import requests
import pandas as pd
from bs4 import BeautifulSoup as bs
url = "https://www.rev.com/blog/transcripts/donald-trump-joe-biden-1st-presidential-debate-transcript-2020"
page = requests.get(url)
soup= bs(page.content, "html.parser")
content_block = soup.find("div", {"class": "fl-callout-text"})
targets = content_block.findAll('p')
targets[0].get_text()
'Chris Wallace: (01:20)\nGood evening from the Health Education Campus of Case Western Reserve University and the Cleveland Clinic. I’m Chris Wallace of Fox News and I welcome you to the first of the 2020 Presidential Debates between President Donald J. Trump and former Vice President Joe Biden. This debate is sponsored by the Commission on Presidential debates. The Commission has designed the format, six roughly 15 minute segments with two minute answers from each candidate to the first question, then open discussion for the rest of each segment. Both campaigns have agreed to these rules. For the record, I decided the topics and the questions in each topic. I can assure you none of the questions has been shared with the Commission or the two candidates.'
# THIS GOT ALMOST EVERYTHING
# transcript = []
# prev_time = ''
# for t in targets:
# target = t.get_text()
# try:
# name = target.split(':')[0]
# time = target.split('(')[1].split(')')[0]
# words = target.split(')')[1].strip()
# obj = {'name': name, 'time': time, 'words': words}
# transcript.append(obj)
# except:
# print(target)
transcript = []
prev_time = ''
for t in targets:
target = t.get_text()
name = target.split(':')[0]
try:
time = target.split('(')[1].split(')')[0]
except:
time = prev_time
try:
words = target.split('\n')[1].strip()
except:
print(target)
obj = {'name': name, 'time': time, 'words': words}
prev_time = time
transcript.append(obj)
df = pd.DataFrame(transcript)
df.to_csv('NLP_debates2020.csv', index=False)
df = pd.read_csv('NLP_debates2020.csv')
# df
# PROBLEM: Can't subtract strings
# SOLUTION: Simply turn it into a datetime
# PROBLEM: 01:20 turns into 1 hour twenty minutes instead of 1 minute 20 sceconds
# SOLUTION: Add "00:" to the front of those and turn it into a time object!
# PROBLEM: You can't subtract time objects
# SOLUTION: Turn it into a datetime object
# PROBLEM: You can't convert this to a datetime object
# SOLUTION: Convert it to a "timedelta" object, wtf that is
# PROBLEM: ... it needs to be a string (back where we started?!)
# SOLUTION: df['datetime'] = pd.to_timedelta(df['timestamp'].astype(str))
# ...and NOW we can use .dif()
# PROBLEM: Now that we have the difference, we STILL can't sum it
# SOLUTION: Use dt.total_seconds() (I seriously must be missing something)
from datetime import time
def better_time(t):
if len(t.split(':')) > 2:
return t
else:
return "00:" + t
df['better_time'] = df.apply(lambda x: better_time(x['time']), axis=1)
def convert_time(t):
try:
return time.fromisoformat(t)
except:
return 'error'
df['timestamp'] = df.apply(lambda x: convert_time(x['better_time']), axis=1)
df['datetime'] = pd.to_timedelta(df['timestamp'].astype(str))
df['time_diff'] = df['datetime'].diff()
df['seconds'] = df['time_diff'].dt.total_seconds()
df
name | time | words | better_time | timestamp | datetime | time_diff | seconds | |
---|---|---|---|---|---|---|---|---|
0 | Chris Wallace | 01:20 | Good evening from the Health Education Campus ... | 00:01:20 | 00:01:20 | 00:01:20 | NaT | NaN |
1 | Chris Wallace | 02:10 | This debate is being conducted under health an... | 00:02:10 | 00:02:10 | 00:02:10 | 00:00:50 | 50.0 |
2 | Vice President Joe Biden | 02:49 | How you doing, man? | 00:02:49 | 00:02:49 | 00:02:49 | 00:00:39 | 39.0 |
3 | President Donald J. Trump | 02:51 | How are you doing? | 00:02:51 | 00:02:51 | 00:02:51 | 00:00:02 | 2.0 |
4 | Vice President Joe Biden | 02:51 | I’m well. | 00:02:51 | 00:02:51 | 00:02:51 | 00:00:00 | 0.0 |
... | ... | ... | ... | ... | ... | ... | ... | ... |
785 | Chris Wallace | 01:10:43 | Gentlemen, just say that’s the end of it [cros... | 01:10:43 | 01:10:43 | 01:10:43 | 00:00:02 | 2.0 |
786 | President Donald J. Trump | 01:10:47 | I want to see an honest ballot count. | 01:10:47 | 01:10:47 | 01:10:47 | 00:00:04 | 4.0 |
787 | Chris Wallace | 01:10:48 | We’re going to leave it there- | 01:10:48 | 01:10:48 | 01:10:48 | 00:00:01 | 1.0 |
788 | President Donald J. Trump | 01:10:49 | And I think he does too- | 01:10:49 | 01:10:49 | 01:10:49 | 00:00:01 | 1.0 |
789 | Chris Wallace | 01:10:50 | … to be continued in more debates as we go on.... | 01:10:50 | 01:10:50 | 01:10:50 | 00:00:01 | 1.0 |
790 rows × 8 columns
df['number_of_words'] = df.apply(lambda x: len(x['words'].split(' ')), axis=1)
df
name | time | words | better_time | timestamp | datetime | time_diff | seconds | number_of_words | |
---|---|---|---|---|---|---|---|---|---|
0 | Chris Wallace | 01:20 | Good evening from the Health Education Campus ... | 00:01:20 | 00:01:20 | 00:01:20 | NaT | NaN | 124 |
1 | Chris Wallace | 02:10 | This debate is being conducted under health an... | 00:02:10 | 00:02:10 | 00:02:10 | 00:00:50 | 50.0 | 102 |
2 | Vice President Joe Biden | 02:49 | How you doing, man? | 00:02:49 | 00:02:49 | 00:02:49 | 00:00:39 | 39.0 | 4 |
3 | President Donald J. Trump | 02:51 | How are you doing? | 00:02:51 | 00:02:51 | 00:02:51 | 00:00:02 | 2.0 | 4 |
