Last active
May 22, 2021 07:29
-
-
Save pcchou/992c424d695894b4fc44d3c4b5995171 to your computer and use it in GitHub Desktop.
Facebook post parsing bs4 class (2017)
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
from bs4 import BeautifulSoup as Soup | |
from requests import get as GET, post as POST | |
parse_cookie = lambda cookies: dict(map(lambda x: x.split('='), map(lambda x: x.replace(' ', ''), cookies.split(';')))) | |
COOKIE_STRING = "" | |
REQARGS = {'cookies': parse_cookie(COOKIE_STRING), 'headers': {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'}} | |
class Post: | |
def react(self, name): | |
picker = Soup(GET('https://mbasic.facebook.com/reactions/picker/?ft_id={}'.format(self.sid), **REQARGS).text, 'html5lib') | |
try: | |
action_url = picker.find(text=name).findParents('td')[1].find('a').attrs['href'] | |
except AttributeError: | |
return False | |
else: | |
s = GET('https://mbasic.facebook.com' + action_url, **REQARGS, allow_redirects=False) | |
return 302 == s.status_code | |
def comment(self, text="", sticker=None): | |
form = self.s.strong.findParent(id="m_story_permalink_view").find('form') | |
action_url = form.attrs['action'] | |
data = {'fb_dtsg': form.find(attrs={'name': "fb_dtsg"}).attrs['value']} | |
if sticker: | |
data['sticker_id'] = sticker | |
if text: | |
data['comment_text'] = text | |
POST('https://mbasic.facebook.com' + action_url, **REQARGS, data=data) | |
def __init__(self, sid, uid): | |
self.sid = sid | |
self.uid = uid | |
s = self.s = Soup(GET('https://mbasic.facebook.com/story.php?story_fbid={}&id={}'.format(sid, uid), **REQARGS).text, 'html5lib') | |
try: | |
self.contents = '\n'.join(map(str, list(s.strong.findParent(id="m_story_permalink_view").find('p').strings))) | |
except: | |
self.contents = "" | |
try: | |
self.contents += '\n'.join(map(str, list(s.strong.findParent(id="m_story_permalink_view").find('div', attrs={'style': 'font-size:24px;font-weight:300;line-height:1.2;display:inline'}).strings))) | |
except: | |
pass | |
try: | |
h = ''.join(map(str, s.strong.findParent('h3').strings)) | |
except AttributeError: | |
self.type = 'P' | |
else: | |
if "分享了" in h and "貼文" in h: | |
self.type = 'S' | |
elif "分享了" in h and ("相片" in h or "影片" in h): | |
self.type = 'SP' | |
else: | |
self.type = 'M' | |
q = Post(sid="3931951836874187", uid="134395566629852") | |
q.contents |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment