From 9d935affd3c837b8607aa84457f241fe124f33d8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Lo=C3=AFc=20Wikle=20DUBARD?= <loic97429@gmail.com>
Date: Tue, 20 Aug 2019 12:14:46 +0200
Subject: [PATCH] shitpostbot insta parser
---
bot.py | 10 +++++++---
useless/shitpostbot5k.py | 35 ++++++++++++++++++++++++++---------
2 files changed, 33 insertions(+), 12 deletions(-)
diff --git a/bot.py b/bot.py
index 8f67e88..bb0027e 100755
--- a/bot.py
+++ b/bot.py
@@ -59,7 +59,7 @@ class Bot(Client):
'!memes <image_name_or_url> ; <texte1> ; <texte2(facultatif)> ... not yet implemented\n' + \
'!ping \n' + \
'!translate <phrase> ; <lang_source> ; <lang_dest>\n' + \
- '!shitpostbot5000 [status|on|off|random] ... ne pas utiliser PLEASE\n' + \
+ '!shitpostbot5000 [status|on|off|random|timer] ... ne pas utiliser PLEASE\n' + \
'!about -> vas-y test-moi !\n'
return help_text
elif '!translate' in texte:
@@ -102,8 +102,12 @@ class Bot(Client):
elif texte == '!shitpostbot5000 off':
if thread_id in Bot.shitpostbot:
Bot.shitpostbot[thread_id][0].set_off()
- elif texte == '!shitpostbot5000 random':
- self.sendLocalImage(Shitpostbot5000.random(), thread_id=thread_id, thread_type=thread_type)
+ elif '!shitpostbot5000 random' in texte:
+ texte = texte.replace('!shitpostbot5000 random', '')
+ if texte == '':
+ return Shitpostbot5000.random()
+ else:
+ return Shitpostbot5000.random(texte)
# pour rigoler
elif '!memes templates' in texte:
diff --git a/useless/shitpostbot5k.py b/useless/shitpostbot5k.py
index c8eea54..2ebe45d 100755
--- a/useless/shitpostbot5k.py
+++ b/useless/shitpostbot5k.py
@@ -3,7 +3,12 @@ from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
import urllib.request
+import urllib.parse
+import urllib.error
import datetime
+import ssl
+import json
+import random
class Shitpostbot5000(object):
@@ -39,15 +44,27 @@ class Shitpostbot5000(object):
return self.out
@classmethod
- def random(self):
- html = urlopen('https://www.facebook.com/pg/shitpostbot5k/photos')
- bs = BeautifulSoup(html, 'html.parser')
- images = bs.find_all('img', {'src': re.compile('.jpg')})
- images2 = bs.find_all('image_src')
- for image in images:
- print(image["src"])
- return None
+ def getlinks(self, hashtag, url):
+ html = urllib.request.urlopen(url, context=self.ctx).read()
+ soup = BeautifulSoup(html, 'html.parser')
+ script = soup.find('script', text=lambda t: t.startswith('window._sharedData'))
+ page_json = script.text.split(' = ', 1)[1].rstrip(';')
+ data = json.loads(page_json)
+ print('Scraping links with #' + hashtag + "...........")
+ links = []
+ for post in data['entry_data']['TagPage'][0]['graphql']['hashtag']['edge_hashtag_to_media']['edges']:
+ image_src = post['node']['thumbnail_resources'][1]['src']
+ links.append(image_src)
+ return links
+
+ @classmethod
+ def random(self, hashtag=random.choice(['shitpostmeme', 'shitpost', 'shitposts', 'memes', 'climbingmemes', 'rockclimbingmemes', 'climbingmemesaredank', 'climbingmemesofinstagram'])):
+ self.ctx = ssl.create_default_context()
+ self.ctx.check_hostname = False
+ self.ctx.verify_mode = ssl.CERT_NONE
+ return random.choice(self.getlinks(hashtag, 'https://www.instagram.com/explore/tags/' + hashtag + '/'))
+
if __name__ == "__main__":
img = Shitpostbot5000()
- print(img.get_latest())
+ print(Shitpostbot5000.random('shitposts'))
--
GitLab