forked from LC044/WeChatMsg
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
9 changed files
with
155 additions
and
49 deletions.
There are no files selected for viewing
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,91 @@ | ||
import os | ||
import xml.etree.ElementTree as ET | ||
|
||
import requests | ||
|
||
root_path = './data/emoji/' | ||
if not os.path.exists('./data'): | ||
os.mkdir('./data') | ||
if not os.path.exists(root_path): | ||
os.mkdir(root_path) | ||
|
||
|
||
def get_image_format(header): | ||
# 定义图片格式的 magic numbers | ||
image_formats = { | ||
b'\xFF\xD8\xFF': 'jpeg', | ||
b'\x89\x50\x4E\x47\x0D\x0A\x1A\x0A': 'png', | ||
b'\x47\x49\x46': 'gif', | ||
b'\x42\x4D': 'bmp', | ||
# 添加其他图片格式的 magic numbers | ||
} | ||
# 判断文件的图片格式 | ||
for magic_number, image_format in image_formats.items(): | ||
if header.startswith(magic_number): | ||
return image_format | ||
# 如果无法识别格式,返回 None | ||
return None | ||
|
||
|
||
def parser_xml(xml_string): | ||
# Parse the XML string | ||
root = ET.fromstring(xml_string) | ||
emoji = root.find('./emoji') | ||
# Accessing attributes of the 'emoji' element | ||
fromusername = emoji.get('fromusername') | ||
tousername = emoji.get('tousername') | ||
md5 = emoji.get('md5') | ||
cdnurl = emoji.get('cdnurl') | ||
encrypturl = emoji.get('encrypturl') | ||
thumburl = emoji.get('thumburl') | ||
externurl = emoji.get('externurl') | ||
width = emoji.get('width') | ||
height = emoji.get('height') | ||
return { | ||
'width': width, | ||
'height': height, | ||
'cdnurl': cdnurl, | ||
'thumburl': thumburl if thumburl else cdnurl, | ||
'md5': md5 | ||
} | ||
|
||
|
||
def download(url, output_dir, name, thumb=False): | ||
resp = requests.get(url) | ||
byte = resp.content | ||
image_format = get_image_format(byte[:8]) | ||
if image_format: | ||
if thumb: | ||
output_path = os.path.join(output_dir, 'th_' + name + '.' + image_format) | ||
else: | ||
output_path = os.path.join(output_dir, name + '.' + image_format) | ||
else: | ||
output_path = os.path.join(output_dir, name) | ||
with open(output_path, 'wb') as f: | ||
f.write(resp.content) | ||
return output_path | ||
|
||
|
||
def get_emoji(xml_string, thumb=True) -> str: | ||
emoji_info = parser_xml(xml_string) | ||
md5 = emoji_info['md5'] | ||
image_format = ['.png', '.gif', '.jpeg'] | ||
for f in image_format: | ||
prefix = 'th_' if thumb else '' | ||
file_path = os.path.join(root_path, prefix + md5 + f) | ||
if os.path.exists(file_path): | ||
return file_path | ||
url = emoji_info['thumburl'] if thumb else emoji_info['cdnurl'] | ||
print("下载表情包ing:", url) | ||
return download(url, root_path, md5, thumb) | ||
|
||
|
||
if __name__ == '__main__': | ||
xml_string = '<msg><emoji fromusername = "wxid_0o18ef858vnu22" tousername = "wxid_27hqbq7vx5hf22" type="2" idbuffer="media:0_0" md5="71ce49ed3ce9e57e43e07f802983bf45" len = "352588" productid="com.tencent.xin.emoticon.person.stiker_1678703862259eb01f2ef4a313" androidmd5="71ce49ed3ce9e57e43e07f802983bf45" androidlen="352588" s60v3md5 = "71ce49ed3ce9e57e43e07f802983bf45" s60v3len="352588" s60v5md5 = "71ce49ed3ce9e57e43e07f802983bf45" s60v5len="352588" cdnurl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=71ce49ed3ce9e57e43e07f802983bf45&filekey=30350201010421301f020201060402535a041071ce49ed3ce9e57e43e07f802983bf45020305614c040d00000004627466730000000132&hy=SZ&storeid=263ffa00b000720d03274c5820000010600004f50535a1ca0c950b64287022&bizid=1023" designerid = "" thumburl = "http://mmbiz.qpic.cn/mmemoticon/ajNVdqHZLLDSKTMRgM8agiadpFhKz9IJ3cD5Ra2sTROibOaShdt3D4z6PfE92WkjQY/0" encrypturl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=cbaae1d847aac6389652b65562bacaa2&filekey=30350201010421301f020201060402535a0410cbaae1d847aac6389652b65562bacaa20203056150040d00000004627466730000000132&hy=SZ&storeid=263ffa00b0008d8223274c5820000010600004f50535a17b82910b64764739&bizid=1023" aeskey= "7051ab2a34442dec63434832463f45ce" externurl = "http://wxapp.tc.qq.com/262/20304/stodownload?m=960f68693454dfa64b9966ca5d70dbd3&filekey=30340201010420301e020201060402535a0410960f68693454dfa64b9966ca5d70dbd3020221a0040d00000004627466730000000132&hy=SZ&storeid=26423dbe3000793a8720e40de0000010600004f50535a1d40c950b71be0a50&bizid=1023" externmd5 = "41895664fc5a77878e2155fc96209a19" width= "240" height= "240" tpurl= "" tpauthkey= "" attachedtext= "" attachedtextcolor= "" lensid= "" emojiattr= "" linkid= "" desc= "ChEKB2RlZmF1bHQSBuWNlee6rw==" ></emoji> </msg>' | ||
res1 = parser_xml(xml_string) | ||
print(res1, res1['md5']) | ||
# download(res1['cdnurl'], "./data/emoji/", res1['md5']) | ||
# download(res1['thumburl'], "./data/emoji/", res1['md5'], True) | ||
print(get_emoji(xml_string, True)) | ||
print(get_emoji(xml_string, False)) | ||
# http://vweixinf.tc.qq.com/110/20403/stodownload?m=3a4d439aba02dce4834b2c54e9f15597&filekey=3043020101042f302d02016e0402534804203361346434333961626130326463653438333462326335346539663135353937020213f0040d00000004627466730000000131&hy=SH&storeid=323032313037323030373236313130303039653236646365316535316534383236386234306230303030303036653033303034666233&ef=3&bizid=1022 |
Oops, something went wrong.