4 | Vice President Joe Biden | 02:51 | I’m well. | 00:02:51 | 00:02:51 | 00:02:51 | 00:00:00 | 0.0 | 2 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
785 | Chris Wallace | 01:10:43 | Gentlemen, just say that’s the end of it [cros... | 01:10:43 | 01:10:43 | 01:10:43 | 00:00:02 | 2.0 | 17 |
786 | President Donald J. Trump | 01:10:47 | I want to see an honest ballot count. | 01:10:47 | 01:10:47 | 01:10:47 | 00:00:04 | 4.0 | 8 |
787 | Chris Wallace | 01:10:48 | We’re going to leave it there- | 01:10:48 | 01:10:48 | 01:10:48 | 00:00:01 | 1.0 | 6 |
788 | President Donald J. Trump | 01:10:49 | And I think he does too- | 01:10:49 | 01:10:49 | 01:10:49 | 00:00:01 | 1.0 | 6 |
789 | Chris Wallace | 01:10:50 | … to be continued in more debates as we go on.... | 01:10:50 | 01:10:50 | 01:10:50 | 00:00:01 | 1.0 | 122 |
790 rows × 9 columns
df.to_csv('NLP_debates2020_withTimeDiff.csv', index=False)
df = pd.read_csv('NLP_debates2020_withTimeDiff.csv')
df
name | time | words | better_time | timestamp | datetime | time_diff | seconds | number_of_words | |
---|---|---|---|---|---|---|---|---|---|
0 | Chris Wallace | 01:20 | Good evening from the Health Education Campus ... | 00:01:20 | 00:01:20 | 0 days 00:01:20.000000000 | NaN | NaN | 124 |
1 | Chris Wallace | 02:10 | This debate is being conducted under health an... | 00:02:10 | 00:02:10 | 0 days 00:02:10.000000000 | 0 days 00:00:50.000000000 | 50.0 | 102 |
2 | Vice President Joe Biden | 02:49 | How you doing, man? | 00:02:49 | 00:02:49 | 0 days 00:02:49.000000000 | 0 days 00:00:39.000000000 | 39.0 | 4 |
3 | President Donald J. Trump | 02:51 | How are you doing? | 00:02:51 | 00:02:51 | 0 days 00:02:51.000000000 | 0 days 00:00:02.000000000 | 2.0 | 4 |
4 | Vice President Joe Biden | 02:51 | I’m well. | 00:02:51 | 00:02:51 | 0 days 00:02:51.000000000 | 0 days 00:00:00.000000000 | 0.0 | 2 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
785 | Chris Wallace | 01:10:43 | Gentlemen, just say that’s the end of it [cros... | 01:10:43 | 01:10:43 | 0 days 01:10:43.000000000 | 0 days 00:00:02.000000000 | 2.0 | 17 |
786 | President Donald J. Trump | 01:10:47 | I want to see an honest ballot count. | 01:10:47 | 01:10:47 | 0 days 01:10:47.000000000 | 0 days 00:00:04.000000000 | 4.0 | 8 |
787 | Chris Wallace | 01:10:48 | We’re going to leave it there- | 01:10:48 | 01:10:48 | 0 days 01:10:48.000000000 | 0 days 00:00:01.000000000 | 1.0 | 6 |
788 | President Donald J. Trump | 01:10:49 | And I think he does too- | 01:10:49 | 01:10:49 | 0 days 01:10:49.000000000 | 0 days 00:00:01.000000000 | 1.0 | 6 |
789 | Chris Wallace | 01:10:50 | … to be continued in more debates as we go on.... | 01:10:50 | 01:10:50 | 0 days 01:10:50.000000000 | 0 days 00:00:01.000000000 | 1.0 | 122 |
790 rows × 9 columns
dfg = df.groupby('name')['seconds'].sum()
dfg
name Chris Wallace 1774.0 President Donald J. Trump 707.0 Vice President Joe Biden 1689.0 0.0 Name: seconds, dtype: float64
dfg = df.groupby('name')['number_of_words'].sum()
dfg
name Chris Wallace 4674 President Donald J. Trump 7240 Vice President Joe Biden 6618 7 Name: number_of_words, dtype: int64
biden = df[df['name'] == 'Vice President Joe Biden']
trump = df[df['name'] == 'President Donald J. Trump']
from collections import Counter
biden_words = biden['words']
trump_words = trump['words']
all_biden_words = ""
for w in biden_words:
all_biden_words += w
all_trump_words = ""
for w in trump_words:
all_trump_words += w
biden_word_count = Counter(all_biden_words.split(' '))
biden_word_count.most_common()
[('the', 296), ('to', 220), ('of', 135), ('in', 132), ('a', 123), ('and', 116), ('is', 109), ('that', 82), ('he', 71), ('you', 66), ('people', 61), ('going', 60), ('have', 59), ('not', 58), ('be', 55), ('we', 48), ('it', 46), ('And', 46), ('what', 45), ('I', 44), ('He', 43), ('are', 41), ('for', 37), ('on', 37), ('about', 35), ('this', 30), ('who', 29), ('by', 29), ('because', 28), ('get', 27), ('has', 27), ('his', 26), ('with', 25), ('[crosstalk', 25), ('was', 25), ('they', 23), ('out', 23), ('fact', 23), ('all', 23), ('The', 22), ('as', 22), ('do', 22), ('at', 21), ('your', 20), ('should', 19), ('We', 19), ('it’s', 19), ('He’s', 18), ('more', 18), ('there', 18), ('did', 18), ('so', 17), ('way', 17), ('like', 17), ('able', 17), ('just', 17), ('can', 17), ('make', 17), ('take', 17), ('been', 16), ('will', 16), ('if', 16), ('it.', 16), ('They', 16), ('how', 16), ('You', 16), ('sure', 16), ('when', 15), ('we’re', 15), ('he’s', 15), ('my', 15), ('doesn’t', 15), ('tax', 15), ('It’s', 14), ('want', 14), ('know', 14), ('don’t', 14), ('up', 14), ('say', 13), ('I’m', 13), ('fact,', 13), ('got', 13), ('no', 13), ('being', 13), ('American', 12), ('that’s', 12), ('down', 12), ('him', 12), ('look', 12), ('said', 12), ('now', 11), ('their', 11), ('from', 11), ('If', 11), ('them', 11), ('That’s', 11), ('would', 11), ('This', 11), ('than', 11), ('It', 11), ('an', 10), ('that,', 10), ('million', 10), ('had', 10), ('were', 10), ('here’s', 10), ('deal.', 10), ('way,', 10), ('those', 10), ('talking', 10), ('which', 9), ('talk', 9), ('never', 9), ('didn’t', 9), ('vote', 8), ('United', 8), ('They’re', 8), ('made', 8), ('very', 8), ('one', 8), ('many', 8), ('done', 8), ('Number', 8), ('number', 8), ('said,', 8), ('back', 8), ('or', 8), ('even', 8), ('lot', 8), ('but', 8), ('these', 8), ('open', 8), ('they’re', 8), ('election', 7), ('wants', 7), ('went', 7), ('could', 