECT fileID, data = backup.execute_sql("""SELECT fileID,
@@ -30,7 +33,7 @@ def extract_encrypted(base_dir, password):
FROM Files FROM Files
WHERE relativePath WHERE relativePath
LIKE 'Message/Media/%'""" LIKE 'Message/Media/%'"""
) )
if not os.path.isdir("Message"): if not os.path.isdir("Message"):
os.mkdir("Message") os.mkdir("Message")
if not os.path.isdir("Message/Media"): if not os.path.isdir("Message/Media"):
@@ -56,6 +59,7 @@ def extract_encrypted(base_dir, password):
print(f"Gathering media...({i}/{total_row_number})", end="\r") print(f"Gathering media...({i}/{total_row_number})", end="\r")
print(f"Gathering media...({total_row_number}/{total_row_number})", end="\r") print(f"Gathering media...({total_row_number}/{total_row_number})", end="\r")
def is_encrypted(base_dir): def is_encrypted(base_dir):
with sqlite3.connect(f"{base_dir}/Manifest.db") as f: with sqlite3.connect(f"{base_dir}/Manifest.db") as f:
c = f.cursor() c = f.cursor()
@@ -68,6 +72,7 @@ def is_encrypted(base_dir):
else: else:
return False return False
def extract_media(base_dir): def extract_media(base_dir):
if is_encrypted(base_dir): if is_encrypted(base_dir):
if not support_encrypted: if not support_encrypted:
@@ -81,7 +86,7 @@ def extract_media(base_dir):
wts_db = os.path.join(base_dir, "7c/7c7fba66680ef796b916b067077cc246adacf01d") wts_db = os.path.join(base_dir, "7c/7c7fba66680ef796b916b067077cc246adacf01d")
if not os.path.isfile(wts_db): if not os.path.isfile(wts_db):
print("WhatsApp database not found.") print("WhatsApp database not found.")
sys.exit(1) exit()
else: else:
shutil.copyfile(wts_db, "7c7fba66680ef796b916b067077cc246adacf01d") shutil.copyfile(wts_db, "7c7fba66680ef796b916b067077cc246adacf01d")
with sqlite3.connect(f"{base_dir}/Manifest.db") as manifest: with sqlite3.connect(f"{base_dir}/Manifest.db") as manifest:

92
Whatsapp_Chat_Exporter/whatsapp.html
View File

@@ -72,29 +72,37 @@
<a href="#{{msg.reply}}" style="color: #168acc;">"{{ msg.quoted_data or 'media' }}"</a> <a href="#{{msg.reply}}" style="color: #168acc;">"{{ msg.quoted_data or 'media' }}"</a>
</div> </div>
{% endif %} {% endif %}
{% if msg.media == false %} {% if msg.meta == true or msg.media == false and msg.data is none %}
{% filter escape %}{{ msg.data or "{This message is not supported yet}" | replace('\n', '<br>') }}{% endfilter %} <div style="text-align: center;" class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar">
<p>{{ msg.data or 'This message is not supported' }}</p>
</div>
{% else %} {% else %}
{% if "image/" in msg.mime %} {% if msg.media == false %}
<a href="{{ msg.data }}"><img src="{{ msg.data }}" /></a> {{ msg.data | sanitize_except() }}
{% elif "audio/" in msg.mime %}
<audio controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</audio>
{% elif "video/" in msg.mime %}
<video controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</video>
{% elif "/" in msg.mime %}
{The file cannot be displayed here, however it should be located at {{ msg.data }}}
{% else %} {% else %}
{% filter escape %}{{ msg.data }}{% endfilter %} {% if "image/" in msg.mime %}
<a href="{{ msg.data }}"><img src="{{ msg.data }}" /></a>
{% elif "audio/" in msg.mime %}
<audio controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</audio>
{% elif "video/" in msg.mime %}
<video controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</video>
{% elif "/" in msg.mime %}
<div style="text-align: center;" class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar">
<p>The file cannot be displayed here, however it should be located at {{ msg.data }}</p>
</div>
{% else %}
{% filter escape %}{{ msg.data }}{% endfilter %}
{% endif %}
{% if msg.caption is not none %}
<br>
{{ msg.caption }}
{% endif %}
{% endif %} {% endif %}
{% if msg.caption is not none %}
<br>
{{ msg.caption }}
{% endif %} {% endif %}
{% endif %}
</div> </div>
</div> </div>
<div class="w3-col m2 l2" style="padding-left: 10px"><img src="{{ my_avatar }}" onerror="this.style.display='none'"></div> <div class="w3-col m2 l2" style="padding-left: 10px"><img src="{{ my_avatar }}" onerror="this.style.display='none'"></div>
@@ -120,27 +128,35 @@
<a href="#{{msg.reply}}" style="color: #168acc;">"{{ msg.quoted_data or 'media' }}"</a> <a href="#{{msg.reply}}" style="color: #168acc;">"{{ msg.quoted_data or 'media' }}"</a>
</div> </div>
{% endif %} {% endif %}
{% if msg.media == false %} {% if msg.meta == true or msg.media == false and msg.data is none %}
{% filter escape %}{{ msg.data or "{This message is not supported yet}" }}{% endfilter %} <div style="text-align: center;" class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar">
<p>{{ msg.data or 'This message is not supported' }}</p>
</div>
{% else %} {% else %}
{% if "image/" in msg.mime %} {% if msg.media == false %}
<a href="{{ msg.data }}"><img src="{{ msg.data }}" /></a> {{ msg.data | sanitize_except() }}
{% elif "audio/" in msg.mime %}
<audio controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</audio>
{% elif "video/" in msg.mime %}
<video controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</video>
{% elif "/" in msg.mime %}
{The file cannot be displayed here, however it should be located at {{ msg.data }}}
{% else %} {% else %}
{% filter escape %}{{ msg.data }}{% endfilter %} {% if "image/" in msg.mime %}
{% endif %} <a href="{{ msg.data }}"><img src="{{ msg.data }}" /></a>
{% if msg.caption is not none %} {% elif "audio/" in msg.mime %}
<br> <audio controls="controls" autobuffer="autobuffer">
{{ msg.caption }} <source src="{{ msg.data }}" />
</audio>
{% elif "video/" in msg.mime %}
<video controls="controls" autobuffer="autobuffer">
<source src="{{ msg.data }}" />
</video>
{% elif "/" in msg.mime %}
<div style="text-align: center;" class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar">
<p>The file cannot be displayed here, however it should be located at {{ msg.data }}</p>
</div>
{% else %}
{% filter escape %}{{ msg.data }}{% endfilter %}
{% endif %}
{% if msg.caption is not none %}
<br>
{{ msg.caption }}
{% endif %}
{% endif %} {% endif %}
{% endif %} {% endif %}
</div> </div>

10
setup.py
View File

@@ -12,12 +12,13 @@ setuptools.setup(
version=version, version=version,
author="KnugiHK", author="KnugiHK",
author_email="info@knugi.com", author_email="info@knugi.com",
description="A Whatsapp database parser that will give you the history of your Whatsapp conversations in HTML and JSON.", description="A Whatsapp database parser that will give you the "
"history of your Whatsapp conversations in HTML and JSON.",
long_description=long_description, long_description=long_description,
long_description_content_type="text/markdown", long_description_content_type="text/markdown",
url="https://github.com/KnugiHK/Whatsapp-Chat-Exporter", url="https://github.com/KnugiHK/Whatsapp-Chat-Exporter",
packages=setuptools.find_packages(), packages=setuptools.find_packages(),
package_data = { package_data={
'': ['whatsapp.html'] '': ['whatsapp.html']
}, },
classifiers=[ classifiers=[
@@ -36,9 +37,10 @@ setuptools.setup(
], ],
python_requires='>=3.7', python_requires='>=3.7',
install_requires=[ install_requires=[
'jinja2' 'jinja2',
'bleach'
], ],
extras_require = { extras_require={
'android_backup': ["pycryptodome"] 'android_backup': ["pycryptodome"]
}, },
entry_points={ entry_points={