From 9beff69b1704726246ff5ba7f0772d63328c5502 Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Sat, 5 Aug 2023 20:07:07 -0300
Subject: [PATCH 1/8] delete iframe from tweets and display as text

---
 README.md |   4 +-
 app.py    | 152 +++++++++++++++++++++++++++++++++++++++++-------------
 2 files changed, 119 insertions(+), 37 deletions(-)

diff --git a/README.md b/README.md
index c99102f..8205dfe 100644
--- a/README.md
+++ b/README.md
@@ -15,7 +15,7 @@ Tool that displays multiple archived tweets on Wayback Machine to avoid opening
 
 ## Features
 
-- 30 embedded tweets per page
+- 30 tweets per page
 - Filtering by only deleted tweets
 
 ## Development
@@ -54,7 +54,7 @@ Streamlit will be served at http://localhost:8501
 - [x] Changelog
 - [ ] Prevent duplicate URLs
 - [ ] Range size defined by user
-- [ ] Hide Twitter header banner (iframe)
 - [ ] `parse_links` exception
+- [ ] Add current page to page title
 
 ## [Changelog](/CHANGELOG.md)
diff --git a/app.py b/app.py
index 3fa25ff..d02569e 100644
--- a/app.py
+++ b/app.py
@@ -2,8 +2,10 @@
 import datetime
 import streamlit as st
 import streamlit.components.v1 as components
+import json
+import re
 
-__version__ = '0.1.4'
+__version__ = '0.2'
 
 year = datetime.datetime.now().year
 
@@ -20,7 +22,7 @@
 
         Tool that displays multiple archived tweets on Wayback Machine to avoid opening each link manually.
 
-        - 30 embedded tweets per page
+        - 30 tweets per page
         - Filtering by only deleted tweets
 
         This tool is experimental, please feel free to send your [feedbacks](https://github.com/claromes/waybacktweets/issues).
@@ -76,29 +78,68 @@ def scroll_into_view():
 
     components.html(js, width=0, height=0)
 
-@st.cache_data(ttl=1800, show_spinner=False)
 def embed(tweet):
-    api = 'https://publish.twitter.com/oembed?url={}'.format(tweet)
-    response = requests.get(api)
+    try:
+        url = 'https://publish.twitter.com/oembed?url={}'.format(tweet)
+        response = requests.get(url, timeout=1)
+
+        regex = r'<blockquote class="twitter-tweet"><p[^>]*>(.*?)<\/p>.*?&mdash; (.*?)<\/a>'
+        regex_author = r'^(.*?)\s*\('
+
+        if response.status_code == 200 or response.status_code == 302:
+            status_code = response.status_code
+            html = response.json()['html']
+            author_name = response.json()['author_name']
+
+            matches_html = re.findall(regex, html, re.DOTALL)
+
+            tweet_content = []
+            user_info = []
+            is_RT = []
+
+            for match in matches_html:
+                tweet_content_match = re.sub(r'<a[^>]*>|<\/a>', '', match[0].strip())
+                user_info_match = re.sub(r'<a[^>]*>|<\/a>', '', match[1].strip())
+                user_info_match = user_info_match.replace(')', '), ')
+
+                match_author = re.search(regex_author, user_info_match)
+                author_tweet = match_author.group(1)
+
+                if tweet_content_match:
+                    tweet_content.append(tweet_content_match)
+                if user_info_match:
+                    user_info.append(user_info_match)
+
+                    is_RT_match = False
+                    if author_name != author_tweet:
+                        is_RT_match = True
+
+                    is_RT.append(is_RT_match)
+
+            return status_code, tweet_content, user_info, is_RT
+        else:
+            return False
+    except requests.exceptions.Timeout:
+        st.error('Connection to web.archive.org timed out.')
+
 
-    if response.status_code == 200 or response.status_code == 304:
-        return response.json()['html']
-    else:
-        return None
 
 @st.cache_data(ttl=1800, show_spinner=False)
 def tweets_count(handle):
     url = 'https://web.archive.org/cdx/search/cdx?url=https://twitter.com/{}/status/*&output=json'.format(handle)
-    response = requests.get(url)
-    if response.status_code == 200:
-        data = response.json()
-        if data and len(data) > 1:
-            total_tweets = len(data) - 1
-            return total_tweets
-        else:
-            return 0
-    else:
-        return None
+    try:
+        response = requests.get(url, timeout=5)
+
+        if response.status_code == 200:
+            data = response.json()
+            if data and len(data) > 1:
+                total_tweets = len(data) - 1
+                return total_tweets
+            else:
+                return 0
+    except requests.exceptions.Timeout:
+        st.error('Connection to web.archive.org timed out.')
+
 
 @st.cache_data(ttl=1800, show_spinner=False)
 def query_api(handle, limit, offset):
@@ -107,11 +148,13 @@ def query_api(handle, limit, offset):
         st.stop()
 
     url = 'https://web.archive.org/cdx/search/cdx?url=https://twitter.com/{}/status/*&output=json&limit={}&offset={}'.format(handle, limit, offset)
-    response = requests.get(url)
-    if response.status_code == 200:
-        return response.json()
-    else:
-        return None
+    try:
+        response = requests.get(url, timeout=1)
+
+        if response.status_code == 200 or response.status_code == 304:
+            return response.json()
+    except requests.exceptions.Timeout:
+        st.error('Connection to web.archive.org timed out.')
 
 @st.cache_data(ttl=1800, show_spinner=False)
 def parse_links(links):
@@ -206,22 +249,61 @@ def next_page():
                         if not only_deleted:
                             attr(i)
 
-                            if tweet == None:
-                                st.error('Tweet has been deleted.')
-                                components.iframe(src=link, width=700, height=1000, scrolling=True)
-                                st.divider()
-                            else:
-                                components.html(tweet, width=700, height=1000, scrolling=True)
-                                st.divider()
+                            if tweet:
+                                status_code = tweet[0]
+                                tweet_content = tweet[1]
+                                user_info = tweet[2]
+                                is_RT = tweet[3]
+
+                                if mimetype[i] == 'application/json':
+                                    if is_RT[0] == True:
+                                        st.info('*Retweet*')
+                                    st.write(tweet_content[0])
+                                    st.write(user_info[0])
+
+                                    st.divider()
+                                if mimetype[i] == 'text/html':
+                                    if is_RT[0] == True:
+                                        st.info('*Retweet*')
+                                    st.write(tweet_content[0])
+                                    st.write(user_info[0])
+
+                                    st.divider()
+                            elif not tweet:
+                                if mimetype[i] == 'application/json':
+                                    st.error('Tweet has been deleted.')
+                                    response = requests.get(link, timeout=5)
+                                    json_data = response.json()
+
+                                    st.json(json_data, expanded=False)
+
+                                    st.divider()
+                                if mimetype[i] == 'text/html':
+                                    st.error('Tweet has been deleted.')
+                                    st.info('IFRAME')
+                                    st.write(link)
+
+                                    st.divider()
 
                         if only_deleted:
-                            if tweet == None:
+                            if not tweet:
                                 return_none_count += 1
                                 attr(i)
 
-                                st.error('Tweet has been deleted.')
-                                components.iframe(src=link, width=700, height=1000, scrolling=True)
-                                st.divider()
+                                if mimetype[i] == 'application/json':
+                                    st.error('Tweet has been deleted.')
+                                    response = requests.get(link, timeout=5)
+                                    json_data = response.json()
+
+                                    st.json(json_data, expanded=False)
+
+                                    st.divider()
+                                if mimetype[i] == 'text/html':
+                                    st.error('Tweet has been deleted.')
+                                    st.info('IFRAME')
+                                    st.write(link)
+
+                                    st.divider()
 
                             progress.write('{} URLs have been captured in the range {}-{}'.format(return_none_count, start_index, end_index))
 

From 09581f0df68aff027ee870d940b2f773ba891a1e Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Sat, 5 Aug 2023 22:01:31 -0300
Subject: [PATCH 2/8] add progress bar, refactoring

---
 README.md |   4 +
 app.py    | 218 +++++++++++++++++++++++++++---------------------------
 2 files changed, 115 insertions(+), 107 deletions(-)

diff --git a/README.md b/README.md
index 8205dfe..c7cf677 100644
--- a/README.md
+++ b/README.md
@@ -42,6 +42,8 @@ Streamlit will be served at http://localhost:8501
 - [x] `only_deleted` checkbox selected for handles without deleted tweets
 - [x] Pagination: set session variable on first click
 - [x] Pagination: scroll to top
+- [ ] `IndexError`
+- [ ] Timeout error
 