7), ('man', 7), ('deal', 7), ('plan', 7), ('go', 7), ('it,', 7), ('jobs', 7), ('create', 7), ('you’re', 7), ('President', 6), ('thousands', 6), ('only', 6), ('that.', 6), ('trying', 6), ('having', 6), ('But', 6), ('same', 6), ('until', 6), ('What', 6), ('Well,', 6), ('shut', 6), ('ballot', 6), ('one.', 6), ('everything', 6), ('plan.', 6), ('vote.', 6), ('us', 6), ('bring', 6), ('economy', 6), ('them,', 6), ('own', 6), ('end', 6), ('you.', 6), ('His', 6), ('totally', 6), ('president', 6), ('can’t', 6), ('ballots', 6), ('right', 5), ('here', 5), ('Affordable', 5), ('Care', 5), ('before', 5), ('money', 5), ('then', 5), ('simply', 5), ('does', 5), ('me', 5), ('me,', 5), ('still', 5), ('wrong', 5), ('any', 5), ('two,', 5), ('won’t', 5), ('about.', 5), ('let', 5), ('When', 5), ('why', 5), ('knew', 5), ('give', 5), ('job', 5), ('need', 5), ('someone', 5), ('where', 5), ('says', 5), ('terms', 5), ('care', 5), ('asked', 5), ('work', 5), ('put', 5), ('COVID', 5), ('guy', 5), ('administration', 5), ('our', 5), ('things', 5), ('There’s', 5), ('police', 5), ('out.', 5), ('violence', 5), ('is,', 5), ('support', 5), ('millions', 5), ('doing', 4), ('States', 4), ('States.', 4), ('already', 4), ('see', 4), ('what’s', 4), ('now,', 4), ('into', 4), ('she', 4), ('other', 4), ('pre-existing', 4), ('there’s', 4), ('away', 4), ('knows', 4), ('big', 4), ('saying', 4), ('Biden', 4), ('under', 4), ('am', 4), ('COVID.', 4), ('well', 4), ('him.', 4), ('matter', 4), ('whole', 4), ('you,', 4), ('tell', 4), ('help', 4), ('ever', 4), ('hasn’t', 4), ('talks', 4), ('position', 4), ('voting', 4), ('day', 4), ('In', 4), ('between', 4), ('serious', 4), ('determine', 4), ('great', 4), ('down.', 4), ('another', 4), ('trust', 4), ('do,', 4), ('No', 4), ('time', 4), ('idea', 4), ('Why', 4), ('making', 4), ('less', 4), ('economic', 4), ('every', 4), ('blew', 4), ('I’ll', 4), ('good', 4), ('happened', 4), ('stay', 4), ('problem.', 4), ('build', 4), ('Green', 4), ('New', 4), ('mail-in', 4), ('How', 3), ('first', 3), ('forward', 3), ('Mr.', 3), ('middle', 3), ('voted', 3), ('thing', 3), ('outcome', 3), ('rid', 3), ('insurance', 3), ('justice,', 3), ('opposed', 3), ('court,', 3), ('down,', 3), ('pay', 3), ('passed', 3), ('election.', 3), ('next', 3), ('wipe', 3), ('Democratic', 3), ('200,000', 3), ('died', 3), ('happy', 3), ('point', 3), ('now.', 3), ('public', 3), ('call', 3), ('costs', 3), ('healthcare', 3), ('recession.', 3), ('since', 3), ('that’ll', 3), ('wasn’t', 3), ('is.', 3), ('laid', 3), ('do?', 3), ('people.', 3), ('told', 3), ('doing.', 3), ('businesses', 3), ('money.', 3), ('together', 3), ('save', 3), ('folks', 3), ('Director', 3), ('gone', 3), ('gone.', 3), ('maybe', 3), ('some', 3), ('year', 3), ('out,', 3), ('no,', 3), ('no.', 3), ('try', 3), ('One', 3), ('Because', 3), ('A', 3), ('provide', 3), ('mean,', 3), ('head', 3), ('everybody', 3), ('billion', 3), ('president.', 3), ('People', 3), ('states', 3), ('America', 3), ('significant', 3), ('fix', 3), ('anything', 3), ('aren’t', 3), ('Not', 3), ('nothing', 3), ('makes', 3), ('eliminate', 3), ('four', 3), ('billions', 3), ('trade', 3), ('way.', 3), ('before.', 3), ('discredited.', 3), ('son', 3), ('true.', 3), ('America.', 3), ('we’ve', 3), ('gas', 3), ('held', 3), ('happen.', 3), ('different', 3), ('together.', 3), ('15%', 3), ('I’ve', 3), ('FBI', 3), ('president,', 3), ('much', 3), ('That', 3), ('oil', 3), ('We’re', 3), ('jobs.', 3), ('jobs,', 3), ('Paris', 3), ('paying', 3), ('vote,', 3), ('evidence', 3), ('votes', 3), ('counted,', 3), ('accepted.', 3), ('ballots,', 3), ('this,', 2), ('Supreme', 2), ('Court', 2), ('Senators', 2), ('happen', 2), ('wait', 2), ('elect', 2), ('stake', 2), ('running', 2), ('Act,', 2), ('20', 2), ('health', 2), ('goes', 2), ('fine', 2), ('person.', 2), ('rights', 2), ('woman', 2), ('charge', 2), ('they’ll', 2), ('well.', 2), ('Those', 2), ('companies', 2), ('forward.', 2), ('one,', 2), ('Obamacare', 2), ('increase', 2), ('do.', 2), ('me.', 2), ('Party', 2), ('approved', 2), ('of.', 2), ('seven', 2), ('also', 2), ('healthcare.He', 2), ('not.', 2), ('poor', 2), ('Medicaid', 2), ('most', 2), ('option.', 2), ('vast', 2), ('majority', 2), ('beat', 2), ('tonight', 2), ('far', 2), ('through', 2), ('away.', 2), ('that.He', 2), ('sends', 2), ('power.', 2), ('drug', 2), ('almost', 2), ('become', 2), ('issue', 2), ('Vote', 2), ('know,', 2), ('answer', 2), ('really', 2), ('As', 2), ('over', 2), ('world’s', 2), ('addition', 2), ('1000', 2), ('dying.', 2), ('anything.', 2), ('crisis', 2), ('was.', 2), ('insisting', 2), ('China', 2), ('themselves', 2), ('dangerous', 2), ('ask', 2), ('Xi', 2), ('nothing.', 2), ('waited', 2), ('providing', 2), ('order', 2), ('keep', 2), ('open.', 2), ('schools', 2), ('cost', 2), ('golf', 2), ('Democrats', 2), ('Republicans', 2), ('needs', 2), ('reason', 2), ('look,', 2), ('home.', 2), ('COVID?', 2), ('lost', 2), ('couldn’t', 2), ('CDC', 2), ('mask,', 2), ('half', 2), ('Just', 2), ('mask.', 2), ('vaccine,', 2), ('all.', 2), ('By', 2), ('vaccine.', 2), ('vaccine', 2), ('year,', 2), ('God', 2), ('question', 2), ('pointed', 2), ('people…', 2), ('looked', 2), ('market.', 2), ('unless', 2), ('I’d', 2), ('ability', 2), ('need.', 2), ('meet', 2), ('them.', 2), ('sits', 2), ('think', 2), ('respond', 2), ('masks', 2), ('difference.', 2), ('wore', 2), ('social', 2), ('person', 2), ('last', 