diff options
| author | la-ninpre <leobrekalini@gmail.com> | 2020-11-26 23:56:43 +0300 |
|---|---|---|
| committer | la-ninpre <leobrekalini@gmail.com> | 2020-11-26 23:58:27 +0300 |
| commit | 48d5e233fda099780ab6705505f4154b0cefa11b (patch) | |
| tree | e0475e16416e54f12564e230a16de08ac2506553 | |
| parent | e4f357e68c6e2a40ecdd914d84e66dceb0e86cfd (diff) | |
| download | tg2md-48d5e233fda099780ab6705505f4154b0cefa11b.tar.gz tg2md-48d5e233fda099780ab6705505f4154b0cefa11b.zip | |
make a rename
notice repo name also changed
| -rw-r--r-- | README.md | 3 | ||||
| -rw-r--r-- | tg2md.py (renamed from parse.py) | 9 |
2 files changed, 10 insertions, 2 deletions
@@ -1,4 +1,4 @@ -# telegram2md +# tg2md This script parses output from Telegram channel and converts each post to jekyll-applicable post in markdown. @@ -37,6 +37,7 @@ and `files`, you should change `photo_dir` and `media_dir` variables. ## todo's +- use argparse module instead of crap - replies - single/muliple tags - forwarded posts @@ -54,6 +54,10 @@ def text_format(string, fmt): return output def text_link_format(text, link): + # convert telegram links to anchors + # this implies that telegram links are pointing to the same channel + if link.startswith('https://t.me/c/'): + link = '#' + link.split('/')[-1] link_fmt = '[{text}]({href})' link_fmt = link_fmt.format(text=text.strip(), href=link) link_fmt += '\n' * text.count('\n') * text.endswith('\n') @@ -73,7 +77,10 @@ def parse_text_object(obj): return text_link_format(obj_text, obj['href']) elif obj_type == 'link' or obj_type == 'email': - post_link = '<{href}>'.format(href=obj_text.strip()) + link = obj_text.strip() + link = 'https://' * (obj_type == 'link') * \ + (1 - link.startswith('https://')) + link + post_link = '<{href}>'.format(href=link) return post_link elif obj_type == 'phone': |