 ## Roadmap
 
@@ -56,5 +58,7 @@ Streamlit will be served at http://localhost:8501
 - [ ] Range size defined by user
 - [ ] `parse_links` exception
 - [ ] Add current page to page title
+- [ ] Parse MIME type `warc/revisit`
+- [ ] Filter by period/datetime
 
 ## [Changelog](/CHANGELOG.md)
diff --git a/app.py b/app.py
index d02569e..299dddc 100644
--- a/app.py
+++ b/app.py
@@ -4,6 +4,7 @@
 import streamlit.components.v1 as components
 import json
 import re
+from bs4 import BeautifulSoup
 
 __version__ = '0.2'
 
@@ -39,6 +40,16 @@
     header[data-testid="stHeader"] {
         opacity: 0.5;
     }
+    div[data-testid="stDecoration"] {
+        visibility: hidden;
+        height: 0%;
+        position: fixed;
+    }
+    div[data-testid="stStatusWidget"] {
+        visibility: hidden;
+        height: 0%;
+        position: fixed;
+    }
 </style>
 '''
 
@@ -99,6 +110,8 @@ def embed(tweet):
 
             for match in matches_html:
                 tweet_content_match = re.sub(r'<a[^>]*>|<\/a>', '', match[0].strip())
+                tweet_content_match = tweet_content_match.replace('<br>', '\n')
+
                 user_info_match = re.sub(r'<a[^>]*>|<\/a>', '', match[1].strip())
                 user_info_match = user_info_match.replace(')', '), ')
 
@@ -120,7 +133,7 @@ def embed(tweet):
         else:
             return False
     except requests.exceptions.Timeout:
-        st.error('Connection to web.archive.org timed out.')
+        st.error('Connection to publish.twitter.com timed out.')
 
 
 
@@ -128,7 +141,7 @@ def embed(tweet):
 def tweets_count(handle):
     url = 'https://web.archive.org/cdx/search/cdx?url=https://twitter.com/{}/status/*&output=json'.format(handle)
     try:
-        response = requests.get(url, timeout=5)
+        response = requests.get(url, timeout=10)
 
         if response.status_code == 200:
             data = response.json()
@@ -191,6 +204,8 @@ def attr(i):
 handle = st.text_input('username', placeholder='username', label_visibility='collapsed')
 query = st.button('Query', type='primary', use_container_width=True)
 
+bar = st.progress(0)
+
 if query or handle:
     if handle != st.session_state.current_handle:
         st.session_state.offset = 0
@@ -207,130 +222,119 @@ def attr(i):
     only_deleted = st.checkbox('Only deleted tweets')
 
     try:
-        with st.spinner(''):
-            progress = st.empty()
-            links = query_api(handle, tweets_per_page, st.session_state.offset)
-            parsed_links = parse_links(links)[0]
-            tweet_links = parse_links(links)[1]
-            mimetype = parse_links(links)[2]
-            timestamp = parse_links(links)[3]
+        progress = st.empty()
+        links = query_api(handle, tweets_per_page, st.session_state.offset)
+        parsed_links = parse_links(links)[0]
+        tweet_links = parse_links(links)[1]
+        mimetype = parse_links(links)[2]
+        timestamp = parse_links(links)[3]
+
+
+        if links:
+            st.divider()
+
+            st.session_state.current_handle = handle
+            st.session_state.current_query = query
+
+            return_none_count = 0
+
+            def prev_page():
+                st.session_state.offset -= tweets_per_page
 
+                #scroll to top config
+                st.session_state.update_component += 1
+                scroll_into_view()
+
+            def next_page():
+                st.session_state.offset += tweets_per_page
+
+                #scroll to top config
+                st.session_state.update_component += 1
+                scroll_into_view()
+
+            def display_tweet():
+                if is_RT[0] == True:
+                    st.info('*Retweet*')
+                st.write(tweet_content[0])
+                st.write(user_info[0])
 
-            if links:
                 st.divider()
 
