{{SERVER_NAME}}
Channel ID
{{CHANNEL_ID}}
@@ -1283,10 +1338,6 @@
Total Message Participants
{{MESSAGE_PARTICIPANTS}}
-
{{SD}}
Transcript Timezone
- {{TIMEZONE}}
-
+ {{DISPLAY}}
-
- {{USERNAME}}
{{DISCRIMINATOR}}
{{BOT}}
+
+
", self.content) output = [] if "http://" in content or "https://" in content and "](" not in content: for word in content.replace("
", "
").split(): - if word.startswith("<") and word.endswith(">"): + + if "http" not in word: + output.append(word) + continue + + if "<" in word and ">" in word: pattern = r"<https?:\/\/(.*)>" - url = re.search(pattern, word).group(1) - url = f'https://{url}' - output.append(url) + match_url = re.search(pattern, word).group(1) + url = f'https://{match_url}' + word = word.replace("https://" + match_url, url) + word = word.replace("http://" + match_url, url) + output.append(remove_silent_link(word, match_url)) elif "https://" in word: - pattern = r"https://[^\s>\"*]*" + pattern = r"https://[^\s>`\"*]*" word_link = re.search(pattern, word).group() if word_link.endswith(")"): output.append(word) @@ -284,7 +298,7 @@ def remove_silent_link(url): word = re.sub(pattern, word_full, word) output.append(remove_silent_link(word)) elif "http://" in word: - pattern = r"http://[^\s>\"*]*" + pattern = r"http://[^\s>`\"*]*" word_link = re.search(pattern, word).group() if word_link.endswith(")"): output.append(word) diff --git a/chat_exporter/parse/mention.py b/chat_exporter/parse/mention.py index 9316454..3c0a58b 100644 --- a/chat_exporter/parse/mention.py +++ b/chat_exporter/parse/mention.py @@ -1,6 +1,9 @@ import re from typing import Optional +import pytz +import datetime + from chat_exporter.ext.discord_import import discord bot: Optional[discord.Client] = None @@ -22,6 +25,16 @@ class ParseMention: REGEX_CHANNELS_2 = r"<#([0-9]+)>" REGEX_EMOJIS = r"<a?(:[^\n:]+:)[0-9]+>" REGEX_EMOJIS_2 = r""
+ REGEX_TIME_HOLDER = (
+ [r"<t:([0-9]+):t>", "%H:%M"],
+ [r"<t:([0-9]+):T>", "%T"],
+ [r"<t:([0-9]+):d>", "%d/%m/%Y"],
+ [r"<t:([0-9]+):D>", "%e %B %Y"],
+ [r"<t:([0-9]+):f>", "%e %B %Y %H:%M"],
+ [r"<t:([0-9]+):F>", "%A, %e %B %Y %H:%M"],
+ [r"<t:([0-9]+):R>", "%e %B %Y %H:%M"],
+ [r"<t:([0-9]+)>", "%e %B %Y %H:%M"]
+ )
ESCAPE_LT = "______lt______"
ESCAPE_GT = "______gt______"
@@ -31,17 +44,18 @@ def __init__(self, content, guild):
self.content = content
self.guild = guild
- def flow(self):
- self.escape_mentions()
- self.escape_mentions()
- self.unescape_mentions()
- self.channel_mention()
- self.member_mention()
- self.role_mention()
+ async def flow(self):
+ await self.escape_mentions()
+ await self.escape_mentions()
+ await self.unescape_mentions()
+ await self.channel_mention()
+ await self.member_mention()
+ await self.role_mention()
+ await self.time_mention()
return self.content
- def escape_mentions(self):
+ async def escape_mentions(self):
for match in re.finditer("(%s|%s|%s|%s|%s|%s|%s|%s)"
% (self.REGEX_ROLES, self.REGEX_MEMBERS, self.REGEX_CHANNELS, self.REGEX_EMOJIS,
self.REGEX_ROLES_2, self.REGEX_MEMBERS_2, self.REGEX_CHANNELS_2,
@@ -56,13 +70,13 @@ def escape_mentions(self):
self.content = pre_content + match_content + post_content
- def unescape_mentions(self):
+ async def unescape_mentions(self):
self.content = self.content.replace(self.ESCAPE_LT, "<")
self.content = self.content.replace(self.ESCAPE_GT, ">")
self.content = self.content.replace(self.ESCAPE_AMP, "&")
pass
- def channel_mention(self):
+ async def channel_mention(self):
holder = self.REGEX_CHANNELS, self.REGEX_CHANNELS_2
for regex in holder:
match = re.search(regex, self.content)
@@ -79,7 +93,7 @@ def channel_mention(self):
match = re.search(regex, self.content)
- def role_mention(self):
+ async def role_mention(self):
holder = self.REGEX_ROLES, self.REGEX_ROLES_2
for regex in holder:
match = re.search(regex, self.content)
@@ -100,7 +114,7 @@ def role_mention(self):
match = re.search(regex, self.content)
- def member_mention(self):
+ async def member_mention(self):
holder = self.REGEX_MEMBERS, self.REGEX_MEMBERS_2
for regex in holder:
match = re.search(regex, self.content)
@@ -124,3 +138,25 @@ def member_mention(self):
replacement)
match = re.search(regex, self.content)
+
+ async def time_mention(self):
+ holder = self.REGEX_TIME_HOLDER
+ timezone = pytz.timezone(self.guild.timezone)
+
+ for p in holder:
+ regex, strf = p
+ match = re.search(regex, self.content)
