From 850a46aea1db06046118110b5a80df25ac823d41 Mon Sep 17 00:00:00 2001 From: Ben Busby Date: Fri, 10 Apr 2020 14:52:27 -0600 Subject: [PATCH] Refactored routes, added filter class for returned results, added dockerignore --- .dockerignore | 1 + app/filter.py | 111 +++++++++++++++++++++++++++++++++++++++ rhyme.py => app/rhyme.py | 1 + app/routes.py | 110 +++----------------------------------- 4 files changed, 121 insertions(+), 102 deletions(-) create mode 100644 .dockerignore create mode 100644 app/filter.py rename rhyme.py => app/rhyme.py (99%) diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000..2d2ecd6 --- /dev/null +++ b/.dockerignore @@ -0,0 +1 @@ +.git/ diff --git a/app/filter.py b/app/filter.py new file mode 100644 index 0000000..7e845d3 --- /dev/null +++ b/app/filter.py @@ -0,0 +1,111 @@ +from bs4 import BeautifulSoup +import re +import urllib.parse as urlparse +from urllib.parse import parse_qs + +AD_CLASS = 'ZINbbc' +SPONS_CLASS = 'D1fz0e' + + +def reskin(page, dark_mode=False): + # Aesthetic only re-skinning + page = page.replace('>G<', '>Sh<') + pattern = re.compile('4285f4|ea4335|fbcc05|34a853|fbbc05', re.IGNORECASE) + page = pattern.sub('685e79', page) + if dark_mode: + page = page.replace('fff', '000').replace('202124', 'ddd').replace('1967D2', '3b85ea') + + return page + + +def gen_query(q, args, near_city=None): + # Use :past(hour/day/week/month/year) if available + # example search "new restaurants :past month" + tbs = '' + # if 'tbs' in request.args: + # tbs = '&tbs=' + request.args.get('tbs') + # q = q.replace(q.split(':past', 1)[-1], '').replace(':past', '') + if ':past' in q: + time_range = str.strip(q.split(':past', 1)[-1]) + tbs = '&tbs=qdr:' + str.lower(time_range[0]) + + # Ensure search query is parsable + q = urlparse.quote(q) + + # Pass along type of results (news, images, books, etc) + tbm = '' + if 'tbm' in args: + tbm = '&tbm=' + args.get('tbm') + + # Get results page start value (10 per page, ie page 2 start val = 20) + start = '' + if 'start' in args: + start = '&start=' + args.get('start') + + # Grab city from config, if available + near = '' + if near_city: + near = '&near=' + urlparse.quote(near_city) + + return q + tbs + tbm + start + near + + +def cook(soup, user_agent, nojs=False, dark_mode=False): + # Remove all ads (TODO: Ad specific div classes probably change over time, look into a more generic method) + main_divs = soup.find('div', {'id': 'main'}) + if main_divs is not None: + ad_divs = main_divs.findAll('div', {'class': AD_CLASS}, recursive=False) + sponsored_divs = main_divs.findAll('div', {'class': SPONS_CLASS}, recursive=False) + for div in ad_divs + sponsored_divs: + div.decompose() + + # Remove unnecessary button(s) + for button in soup.find_all('button'): + button.decompose() + + # Remove svg logos + for svg in soup.find_all('svg'): + svg.decompose() + + # Update logo + logo = soup.find('a', {'class': 'l'}) + if logo is not None and ('Android' in user_agent or 'iPhone' in user_agent): + logo.insert(0, 'Shoogle') + logo['style'] = 'display: flex;justify-content: center;align-items: center;color: #685e79;font-size: 18px;' + + # Replace hrefs with only the intended destination (no "utm" type tags) + for a in soup.find_all('a', href=True): + href = a['href'] + if '/advanced_search' in href: + a.decompose() + continue + + if 'url?q=' in href: + # Strip unneeded arguments + href = urlparse.urlparse(href) + href = parse_qs(href.query)['q'][0] + + # Add no-js option + if nojs: + nojs_link = soup.new_tag('a') + nojs_link['href'] = '/window?location=' + href + nojs_link['style'] = 'display:block;width:100%;' + nojs_link.string = 'NoJS Link: ' + nojs_link['href'] + a.append(BeautifulSoup('

', 'html.parser')) + a.append(nojs_link) + + # Set up dark mode if active + if dark_mode: + soup.find('html')['style'] = 'scrollbar-color: #333 #111;' + for input_element in soup.findAll('input'): + input_element['style'] = 'color:#fff;' + + # Ensure no extra scripts passed through + try: + for script in soup('script'): + script.decompose() + soup.find('div', id='sfooter').decompose() + except Exception: + pass + + return soup diff --git a/rhyme.py b/app/rhyme.py similarity index 99% rename from rhyme.py rename to app/rhyme.py index ba21cb7..23b9137 100644 --- a/rhyme.py +++ b/app/rhyme.py @@ -8,6 +8,7 @@ random.seed(time.time()) ph = Phyme() + def get_rhyme(word): # Get all rhymes and merge to one list (normally separated by syllable count) rhymes = ph.get_perfect_rhymes(word) diff --git a/app/routes.py b/app/routes.py