-                st.session_state.current_handle = handle
-                st.session_state.current_query = query
+            def display_not_tweet():
+                if mimetype[i] == 'application/json':
+                    st.error('Tweet has been deleted.')
+                    response = requests.get(link, timeout=5)
+                    json_data = response.json()
+
+                    st.json(json_data, expanded=False)
+
+                    st.divider()
+                if mimetype[i] == 'text/html':
+                    st.error('Tweet has been deleted.')
+                    components.iframe(link, height=500)
 
-                return_none_count = 0
+                    st.divider()
 
-                def prev_page():
-                    st.session_state.offset -= tweets_per_page
+            start_index = st.session_state.offset
+            end_index = min(count, start_index + tweets_per_page)
 
-                    #scroll to top config
-                    st.session_state.update_component += 1
-                    scroll_into_view()
+            for i in range(tweets_per_page):
+                try:
+                    bar.progress((i*3) + 13)
 
-                def next_page():
-                    st.session_state.offset += tweets_per_page
+                    link = parsed_links[i]
+                    tweet = embed(tweet_links[i])
 
-                    #scroll to top config
-                    st.session_state.update_component += 1
-                    scroll_into_view()
+                    if not only_deleted:
+                        attr(i)
 
-                start_index = st.session_state.offset
-                end_index = min(count, start_index + tweets_per_page)
+                        if tweet:
+                            status_code = tweet[0]
+                            tweet_content = tweet[1]
+                            user_info = tweet[2]
+                            is_RT = tweet[3]
 
-                for i in range(tweets_per_page):
-                    try:
-                        link = parsed_links[i]
-                        tweet = embed(tweet_links[i])
+                            if mimetype[i] == 'application/json':
+                                display_tweet()
 
-                        if not only_deleted:
+                            if mimetype[i] == 'text/html':
+                                display_tweet()
+                        elif not tweet:
+                            display_not_tweet()
+
+                    if only_deleted:
+                        if not tweet:
+                            return_none_count += 1
                             attr(i)
 
-                            if tweet:
-                                status_code = tweet[0]
-                                tweet_content = tweet[1]
-                                user_info = tweet[2]
-                                is_RT = tweet[3]
-
-                                if mimetype[i] == 'application/json':
-                                    if is_RT[0] == True:
-                                        st.info('*Retweet*')
-                                    st.write(tweet_content[0])
-                                    st.write(user_info[0])
-
-                                    st.divider()
-                                if mimetype[i] == 'text/html':
-                                    if is_RT[0] == True:
-                                        st.info('*Retweet*')
-                                    st.write(tweet_content[0])
-                                    st.write(user_info[0])
-
-                                    st.divider()
-                            elif not tweet:
-                                if mimetype[i] == 'application/json':
-                                    st.error('Tweet has been deleted.')
-                                    response = requests.get(link, timeout=5)
-                                    json_data = response.json()
-
-                                    st.json(json_data, expanded=False)
-
-                                    st.divider()
-                                if mimetype[i] == 'text/html':
-                                    st.error('Tweet has been deleted.')
-                                    st.info('IFRAME')
-                                    st.write(link)
-
-                                    st.divider()
-
-                        if only_deleted:
-                            if not tweet:
-                                return_none_count += 1
-                                attr(i)
-
-                                if mimetype[i] == 'application/json':
-                                    st.error('Tweet has been deleted.')
-                                    response = requests.get(link, timeout=5)
-                                    json_data = response.json()
-
-                                    st.json(json_data, expanded=False)
-
-                                    st.divider()
-                                if mimetype[i] == 'text/html':
-                                    st.error('Tweet has been deleted.')
-                                    st.info('IFRAME')
-                                    st.write(link)
-
-                                    st.divider()
-
-                            progress.write('{} URLs have been captured in the range {}-{}'.format(return_none_count, start_index, end_index))
-
-                        if start_index <= 0:
-                            st.session_state.prev_disabled = True
-                        else:
-                            st.session_state.prev_disabled = False
-
-                        if i + 1 == count:
-                            st.session_state.next_disabled = True
-                        else:
-                            st.session_state.next_disabled = False
-                    except IndexError:
-                        if start_index <= 0:
-                            st.session_state.prev_disabled = True
-                        else:
-                            st.session_state.prev_disabled = False
+                            display_not_tweet()
+
+                        progress.write('{} URLs have been captured in the range {}-{}'.format(return_none_count, start_index, end_index))
 
+                    if start_index <= 0:
+                        st.session_state.prev_disabled = True
+                    else:
+                        st.session_state.prev_disabled = False
+
+                    if i + 1 == count:
                         st.session_state.next_disabled = True
+                    else:
+                        st.session_state.next_disabled = False
+                except IndexError:
+                    if start_index <= 0:
+                        st.session_state.prev_disabled = True
+                    else:
+                        st.session_state.prev_disabled = False
+
+                    st.session_state.next_disabled = True
 
-                prev, _ , next = st.columns([3, 4, 3])
+            prev, _ , next = st.columns([3, 4, 3])
 
-                prev.button('Previous', disabled=st.session_state.prev_disabled, key='prev_button_key', on_click=prev_page, type='primary', use_container_width=True)
-                next.button('Next', disabled=st.session_state.next_disabled, key='next_button_key', on_click=next_page, type='primary', use_container_width=True)
+            prev.button('Previous', disabled=st.session_state.prev_disabled, key='prev_button_key', on_click=prev_page, type='primary', use_container_width=True)
+            next.button('Next', disabled=st.session_state.next_disabled, key='next_button_key', on_click=next_page, type='primary', use_container_width=True)
 
-            if not links:
-                st.error('Unable to query the Wayback Machine API.')
+        if not links:
+            st.error('Unable to query the Wayback Machine API.')
     except TypeError as e:
         st.error('''
         {}. Refresh this page and try again.

From 2a4ba380b3f6f368eb7e4b1e5bcacb0976277886 Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Mon, 14 Aug 2023 17:48:52 -0300
Subject: [PATCH 3/8] test screenshot

---
 README.md        |  2 ++
 app.py           | 39 ++++++++++++++++++++++++++++++++-------
 requirements.txt |  2 +-
 3 files changed, 35 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index c7cf677..ea8eaf3 100644
--- a/README.md
+++ b/README.md
@@ -60,5 +60,7 @@ Streamlit will be served at http://localhost:8501
 - [ ] Add current page to page title
 - [ ] Parse MIME type `warc/revisit`
 - [ ] Filter by period/datetime
+- [ ] Apply filters by API endpoints
+- [ ] Add contributing guidelines
 
 ## [Changelog](/CHANGELOG.md)
diff --git a/app.py b/app.py
index 299dddc..41225d0 100644
--- a/app.py
+++ b/app.py
@@ -4,7 +4,8 @@
 import streamlit.components.v1 as components
 import json
 import re
-from bs4 import BeautifulSoup
+import os
+from selenium import webdriver
 
 __version__ = '0.2'
 
@@ -92,7 +93,7 @@ def scroll_into_view():
 def embed(tweet):
     try:
         url = 'https://publish.twitter.com/oembed?url={}'.format(tweet)
-        response = requests.get(url, timeout=1)
+        response = requests.get(url)
 
         regex = r'<blockquote class="twitter-tweet"><p[^>]*>(.*?)<\/p>.*?&mdash; (.*?)<\/a>'
         regex_author = r'^(.*?)\s*\('
@@ -141,7 +142,7 @@ def embed(tweet):
 def tweets_count(handle):
     url = 'https://web.archive.org/cdx/search/cdx?url=https://twitter.com/{}/status/*&output=json'.format(handle)
     try:
-        response = requests.get(url, timeout=10)
+        response = requests.get(url)
 
         if response.status_code == 200:
             data = response.json()
@@ -162,7 +163,7 @@ def query_api(handle, limit, offset):
 
     url = 'https://web.archive.org/cdx/search/cdx?url=https://twitter.com/{}/status/*&output=json&limit={}&offset={}'.format(handle, limit, offset)
     try:
-        response = requests.get(url, timeout=1)
+        response = requests.get(url)
 
         if response.status_code == 200 or response.status_code == 304:
             return response.json()
@@ -204,7 +205,7 @@ def attr(i):
 handle = st.text_input('username', placeholder='username', label_visibility='collapsed')
 query = st.button('Query', type='primary', use_container_width=True)
 
-bar = st.progress(0)
+bar = st.empty()
 
 if query or handle:
     if handle != st.session_state.current_handle:
@@ -222,6 +223,7 @@ def attr(i):
     only_deleted = st.checkbox('Only deleted tweets')
 
     try:
+        bar.progress(0)
         progress = st.empty()
         links = query_api(handle, tweets_per_page, st.session_state.offset)
         parsed_links = parse_links(links)[0]
@@ -263,15 +265,38 @@ def display_tweet():
             def display_not_tweet():
                 if mimetype[i] == 'application/json':
                     st.error('Tweet has been deleted.')
-                    response = requests.get(link, timeout=5)
+                    response = requests.get(link)
                     json_data = response.json()
+                    json_text = response.json()['text']
 
+                    st.code(json_text)
                     st.json(json_data, expanded=False)
 
                     st.divider()
                 if mimetype[i] == 'text/html':
                     st.error('Tweet has been deleted.')
-                    components.iframe(link, height=500)
+
+                    re_link = re.search(r'[^/]+$', link)
+                    re_link = re_link.group()
+                    screenshot_filename = 'img_{}.jpg'.format(re_link)
+
+                    if not os.path.exists(screenshot_filename):
+                        options = webdriver.ChromeOptions()
+                        options.add_argument('--headless')
+
+                        driver = webdriver.Chrome(options=options)
+                        driver.get(link)
+                        driver.set_window_size(700, 700)
+
+                        current_directory = os.getcwd()
+                        screenshot_path = os.path.join(current_directory, screenshot_filename)
+
+                        driver.save_screenshot(screenshot_path)
+                        driver.quit()
+
+                    st.image(screenshot_filename)
+                    # components.iframe(link, height=500, width=700)
+                    # st.markdown('<iframe src="{}" loading="lazy" height=500 width=auto></iframe>'.format(link), unsafe_allow_html=True)
 
                     st.divider()
 
diff --git a/requirements.txt b/requirements.txt
index 5f0beb7..dee3de6 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,2 @@
 requests==2.30.0
-streamlit==1.23.1
+streamlit==1.25.0

From 1bfb6b3faa1f3d71301ca9a562946c891e3041df Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Mon, 14 Aug 2023 17:51:32 -0300
Subject: [PATCH 4/8] update req

---
 requirements.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/requirements.txt b/requirements.txt
index dee3de6..edfe694 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,3 @@
 requests==2.30.0
 streamlit==1.25.0
+selenium==4.11.2
\ No newline at end of file

From e57d84b9ac4deb69a071970a823287b33da47ab5 Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Mon, 14 Aug 2023 17:56:53 -0300
Subject: [PATCH 5/8] test lazy loading

---
 app.py           | 23 +----------------------
 requirements.txt |  3 +--
 2 files changed, 2 insertions(+), 24 deletions(-)

diff --git a/app.py b/app.py
index 41225d0..717b545 100644
--- a/app.py
+++ b/app.py
@@ -4,8 +4,6 @@
 import streamlit.components.v1 as components
 import json
 import re
-import os
-from selenium import webdriver
 
 __version__ = '0.2'
 
@@ -276,27 +274,8 @@ def display_not_tweet():
                 if mimetype[i] == 'text/html':
                     st.error('Tweet has been deleted.')
 
-                    re_link = re.search(r'[^/]+$', link)
-                    re_link = re_link.group()
-                    screenshot_filename = 'img_{}.jpg'.format(re_link)
-
-                    if not os.path.exists(screenshot_filename):
-                        options = webdriver.ChromeOptions()
-                        options.add_argument('--headless')
-
-                        driver = webdriver.Chrome(options=options)
-                        driver.get(link)
-                        driver.set_window_size(700, 700)
-
-                        current_directory = os.getcwd()
-                        screenshot_path = os.path.join(current_directory, screenshot_filename)
-
-                        driver.save_screenshot(screenshot_path)
-                        driver.quit()
-
-                    st.image(screenshot_filename)
                     # components.iframe(link, height=500, width=700)
-                    # st.markdown('<iframe src="{}" loading="lazy" height=500 width=auto></iframe>'.format(link), unsafe_allow_html=True)
+                    st.markdown('<iframe src="{}" loading="lazy" height=500 width=auto></iframe>'.format(link), unsafe_allow_html=True)
 
                     st.divider()
 
diff --git a/requirements.txt b/requirements.txt
index edfe694..dff5d86 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,2 @@
 requests==2.30.0
-streamlit==1.25.0
-selenium==4.11.2
\ No newline at end of file
+streamlit==1.25.0
\ No newline at end of file

