Reply to thread

Message

<blockquote data-quote="Mikee" data-source="post: 418124" data-attributes="member: 76567">[CODE]#Instagram Thief#scape the top page every hour, check every photo&nbsp; on the top page, compare each of their likes#download the photo with the highest votes. Do this every hour, also keep track of the tags that they used#upload the photo i downloaded, to my account and put the same tags in them#after 24 hours, record which photos got most likes, and record their tags in a JSON File.#do this every dayfrom bs4 import BeautifulSoupimport urllib3class InstagramPhoto(object):&nbsp; &nbsp; top_page_text = None&nbsp;&nbsp; &nbsp; def __init__(self):&nbsp; &nbsp; &nbsp; &nbsp; self.data = None&nbsp; &nbsp; @staticmethod&nbsp; &nbsp; def get_top_page():&nbsp; &nbsp; &nbsp; &nbsp; try:&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; http = urllib3.PoolManager()&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; r = http.request(&quot;GET&quot;, &quot;https://www.instagram.com/explore/&quot;)&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; print (r.data.decode('utf-8'))&nbsp; &nbsp; &nbsp; &nbsp; except Exception as e:&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; print(&quot;\nAn Error With UrlLib3 Has Occured...\n\n&quot;,e,&quot;\n&quot;)&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; return&nbsp; &nbsp; '''&nbsp; &nbsp; def find_top_photo(self):&nbsp; &nbsp; &nbsp; &nbsp; try:&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; if self.top_page_text is None:&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; raise Exception&nbsp; &nbsp; &nbsp; &nbsp; except Exception:&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; print(&quot;Woops, The Top Instagram Page Was Not Yet Accessed !&quot;)&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; return&nbsp; &nbsp; &nbsp; &nbsp; text = &quot;&lt;div class = _mck9w _gvoze _f2mse&gt; hey we have some text&quot;&nbsp; &nbsp; &nbsp; &nbsp; soup = BeautifulSoup(self.top_page_text, &quot;html.parser&quot;)&nbsp; &nbsp; &nbsp; &nbsp; print(soup.prettify())&nbsp; &nbsp; &nbsp;&nbsp; '''&nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp;&nbsp; def main():&nbsp; &nbsp; get_top_page = InstagramPhoto.get_top_page()&nbsp; &nbsp; '''&nbsp; &nbsp; new_photo = InstagramPhoto() #creating an instance of the new_photo that we wanna get&nbsp; &nbsp; new_photo.find_top_photo()&nbsp; &nbsp; '''if __name__ == &quot;__main__&quot;:&nbsp; &nbsp; main()[/CODE]The print doesn't return the full source. It literally skips the &lt;body&gt; which is what I need. Does anyone know how I can get around this?Thanks.I've tried using the requests module but it literally does the same thing.</blockquote>

[QUOTE="Mikee, post: 418124, member: 76567"] [CODE] #Instagram Thief #scape the top page every hour, check every photo on the top page, compare each of their likes #download the photo with the highest votes. Do this every hour, also keep track of the tags that they used #upload the photo i downloaded, to my account and put the same tags in them #after 24 hours, record which photos got most likes, and record their tags in a JSON File. #do this every day from bs4 import BeautifulSoup import urllib3 class InstagramPhoto(object): top_page_text = None def __init__(self): self.data = None @staticmethod def get_top_page(): try: http = urllib3.PoolManager() r = http.request("GET", "https://www.instagram.com/explore/") print (r.data.decode('utf-8')) except Exception as e: print("\nAn Error With UrlLib3 Has Occured...\n\n",e,"\n") return ''' def find_top_photo(self): try: if self.top_page_text is None: raise Exception except Exception: print("Woops, The Top Instagram Page Was Not Yet Accessed !") return text = "<div class = _mck9w _gvoze _f2mse> hey we have some text" soup = BeautifulSoup(self.top_page_text, "html.parser") print(soup.prettify()) ''' def main(): get_top_page = InstagramPhoto.get_top_page() ''' new_photo = InstagramPhoto() #creating an instance of the new_photo that we wanna get new_photo.find_top_photo() ''' if __name__ == "__main__": main() [/CODE] The print doesn't return the full source. It literally skips the <body> which is what I need. Does anyone know how I can get around this? Thanks. I've tried using the requests module but it literally does the same thing. [/QUOTE]

Verification

Reply to thread

Connect with us

Newest members