index 03fa69f..6f225e6 100644 --- a/app/routes.py +++ b/app/routes.py @@ -1,14 +1,11 @@ -from app import app +from app import app, rhyme, filter from bs4 import BeautifulSoup -from flask import request, redirect, Response, render_template +from flask import request, redirect, render_template +from io import BytesIO import json import os import pycurl -import rhyme -import re import urllib.parse as urlparse -from urllib.parse import parse_qs -from io import BytesIO APP_ROOT = os.path.dirname(os.path.abspath(__file__)) STATIC_FOLDER = os.path.join(APP_ROOT, 'static') @@ -31,7 +28,6 @@ def get_ua(user_agent): def send_request(curl_url, ua): - request_header = [] response_header = [] b_obj = BytesIO() @@ -59,105 +55,15 @@ def search(): if q is None or len(q) <= 0: return render_template('error.html') - # Use :past(hour/day/week/month/year) if available - # example search "new restaurants :past month" - tbs = '' - # if 'tbs' in request.args: - # tbs = '&tbs=' + request.args.get('tbs') - # q = q.replace(q.split(':past', 1)[-1], '').replace(':past', '') - if ':past' in q: - time_range = str.strip(q.split(':past', 1)[-1]) - tbs = '&tbs=qdr:' + str.lower(time_range[0]) - - # Ensure search query is parsable - q = urlparse.quote(q) - - # Pass along type of results (news, images, books, etc) - tbm = '' - if 'tbm' in request.args: - tbm = '&tbm=' + request.args.get('tbm') - - # Get results page start value (10 per page, ie page 2 start val = 20) - start = '' - if 'start' in request.args: - start = '&start=' + request.args.get('start') - - # Grab city from config, if available - near = '' - if 'near' in user_config: - near = '&near=' + urlparse.quote(user_config['near']) - + full_query = filter.gen_query(q, request.args) user_agent = request.headers.get('User-Agent') - full_query = q + tbs + tbm + start + near - - get_body = send_request(SEARCH_URL + full_query, get_ua(user_agent)) - - # Aesthetic only re-skinning dark_mode = 'dark' in user_config and user_config['dark'] - get_body = get_body.replace('>G<', '>Sh<') - pattern = re.compile('4285f4|ea4335|fbcc05|34a853|fbbc05', re.IGNORECASE) - get_body = pattern.sub('685e79', get_body) - if dark_mode: - get_body = get_body.replace('fff', '000').replace('202124', 'ddd').replace('1967D2', '3b85ea') + nojs = 'nojs' in user_config and user_config['nojs'] - soup = BeautifulSoup(get_body, 'html.parser') + get_body = filter.reskin(send_request( + SEARCH_URL + full_query, get_ua(user_agent)), dark_mode=dark_mode) - # Remove all ads (TODO: Ad specific div classes probably change over time, look into a more generic method) - main_divs = soup.find('div', {'id': 'main'}) - if main_divs is not None: - ad_divs = main_divs.findAll('div', {'class': 'ZINbbc'}, recursive=False) - sponsored_divs = main_divs.findAll('div', {'class': 'D1fz0e'}, recursive=False) - for div in ad_divs + sponsored_divs: - div.decompose() - - # Remove unnecessary button(s) - for button in soup.find_all('button'): - button.decompose() - - # Remove svg logos - for svg in soup.find_all('svg'): - svg.decompose() - - # Update logo - logo = soup.find('a', {'class': 'l'}) - if logo is not None and ('Android' in user_agent or 'iPhone' in user_agent): - logo.insert(0, 'Shoogle') - logo['style'] = 'display: flex;justify-content: center;align-items: center;color: #685e79;font-size: 18px;' - - # Replace hrefs with only the intended destination (no "utm" type tags) - for a in soup.find_all('a', href=True): - href = a['href'] - if '/advanced_search' in href: - a.decompose() - continue - - if 'url?q=' in href: - # Strip unneeded arguments - href = urlparse.urlparse(href) - href = parse_qs(href.query)['q'][0] - - # Add no-js option - if 'nojs' in user_config and user_config['nojs']: - nojs_link = soup.new_tag('a') - nojs_link['href'] = '/window?location=' + href - nojs_link['style'] = 'display:block;width:100%;' - nojs_link.string = 'NoJS Link: ' + nojs_link['href'] - a.append(BeautifulSoup('

', 'html.parser')) - a.append(nojs_link) - - # Set up dark mode if active - if dark_mode: - soup.find('html')['style'] = 'scrollbar-color: #333 #111;' - for input_element in soup.findAll('input'): - input_element['style'] = 'color:#fff;' - - # Ensure no extra scripts passed through - try: - for script in soup('script'): - script.decompose() - soup.find('div', id='sfooter').decompose() - except Exception: - pass + soup = filter.cook(BeautifulSoup(get_body, 'html.parser'), user_agent, nojs=nojs, dark_mode=dark_mode) return render_template('display.html', query=urlparse.unquote(q), response=soup)