2), ('came', 2), ('worried', 2), ('effect.', 2), ('Come', 2), ('masks,', 2), ('difference', 2), ('billionaires', 2), ('proposal,', 2), ('home,', 2), ('small', 2), ('towns', 2), ('America,', 2), ('worked', 2), ('became', 2), ('front', 2), ('more.', 2), ('better', 2), ('home', 2), ('school', 2), ('national', 2), ('emergency.', 2), ('They’ve', 2), ('Look,', 2), ('advantage', 2), ('code.', 2), ('weren’t', 2), ('worst', 2), ('federal', 2), ('buildings', 2), ('penny', 2), ('single', 2), ('inherited', 2), ('recovery', 2), ('booming', 2), ('brought', 2), ('done.', 2), ('art', 2), ('true.None', 2), ('everyone,', 2), ('testified', 2), ('fired', 2), ('family,', 2), ('people,', 2), ('absolutely', 2), ('true.That’s', 2), ('equity', 2), ('walked', 2), ('true,', 2), ('remember', 2), ('coming', 2), ('killed', 2), ('Floyd', 2), ('killed,', 2), ('peaceful', 2), ('protest', 2), ('White', 2), ('use', 2), ('church', 2), ('hold', 2), ('after', 2), ('dog', 2), ('African', 2), ('something', 2), ('500', 2), ('Americans.', 2), ('did.', 2), ('law', 2), ('enforcement', 2), ('officers', 2), ('bad', 2), ('accountable.', 2), ('entire', 2), ('These', 2), ('cops', 2), ('grow', 2), ('bit', 2), ('country', 2), ('cannot', 2), ('racism', 2), ('crime', 2), ('suburbs.', 2), ('white', 2), ('suburbs', 2), ('failure', 2), ('defunding', 2), ('police,', 2), ('local', 2), ('calls', 2), ('$400', 2), ('assistance.', 2), ('up.', 2), ('former', 2), ('vice', 2), ('clear', 2), ('keeps', 2), ('fire', 2), ('weaker,', 2), ('divided', 2), ('violent.', 2), ('left', 2), ('regard', 2), ('Putin', 2), ('son,', 2), ('behind', 2), ('proud', 2), ('report', 2), ('standards', 2), ('renewable', 2), ('energy', 2), ('coal', 2), ('plant', 2), ('move', 2), ('fleet', 2), ('emit', 2), ('heat', 2), ('creating', 2), ('carbon', 2), ('$20', 2), ('Look', 2), ('hurricanes,', 2), ('hard,', 2), ('come', 2), ('Deal', 2), ('director,', 2), ('polls', 2), ('counted.', 2), ('sent', 2), ('day.', 2), ('count', 2), ('for,', 2), ('somehow', 2), ('doing,', 1), ('man?I’m', 1), ('well.Well,', 1), ('all,', 1), ('thank', 1), ('looking', 1), ('President.The', 1), ('nominee', 1), ('occurs', 1), ('chance', 1), ('already.', 1), ('started.', 1), ('Tens', 1), ('wait.', 1), ('express', 1), ('view', 1), ('Vice', 1), ('President.Now,', 1), ('President’s', 1), ('clear,', 1), ('Act.', 1), ('ran', 1), ('governing', 1), ('strip', 1), ('court.', 1), ('seems', 1), ('she’s', 1), ('written,', 1), ('bench,', 1), ('her', 1), ('right,', 1), ('thinks', 1), ('Act', 1), ('Constitutional.', 1), ('struck', 1), ('happens?', 1), ('Women’s', 1), ('fundamentally', 1), ('changed.', 1), ('Once', 1), ('again,', 1), ('condition', 1), ('pregnancy.', 1), ('women', 1), ('exact', 1), ('procedure', 1), ('gets.And', 1), ('ended', 1), ('we,', 1), ('hundred', 1), ('conditions', 1), ('taken', 1), ('conditions,', 1), ('love', 1), ('this.', 1), ('appropriate', 1), ('wins', 1), ('Senate', 1), ('Republican,', 1), ('not,', 1), ('February.He’s', 1), ('elected', 1), ('election.That’s', 1), ('true.Open', 1), ('discussion.Number', 1), ('proposed.', 1), ('proposed', 1), ('expand', 1), ('any.', 1), ('debates', 1), ('23', 1), ('colleagues', 1), ('win', 1), ('nomination', 1), ('won,', 1), ('wanted', 1), ('allow', 1), ('private', 1), ('still.', 1), ('can.', 1), ('proposal.That', 1), ('lie.The', 1), ('party', 1), ('Right', 1), ('Party.I', 1), ('now.The', 1), ('platform', 1), ('I,', 1), ('of,', 1), ('Now,', 1), ('conditions.', 1), ('And,', 1), ('20,', 1), ('200', 1), ('mil-', 1), ('watch,', 1), ('survived?', 1), ('contracted', 1), ('mean', 1), ('strike', 1), ('Act?I’m', 1), ('this.You’re', 1), ('up.Let', 1), ('finish.', 1), ('Roe', 1), ('V.', 1), ('Wade.', 1), ('all-It’s', 1), ('court.In', 1), ('court.Donald', 1), ('quiet', 1), ('minute.All', 1), ('right.Good', 1), ('healthcare.Yes.It', 1), ('not.It', 1), ('qualify', 1), ('free', 1), ('States,', 1), ('except', 1), ('Governors', 1), ('deny', 1), ('Medicaid.', 1), ('Anyone', 1), ('qualifies', 1), ('Medicare,', 1), ('excuse', 1), ('automatically', 1), ('enrolled', 1), ('two.Look,', 1), ('hey.I’m', 1), ('listen', 1), ('Bernie', 1), ('Sanders.I', 1), ('hell', 1), ('lot.I’m', 1), ('standing', 1), ('facing', 1), ('old', 1), ('buddy.All', 1), ('do-Look', 1), ('lucky.', 1), ('lucky', 1), ('well.And', 1), ('sure.Because', 1), ('deal,', 1), ('lie.', 1), ('lies.', 1), ('Everybody', 1), ('liar.God,', 1), ('sure-No,', 1), ('that.The', 1), ('guy,', 1), ('night,', 1), ('time.There', 1), ('manifesto,', 1), ('one.Number', 1), ('two.Number', 1), ('two.I’ll', 1), ('what,', 1), ('needing', 1), ('healthcare.Because', 1), ('he,', 1), ('10', 1), ('employers', 1), ('getting', 1), ('eye', 1), ('Take', 1), ('away.He', 1), ('how.', 1), ('offered', 1), ('plan.He', 1), ('wishful', 1), ('thinking.', 1), ('Executive', 1), ('Orders', 1), ('lowered', 1), ('anybody.', 1), ('promising', 1), ('elected.', 1), ('none,', 1), ('else', 1), ('00:17:14].Sure.Whatever', 1), ('issue.', 1), ('speak.', 1), ('You’re', 1), ('strongly', 1), ('feel.Vote', 1), ('now.Make', 1), ('Senators.I’m', 1), ('question.Will', 1), ('up,', 1), ('man?This', 1), ('un-Presidential.That', 1), ('productive', 1), ('segment,', 1), ('it?', 1), ('Keep', 1), ('yapping,', 1), ('man.They', 1), ('do.Good', 1), ('luck.', 1), ('dead.', 1), ('infected', 1), ('We,', 1), ('4%', 1), ('population,', 1), ('20%', 1), ('deaths.', 1), ('40,000', 1), ('contracting', 1), ('750', 1), ('presented', 1), ('number,', 1), ('“It', 1), ('is.”', 1), ('are.', 1), ('February', 1), ('deadly', 1), ('disease.', 1), ('tape', 1), ('acknowledging', 1), ('warning', 1), ('panic', 1), ('panic.', 1), ('panicked.', 1), ('do?He', 1), ('ground', 1), ('Wuhan', 1), ('owe', 1), ('debt', 1), ('gratitude', 1), ('transparent', 1), ('us.', 1), ('then?', 1), ('waited.', 1), ('plan.I', 1), ('March,', 1), ('exactly', 1), ('again', 1), ('July,', 1), ('protective', 1), ('gear', 1), ('possible.', 1), ('House', 1), ('Open', 1), ('bunker', 1), ('sand', 1), ('trap', 1), ('course', 1), ('Oval', 1), ('Office', 1), ('fund', 1), ('lives.I', 1), ('job.', 1), ('done.14,000', 1), ('died,', 1), ('200,000.And', 1), ('…', 1), ('economy.', 1), ('because,', 1), ('morning', 1), ('empty', 1), ('chair', 1), ('kitchen', 1), ('table', 1), ('situation', 1), ('mom', 1), ('dad', 1), ('speak', 1), ('nurse', 1), ('holding', 1), ('phone', 1), ('goodbye?His', 1), ('lose', 1), ('year.', 1), ('wear', 1), ('numbers.', 1), ('notion', 1), ('Nor', 1), ('don’t.', 1), ('scientist.God.This', 1), ('you-…', 1), ('Easter,', 1), ('warm', 1), ('weather,', 1), ('it’d', 1), ('Miraculous,', 1), ('miracle.', 1), ('inject', 1), ('bleach', 1), ('arm,', 1), ('man.So', 1), ('Every', 1), ('company', 1), ('distribution', 1), ('occur', 1), ('sometime', 1), ('beginning', 1), ('pray', 1), ('will.', 1), ('Pray', 1), ('will.No', 1), ('puts', 1), ('pressure', 1), ('disagrees', 1), ('scientists.Everybody', 1), ('knows-Well,', 1), ('scientist.', 1), ('She', 1), ('the-Yes.', 1), ('scientists', 1), ('there,', 1), ('hospital', 1), ('Their', 1), ('depend', 1), ('way-By', 1), ('way-Do', 1), ('believe', 1), ('moment', 1), ('telling', 1), ('light', 1), ('lies', 1), ('relating', 1), ('acknowledged', 1), ('happening,', 1), ('February,', 1), ('record', 1), ('panicked', 1), ('stock', 1), ('two.', 1), ('guess', 1), ('what?', 1), ('die', 1), ('gets', 1), ('smarter,', 1), ('quicker-Oh,', 1), ('break.Well,', 1), ('let’s', 1), ('debate-Because', 1), ('You’ve', 1), ('reopen', 1), ('PPE,', 1), ('sanitation', 1), ('classic-Will', 1), ('shush', 1), ('minute?Nancy', 1), ('Pelosi', 1), ('Schumer,', 1), ('Senate.', 1), ('course.', 1), ('literally,', 1), ('Think', 1), ('it.You', 1), ('admitted', 1), ('you’d', 1), ('down.I', 1), ('that.I', 1), ('that.Just', 1), ('rally.Look,', 1), ('wherewithal', 1), ('provided', 1), ('money,', 1), ...]
trump_word_count = Counter(all_trump_words.split(' '))
trump_word_count.most_common()
[('the', 235), ('a', 182), ('you', 172), ('to', 161), ('and', 144), ('of', 119), ('I', 105), ('have', 92), ('it', 85), ('in', 80), ('that', 75), ('they', 56), ('is', 53), ('we', 50), ('And', 50), ('people', 49), ('was', 43), ('because', 42), ('at', 41), ('going', 40), ('They', 40), ('be', 39), ('want', 39), ('do', 38), ('don’t', 38), ('would', 36), ('with', 36), ('are', 34), ('We', 34), ('on', 34), ('not', 34), ('know', 34), ('what', 33), ('he', 33), ('You', 32), ('very', 31), ('look', 31), ('by', 29), ('had', 29), ('got', 29), ('were', 28), ('it’s', 28), ('me', 28), ('said', 27), ('about', 27), ('just', 27), ('think', 26), ('for', 26), ('but', 25), ('I’m', 25), ('if', 24), ('didn’t', 24), ('all', 24), ('our', 24), ('[crosstalk', 22), ('your', 21), ('down', 21), ('as', 20), ('it.', 20), ('done', 19), ('But', 19), ('tell', 18), ('say', 18), ('no', 18), ('them', 18), ('million', 17), ('It’s', 17), ('never', 17), ('from', 16), ('three', 16), ('like', 16), ('He', 16), ('out', 16), ('will', 15), ('go', 15), ('up', 15), ('did', 14), ('so', 14), ('that’s', 14), ('get', 14), ('can', 14), ('see', 14), ('back', 14), ('law', 14), ('their', 13), ('an', 13), ('where', 13), ('run', 13), ('shut', 13), ('has', 12), ('that.', 12), ('we’re', 12), ('when', 12), ('left', 12), ('If', 12), ('one', 12), ('than', 12), ('came', 12), ('So', 11), ('lot', 11), ('ever', 11), ('been', 11), ('The', 11), ('give', 11), ('far', 11), ('you’ve', 11), ('what’s', 11), ('made', 11), ('this', 11), ('over', 11), ('half', 11), ('right', 10), ('you,', 10), ('you’re', 10), ('they’re', 10), ('much', 10), ('I’ll', 10), ('call', 10), ('let', 10), ('They’re', 10), ('country', 10), ('there', 10), ('good', 9), ('other', 9), ('after', 9), ('way,', 9), ('doing', 9), ('or', 9), ('two', 9), ('which', 9), ('talking', 9), ('big', 9), ('could', 9), ('my', 9), ('more', 9), ('It', 9), ('country.', 9), ('I’ve', 9), ('these', 9), ('happened', 9), ('forest', 9), ('even', 8), ('Joe,', 8), ('Joe.', 8), ('we’ve', 8), ('now', 8), ('lost', 8), ('said,', 8), ('every', 7), ('election', 7), ('You’re', 7), ('military', 7), ('things', 7), ('put', 7), ('who', 7), ('closed', 7), ('take', 7), ('November', 7), ('went', 7), ('does', 7), ('New', 7), ('car', 7), ('can’t', 7), ('radical', 7), ('won', 6), ('election.', 6), ('In', 6), ('wouldn’t', 6), ('way', 6), ('it,', 6), ('President', 6), ('elected', 6), ('period', 6), ('years.', 6), ('wants', 6), ('military.', 6), ('Take', 6), ('well', 6), ('people.', 6), ('them.', 6), ('how', 6), ('too', 6), ('millions', 6), ('many', 6), ('that,', 6), ('We’ve', 6), ('me,', 6), ('also', 6), ('him', 6), ('name', 6), ('almost', 6), ('being', 6), ('states', 6), ('they’ve', 6), ('his', 6), ('That’s', 6), ('us', 6), ('dollars', 6), ('everything', 6), ('gave', 6), ('why', 6), ('ballots', 6), ('some', 5), ('time', 5), ('he’s', 