From e02001bda00305ca670c85a82debb327f2f6ea61 Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Mon, 14 Aug 2023 19:27:09 -0300
Subject: [PATCH 6/8] test iframe

---
 app.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/app.py b/app.py
index 717b545..7be3ca6 100644
--- a/app.py
+++ b/app.py
@@ -49,6 +49,10 @@
         height: 0%;
         position: fixed;
     }
+    iframe {
+        background-color: #dddddd;
+        border-radius: 0.5rem;
+    }
 </style>
 '''
 
@@ -275,7 +279,7 @@ def display_not_tweet():
                     st.error('Tweet has been deleted.')
 
                     # components.iframe(link, height=500, width=700)
-                    st.markdown('<iframe src="{}" loading="lazy" height=500 width=auto></iframe>'.format(link), unsafe_allow_html=True)
+                    st.markdown('<iframe srcdoc="Loading..." onload="this.removeAttribute(\'srcdoc\')" src="{}" loading="lazy" height=500 width="100%"></iframe>'.format(link), unsafe_allow_html=True)
 
                     st.divider()
 

From f0d73a28cbe5f9c88f27cc8dea9c48384ddbb0bb Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Mon, 14 Aug 2023 19:29:43 -0300
Subject: [PATCH 7/8] test iframe

---
 app.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/app.py b/app.py
index 7be3ca6..66c1d2f 100644
--- a/app.py
+++ b/app.py
@@ -279,7 +279,7 @@ def display_not_tweet():
                     st.error('Tweet has been deleted.')
 
                     # components.iframe(link, height=500, width=700)
-                    st.markdown('<iframe srcdoc="Loading..." onload="this.removeAttribute(\'srcdoc\')" src="{}" loading="lazy" height=500 width="100%"></iframe>'.format(link), unsafe_allow_html=True)
+                    st.markdown('<iframe src="{}" loading="lazy" height=500 width="100%"></iframe>'.format(link), unsafe_allow_html=True)
 
                     st.divider()
 

From e156a5ebb19cc8313b4ffdc681b1d6786e1041f0 Mon Sep 17 00:00:00 2001
From: Claromes <claromes@hey.com>
Date: Wed, 16 Aug 2023 12:12:04 -0300
Subject: [PATCH 8/8] update code, add warc warning, update iframe

---
 app.py | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/app.py b/app.py
index 66c1d2f..437ed95 100644
--- a/app.py
+++ b/app.py
@@ -5,8 +5,6 @@
 import json
 import re
 
-__version__ = '0.2'
-
 year = datetime.datetime.now().year
 
 st.set_page_config(
@@ -228,11 +226,12 @@ def attr(i):
         bar.progress(0)
         progress = st.empty()
         links = query_api(handle, tweets_per_page, st.session_state.offset)
-        parsed_links = parse_links(links)[0]
-        tweet_links = parse_links(links)[1]
-        mimetype = parse_links(links)[2]
-        timestamp = parse_links(links)[3]
 
+        parse = parse_links(links)
+        parsed_links = parse[0]
+        tweet_links = parse[1]
+        mimetype = parse[2]
+        timestamp = parse[3]
 
         if links:
             st.divider()
@@ -277,9 +276,12 @@ def display_not_tweet():
                     st.divider()
                 if mimetype[i] == 'text/html':
                     st.error('Tweet has been deleted.')
+                    components.iframe(link, height=500, scrolling=True)
+
+                    st.divider()
 
-                    # components.iframe(link, height=500, width=700)
-                    st.markdown('<iframe src="{}" loading="lazy" height=500 width="100%"></iframe>'.format(link), unsafe_allow_html=True)
+                if mimetype[i] == 'warc/revisit':
+                    st.warning('''MIME Type was not parsed.''')
 
                     st.divider()
 
@@ -328,6 +330,7 @@ def display_not_tweet():
                         st.session_state.next_disabled = True
                     else:
                         st.session_state.next_disabled = False
+                # TODO
                 except IndexError:
                     if start_index <= 0:
                         st.session_state.prev_disabled = True