+ while match is not None:
+ time = datetime.datetime.fromtimestamp(int(match.group(1)), timezone)
+ ui_time = time.strftime(strf)
+ tooltip_time = time.strftime("%A, %e %B %Y at %H:%M")
+ original = match.group().replace("<", "<").replace(">", ">")
+ replacement = (
+ f''
+ f'{ui_time}'
+ )
+
+ self.content = self.content.replace(self.content[match.start():match.end()],
+ replacement)
+
+ match = re.search(regex, self.content)
+ 
{{CREATED_AT}} 
{{JOINED_AT}}
+
Member Since
+
-
Account Creation Date
- {{CREATED_AT}}
+ Member ID
+ {{MEMBER_ID}}
Message Count
diff --git a/chat_exporter/html/script/channel_subject.html b/chat_exporter/html/script/channel_subject.html
new file mode 100644
index 0000000..dd31c90
--- /dev/null
+++ b/chat_exporter/html/script/channel_subject.html
@@ -0,0 +1 @@
+This is the {{LIMIT}} of the #{{CHANNEL_NAME}} channel. {{RAW_CHANNEL_TOPIC}}
\ No newline at end of file
diff --git a/chat_exporter/html/script/channel_topic.html b/chat_exporter/html/script/channel_topic.html
new file mode 100644
index 0000000..670915e
--- /dev/null
+++ b/chat_exporter/html/script/channel_topic.html
@@ -0,0 +1 @@
+{{CHANNEL_TOPIC}}
\ No newline at end of file
diff --git a/chat_exporter/parse/markdown.py b/chat_exporter/parse/markdown.py
index c1abaf2..f9a3c7a 100644
--- a/chat_exporter/parse/markdown.py
+++ b/chat_exporter/parse/markdown.py
@@ -1,3 +1,4 @@
+import html
import re
from chat_exporter.ext.emoji_convert import convert_emoji
@@ -225,13 +226,16 @@ def parse_embed_markdown(self):
@staticmethod
def return_to_markdown(content):
- holders = [r"(.*?)", '**%s**'], \
- [r"([^<>]+)", '*%s*'], \
- [r'([^<>]+)', '__%s__'], \
- [r'([^<>]+)', '~~%s~~'], \
- [r'(.*?)
', '> %s'], \
- [r' (.*?)<\/span><\/span>', '||%s||']
+ holders = (
+ [r"(.*?)", '**%s**'],
+ [r"([^<>]+)", '*%s*'],
+ [r'([^<>]+)', '__%s__'],
+ [r'([^<>]+)', '~~%s~~'],
+ [r'(.*?)
', '> %s'],
+ [r' (.*?)<\/span><\/span>', '||%s||'],
+ [r'.*?', '%s']
+ )
for x in holders:
p, r = x
@@ -241,7 +245,7 @@ def return_to_markdown(content):
while match is not None:
affected_text = match.group(1)
content = content.replace(content[match.start():match.end()],
- r % affected_text)
+ r % html.escape(affected_text))
match = re.search(pattern, content)
pattern = re.compile(r'(.*?)')
@@ -260,22 +264,32 @@ def return_to_markdown(content):
return content.lstrip().rstrip()
def https_http_links(self):
- def remove_silent_link(url):
- if url.startswith("<<") and url.endswith(">>"):
- return url[1:-1]
+ def remove_silent_link(url, raw_url=None):
+ pattern = rf"`.*{raw_url}.*`"
+ match = re.search(pattern, self.content)
+
+ if "<" in url and ">" in url and not match:
+ return url.replace("<", "").replace(">", "")
return url
content = re.sub("\n", "", self.content) output = [] if "http://" in content or "https://" in content and "](" not in content: for word in content.replace("
", "
").split(): - if word.startswith("<") and word.endswith(">"): + + if "http" not in word: + output.append(word) + continue + + if "<" in word and ">" in word: pattern = r"<https?:\/\/(.*)>" - url = re.search(pattern, word).group(1) - url = f'https://{url}' - output.append(url) + match_url = re.search(pattern, word).group(1) + url = f'https://{match_url}' + word = word.replace("https://" + match_url, url) + word = word.replace("http://" + match_url, url) + output.append(remove_silent_link(word, match_url)) elif "https://" in word: - pattern = r"https://[^\s>\"*]*" + pattern = r"https://[^\s>`\"*]*" word_link = re.search(pattern, word).group() if word_link.endswith(")"): output.append(word) @@ -284,7 +298,7 @@ def remove_silent_link(url): word = re.sub(pattern, word_full, word) output.append(remove_silent_link(word)) elif "http://" in word: - pattern = r"http://[^\s>\"*]*" + pattern = r"http://[^\s>`\"*]*" word_link = re.search(pattern, word).group() if word_link.endswith(")"): output.append(word) diff --git a/chat_exporter/parse/mention.py b/chat_exporter/parse/mention.py index 9316454..3c0a58b 100644 --- a/chat_exporter/parse/mention.py +++ b/chat_exporter/parse/mention.py @@ -1,6 +1,9 @@ import re from typing import Optional +import pytz +import datetime + from chat_exporter.ext.discord_import import discord bot: Optional[discord.Client] = None @@ -22,6 +25,16 @@ class ParseMention: REGEX_CHANNELS_2 = r"<#([0-9]+)>" REGEX_EMOJIS = r"<a?(:[^\n:]+:)[0-9]+>" REGEX_EMOJIS_2 = r"