5), ('great', 5), ('There’s', 5), ('problem', 5), ('probably', 5), ('aren’t', 5), ('As', 5), ('already', 5), ('years', 5), ('party', 5), ('doesn’t', 5), ('happening', 5), ('individual', 5), ('thing.', 5), ('first', 5), ('47', 5), ('year', 5), ('people,', 5), ('days', 5), ('last', 5), ('better', 5), ('then', 5), ('should', 5), ('died', 5), ('Trump', 5), ('bad', 5), ('political', 5), ('close', 5), ('through', 5), ('found', 5), ('whole', 5), ('When', 5), ('Because', 5), ('vice', 5), ('president', 5), ('any', 5), ('called', 5), ('sent', 5), ('end', 5), ('phenomenal', 4), ('really', 4), ('greatest', 4), ('up.', 4), ('happen', 4), ('concerned,', 4), ('time,', 4), ('We’re', 4), ('private', 4), ('happy', 4), ('Why', 4), ('me.', 4), ('rid', 4), ('him,', 4), ('coming', 4), ('paid', 4), ('agreed', 4), ('under', 4), ('good.', 4), ('make', 4), ('took', 4), ('away', 4), ('they’ll', 4), ('disaster.', 4), ('something', 4), ('answer', 4), ('years,', 4), ('much.', 4), ('in,', 4), ('thousands', 4), ('really,', 4), ('thing', 4), ('job', 4), ('companies', 4), ('to,', 4), ('use', 4), ('lowest', 4), ('economy', 4), ('down.', 4), ('those', 4), ('mask', 4), ('need', 4), ('wear', 4), ('open', 4), ('brought', 4), ('you’ll', 4), ('tax', 4), ('what,', 4), ('leave', 4), ('super', 4), ('group', 4), ('today', 4), ('day', 4), ('place.', 4), ('cars', 4), ('caught', 4), ('sending', 4), ('ballots.', 4), ('Chris.', 3), ('all.', 3), ('top', 3), ('fact,', 3), ('places.', 3), ('she', 3), ('all,', 3), ('He’s', 3), ('hundred', 3), ('point', 3), ('four', 3), ('totally', 3), ('wrong.', 3), ('here,', 3), ('nothing', 3), ('absolutely', 3), ('That', 3), ('most', 3), ('okay.', 3), ('surprised.', 3), ('getting', 3), ('drugs', 3), ('allow', 3), ('Governors', 3), ('Bernie', 3), ('saying', 3), ('is,', 3), ('Obamacare,', 3), ('Chris,', 3), ('pack', 3), ('Court', 3), ('nothing.', 3), ('talk', 3), ('By', 3), ('“President', 3), ('Democrat', 3), ('did.', 3), ('masks.', 3), ('haven’t', 3), ('them,', 3), ('months', 3), ('spoken', 3), ('lot.', 3), ('before', 3), ('set', 3), ('word', 3), ('what?', 3), ('something,', 3), ('built', 3), ('do,', 3), ('problems', 3), ('different', 3), ('down,', 3), ('do.', 3), ('record', 3), ('likes', 3), ('seen', 3), ('People', 3), ('couple', 3), ('This', 3), ('say,', 3), ('York.', 3), ('dollars.', 3), ('given', 3), ('Obama', 3), ('believe', 3), ('care', 3), ('done.', 3), ('slowest', 3), ('recovery', 3), ('since', 3), ('up,', 3), ('means', 3), ('became', 3), ('number', 3), ('son', 3), ('deserve', 3), ('fortune', 3), ('billion', 3), ('support', 3), ('place', 3), ('teaching', 3), ('happen.', 3), ('There', 3), ('Look', 3), ('anything.', 3), ('send', 3), ('A', 3), ('300', 3), ('judges', 3), ('128', 3), ('thrown', 3), ('air.', 3), ('forest.', 3), ('electric', 3), ('solicited', 3), ('ballot,', 3), ('ballot', 3), ('urging', 3), ('am', 3), ('Senate,', 2), ('respected', 2), ('way.', 2), ('her', 2), ('biggest', 2), ('Notre', 2), ('she’s', 2), ('plenty', 2), ('itself.', 2), ('election,', 2), ('know.', 2), ('anybody', 2), ('court.', 2), ('professor', 2), ('single', 2), ('long', 2), ('few', 2), ('Democrats,', 2), ('only', 2), ('difference', 2), ('pre-existing', 2), ('say.', 2), ('strongly,', 2), ('10', 2), ('so,', 2), ('during', 2), ('number.', 2), ('health', 2), ('Your', 2), ('socialist', 2), ('according', 2), ('308,000', 2), ('dying', 2), ('proper', 2), ('healthcare', 2), ('ban', 2), ('China,', 2), ('ballot?', 2), ('here', 2), ('have.', 2), ('course,', 2), ('worst', 2), ('part', 2), ('ask', 2), ('Let', 2), ('something.', 2), ('cutting', 2), ('drug', 2), ('against', 2), ('prices', 2), ('80', 2), ('destroying', 2), ('tiny', 2), ('left,', 2), ('gives', 2), ('socialized', 2), ('early', 2), ('graduated', 2), ('Go', 2), ('Sanders', 2), ('left.', 2), ('plan', 2), ('Obamacare', 2), ('fixed', 2), ('might', 2), ('choice', 2), ('mandate.', 2), ('is.', 2), ('destroyed', 2), ('shouldn’t', 2), ('blame', 2), ('matter', 2), ('cheaper', 2), ('Supreme', 2), ('Joe?', 2), ('understand,', 2), ('listened', 2), ('open,', 2), ('person', 2), ('China’s', 2), ('fault.', 2), ('numbers,', 2), ('China.', 2), ('racist', 2), ('thought', 2), ('Dr.', 2), ('Fauci', 2), ('Many', 2), ('job.”', 2), ('job.', 2), ('ventilators.', 2), ('fake', 2), ('press', 2), ('care.', 2), ('gotten', 2), ('Joe.Well,', 2), ('less', 2), ('behind', 2), ('Johnson', 2), ('&', 2), ('Johnson,', 2), ('sooner.', 2), ('disagree', 2), ('him.', 2), ('No,', 2), ('both', 2), ('vaccine', 2), ('spoke', 2), ('Delaware', 2), ('either', 2), ('Don’t', 2), ('smart', 2), ('Nancy', 2), ('keep', 2), ('shutting', 2), ('minute,', 2), ('second,', 2), ('anything', 2), ('Now', 2), ('very,', 2), ('learned', 2), ('Pennsylvania,', 2), ('certain', 2), ('reasons', 2), ('until', 2), ('here.', 2), ('social', 2), ('Every', 2), ('shows', 2), ('seen.', 2), ('They’ve', 2), ('“Masks', 2), ('okay', 2), ('show', 2), ('true.', 2), ('Nobody', 2), ('tremendous', 2), ('crowds,', 2), ('Joe', 2), ('negative', 2), ('China', 2), ('dead', 2), ('One', 2), ('into', 2), ('nobody’s', 2), ('again.', 2), ('destroy', 2), ('depression,', 2), ('saw', 2), ('hurting', 2), ('whatever', 2), ('look,', 2), ('Michigan,', 2), ('sad', 2), ('he’ll', 2), ('Our', 2), ('well,', 2), ('somebody', 2), ('come', 2), ('schools', 2), ('open.', 2), ('places', 2), ('football.', 2), ('it-…', 2), ('Ohio', 2), ('tax.', 2), ('know,', 2), ('have,', 2), ('dollars,', 2), ('pay', 2), ('person,', 2), ('building', 2), ('administration,', 2), ('man', 2), ('25', 2), ('fixing', 2), ('including', 2), ('taking', 2), ('boomed', 2), ('economic', 2), ('stock', 2), ('market', 2), ('goes', 2), ('jobs.', 2), ('COVID', 2), ('bring', 2), ('best', 2), ('you.', 2), ('ate', 2), ('takes', 2), ('billions', 2), ('makes', 2), ('fire', 2), ('important', 2), ('forgotten', 2), ('now,', 2), ('treated', 2), ('worse', 2), ('support.', 2), ('enforcement', 2), ('Portland,', 2), ('enforcement.', 2), ('words,', 2), ('lose', 2), ('won’t', 2), ('Chicago,', 2), ('cities', 2), ('order', 2), ('middle', 2), ('ended', 2), ('military,', 2), ('else.', 2), ('hundreds', 2), ('hate', 2), ('horrible', 2), ('Oakland.', 2), ('favor', 2), ('shot', 2), ('numbers', 2), ('supporters', 2), ('suburbs', 2), ('Oh,', 2), ('US', 2), ('that.I', 2), ('love', 2), ('National', 2), ('over.', 2), ('problem.', 2), ('wing', 2), ('name,', 2), ('stand', 2), ('Antifa', 2), ('throw', 2), ('administration', 2), ('despite', 2), ('Hillary', 2), ('Clinton,', 2), ('above', 2), ('calling', 2), ('maybe', 2), ('things.', 2), ('vets.', 2), ('judges,', 2), ('judges.', 2), ('openings', 2), ('little', 2), ('tens', 2), ('clean', 2), ('water', 2), ('businesses', 2), ('trees,', 2), ('trees', 2), ('old', 2), ('immaculate', 2), ('extent,', 2), ('California’s', 2), ('management,', 2), ('cities.', 2), ('major', 2), ('country,', 2), ('along', 2), ('expensive', 2), ('least', 2), ('out.', 2), ('too.', 2), ('Green', 2), ('out-…', 2), ('100', 2), ('does.', 2), ('statement', 2), ('tape.', 2), ('transition,', 2), ('won.', 2), ('back.', 2), ('wastepaper', 2), ('fraud', 2), ('losing', 2), ('counting', 2), ('ballots,', 2), ('hope', 2), ('vote.', 2), ('wrong', 2), ('watch.', 2), ('fair', 2), ('cheat.', 2), ('honest', 2), ('How', 1), ('doing?Thank', 1), ('much,', 1), ('simply.', 1), ('Elections', 1), ('consequences.', 1), ('White', 1), ('House,', 1), ('nominee', 1), ('Top,', 1), ('academic,', 1), ('Good', 1), ('endorsers', 1), ('liberal', 1), ('Dame', 1), ('fantastic.', 1), ('time.', 1), ('Even', 1), ('outstanding.', 1), ('She’s', 1), ('served', 1), ('feel', 1), ('Dame,', 1), ('highly', 1), ('student', 1), ('had.', 1), ('school.And', 1), ('therefore', 1), ('choose', 1), ('her,', 1), ('knowingly', 1), ('otherwise.', 1), ('they’d', 1), ('try', 1), ('faster.', 1), ('Merrick', 1), ('Garland,', 1), ('stopped.', 1), ('reverse,', 1), ('also.', 1), ('Definitely', 1), ('reverse.', 1), ('Chris.Thank', 1), ('Joe.There', 1), ('conditions.', 1), ('Okay,', 1), ('Justice', 1), ('Ginsburg', 1), ('powerfully,', 1), ('ago', 1), ('Senate', 1), ('President-During', 1), ('opening.', 1), ('bigger', 1), ('extinguish', 1), ('180', 1), ('care,', 1), ('this.Well,', 1), ('certainly', 1), ('socialist.', 1), ('socialist-That’s', 1), ('saying.Your', 1), ('medicine', 1), ('healthcare.And', 1), ('dominate', 1), ('that.Not', 1), ('Harris.Joe,', 1), ('couldn’t', 1), ('provide', 1), ('this.And', 1), ('200,', 1), ('late', 1), ('draw.', 1), ('heavily', 1), ('infected.', 1), ('Europe.You', 1), ('later,', 1), ('later.We’re', 1), ('people.You', 1), ('ballot.', 1), ('ballot.I', 1), ('so.There’s', 1), ('there.You', 1), ('view', 1), ('Roe', 1), ('V.', 1), ('Wade?', 1), ('view.That’s', 1), ('right.Because', 1), ('healthcare.Yes,', 1), ('Of', 1), ('mandate.Excuse', 1), ('mandate,', 1), ('chunk', 1), ('Obamacare.That', 1), ('Obamacare.Chris,', 1), ('Obamacare.Well,', 1), ('mandate', 1), ('unpopular', 1), ('aspect', 1), ('Obamacare.I', 1), ('protect', 1), ('people.Go', 1), ('ahead.Well,', 1), ('guess', 1), ('debating', 1), ('symbolic.', 1), ('prices.', 1), ('Favored', 1), ('Nations,', 1), ('courage', 1), ('pharma.', 1), ('Drug', 1), ('90%.', 1), ('government,', 1), ('Nobody’s', 1), ('healthcare.All', 1), ('done.I’ll', 1), ('example.', 1), ('Insulin,', 1), ('families,', 1), ('cost.', 1), ('cheap', 1), ('water,', 1), ('truth.', 1), ('cheap.', 1), ('doing.', 1), ('Prescription', 1), ('prices,', 1), ('countries', 1), ('buy', 1), ('fraction', 1), ('do.This', 1), ('stuff.That’s', 1), ('says,', 1), ('way.Joe,', 1), ('Sanders,', 1), ('who’s', 1), ('manifesto,', 1), ('medicine.Are', 1), ('agree?Not', 1), ('much.Not', 1), ('much.If', 1), ('Pocahontas', 1), ('primary.On', 1), ('Super', 1), ('Tuesday,', 1), ('lucky.With', 1), ('what?With', 1), ('what?But', 1), ('agree.', 1), ('liar.', 1), ('class', 1), ('class.You’d', 1), ('You’d', 1), ('ahead,', 1), ('Joe.Listen,', 1), ('manifesto.He', 1), ('left.You', 1), ('00:15:10],', 1), ('medicine.Who', 1), ('Bernie?No,', 1), ('lower', 1), ('price,', 1), ('good.I’ve', 1), ('it.We’ve', 1), ('extent.', 1), ('don’t,', 1), ('good.Obamacare', 1), ('on.', 1), ('guaranteed', 1), ('conditions,', 1), ('Listen,', 1), ('…', 1), ('make,', 1), ('badly?', 1), ('badly,', 1), ('importantly,', 1), ('help', 1), ('Okay.', 1), ('“You’ve', 1), ('well.”', 1), ('meeting', 1), ('expensive.', 1), ('Premiums', 1), ('high,', 1), ('work.', 1), ('better.Go', 1), ('ahead.Good.Of', 1), ('do.Are', 1), ('court?Are', 1), ('court?He', 1), ('question.Why', 1), ('question?', 1), ('new', 1), ('Justices.', 1), ('Radical', 1), ('left.Listen,', 1), ('list,', 1), ('Who’s', 1), ('list?He’s', 1), ('list.The', 1), ('Joe.47', 1), ('understand.Wrong.Wrong.It’s', 1), ('wrong.So,', 1), ('you.If', 1), ('would’ve', 1), ('wide', 1), ('died,', 1), ('200,000.', 1), ('happened.', 1), ('stopped', 1), ('And,', 1), ('Russia.', 1), ('India.', 1), ('exactly', 1), ('straight', 1), ('count,', 1), ('understand.', 1), ('done,', 1), ('“He’s', 1), ('xenophobic.', 1), ('xenophobic,”', 1), ('Wait', 1), ('minute.You', 1), ('terrible.', 1), ('another', 1), ('months.', 1), ('early,', 1), ('saved', 1), ('lives.”', 1), ('worked', 1), ('Governor.', 1), ('Oh', 1), ('look.', 1), ('Most', 1), ('necessarily', 1), ('side', 1), ('gowns.', 1), ('weeks', 1), ('vaccine.', 1), ('therapeutics', 1), ('already.', 1), ('Fewer', 1), ('sick.', 1), ('Far', 1), ('fewer', 1), ('dying.', 1), ('job.The', 1), ('job,', 1), ('news,', 1), ('news.', 1), ('press,', 1), ('unfortunately.', 1), ('used', 1), ('blood.', 1), ('could’ve', 1), ('Swine', 1), ('Flu.', 1), ('H1-N1,', 1), ('own', 1), ('Chief', 1), ('Staff', 1), ('disaster.A', 1), ('lethal', 1), ('disease,', 1), ('way.We', 1), ('late.', 1), ('Joe.You', 1), ('trust', 1), ('Pfizer?Well,', 1), ('rather', 1), ('save', 1), ('lives.It', 1), ('Pfizer,', 1), ('speak', 1), ('Moderna,', 1), ('others.', 1), ('faster', 1), ('become', 1), ('left…', 1), ('Or', 1), ('them.I', 1), ('there,', 1), ('office', 1), ('ago.Because', 1), ('possibility', 1), ('we’ll', 1), ('1st.', 1), ('that.Well,', 1), ('deliver', 1), ('away.', 1), ('Logistically,', 1), ('delivers', 1), ('soldiers', 1), ('200,000', 1), ('day.', 1), ('delivering-It’s', 1), ('up.That', 1), ('sarcastically,', 1), ('sarcastically.You’ll', 1), ('sooner', 1), ('that.We', 1), ('scientists', 1), ('charge-…', 1), ('soon.Did', 1), ('smart?', 1), ('State,', 1), ('forgot', 1), ('college.', 1), ('State.', 1), ('class.', 1), ('word.Because', 1), ...]
set_biden = set(all_biden_words.split(' '))
set_trump = set(all_trump_words.split(' '))
print(len(set_biden))
print(len(set_trump))
1827 1890
set_biden
{'You-', 'hell', 'kids', 'testify,', 'market.', 'penny', 'warming.', 'healthcare.Yes.It', 'students', 'prevailing', 'afraid', '10', 'Accord.', 'talk', 'for', 'panic', 'constitution.', 'Chrysler', 'started.', 'prosecuted', 'Conway.She', 'year.', 'having', 'racists', 'bench,', 'also', 'lucky', 'Keep', 'acknowledged', 'No', 'went', '91', 'psychologist', 'taken', 'help.Because', 'speaking', 'good-paying', 'millions', 'trust', '00:08:48].No', 'That', 'that.I', 'civil', 'Medicaid.', 'many', 'happen,', 'doesn’t', 'lost', 'happening,', 'Bernie', 'deadly', 'serious', 'view', '“No,', 'president', 'spends', 'discredited.That', 'torn', 'respond', 'here.', 'power.', 'waited.', 'our', 'person.', 'the-', 'what?', 'segment,', 'no,', 'gasoline', 'ripped', 'wrong,', 'states.', 'you’ve', 'apples.', 'debates', 'here', 'schools', 'Michigan.', 'clear.', 'eyes,', 'group', 'votes,', 'doing.', 'two', '20,', 'years.', 'disease.', 'healthcare.He', '00:24:25]This', 'taxes.', 'declared', 'hole-…', '4%', '01:05:32]…', 'it?', 'go', 'mom', 'trouble.Look,', 'This', 'media,', 'bad', 'foreign', 'tune', '00:16:04]?Yeah,', 'threat', 'never', 'fine.', '“There', 'mileage', 'working', 'only', 'military', 'up.You’re', 'same', 'said.Every', 'simply', 'bleach', 'Governors', 'admitted', 'true.That’s', 'insults', 'puppy.', 'right', 'social', 'still', 'Women’s', 'early.', 'President.Now,', 'aren’t', 'true.None', 'renewable', '00:59:17]', 'why', 'said-Yes,', 'down', 'contracted', 'wishful', 'were', 'lucky.', 'thirdly,', 'Methane.', 'counties', 'person,', 'died', 'killed.', 'feelings,', 'know,', 'nothing.', '$400', 'state,', 'who,', 'billions', 'who', 'Figure', 'contracting', 'of,', 'those', 'businesses.', 'Claymont', 'enforcement', 'that.He', 'legitimate.Mail', 'new', 'reporter', 'crisis.', 'better', 'saying,', '01:07:24]-Yes.', 'pay', 'are.', 'accountable', 'all,', 'question,', 'Excuse', 'Wuhan', 'budget', 'Scranton.', 'me?No,', 'weather,', 'whatever', 'Nor', 'regard', 'wants', 'entire', 'means', 'Act', 'falling', 'day.', 'tens', 'liar.God,', 'countries', 'feel.Vote', 'shouldn’t', 'two.Look,', 'said,', 'wanted', 'companies', 'blew', 'hundred', 'education', 'your', 'sense', 'of.', '00:04:44].Yeah.The', 'may-Yeah,', 'bile', 'qualifies', 'lives.', '$1', 'Stop', 'two.', 'man.They', 'government', 'one.', 'run', 'conditions', 'why?', 'opened', 'Well,', 'took', 'automobiles', 'Party.I', 'you’d', 'election.That’s', 'let', 'depression', 'Wall', 'rally.Look,', 'idea', 'African', 'answer,', 'Senators', 'their', 'dying.', 'Just', 'energy.', 'like,', 'Many', 'All', 'coal', 'do.', 'iwillvote.com,', 'standards', '21%.', 'plan.', 'another', 'America.', 'under', 'votes-I', 'committed', 'majority', '00:24:32]', 'disastrous', '“It', 'between', 'help', 'focused', 'proposal.Yeah,', 'court.Donald', 'true.It', 'cheaper', 'screwing', 'anti-Semitic', '200', 'deal-…', 'Vote,', 'fool', 'we,', 'calm', 'scientist.', '500', 'worked', 'way.And', 'okay.”', 'true.Look,', 'appropriate,', 'wins', 'people.', 'knows', 'African-American', 'anything.Under', 'finish.Not', 'world,', 'die', 'whistle,', 'Biden', 'faith.', 'got', 'us,', 'trouble', 'employers', 'masks', 'up', 'in', 'right.Good', 'day', 'fire', 'election.', 'incentives', 'Mr.', 'V.', 'would', 'bunker', 'needing', 'relationship', 'turn.I', 'option.', 'teachers', 'trying', 'Good', 'woman', 'son,', 'save', 'emit', 'evidence', 'federal,', 'chiefs,', 'His', 'Roe', 'classic-Will', 'Scranton', 'meet', 'rantings', 'effect.', 'additional', 'Come', '00:24:05]That', 'Care', 'putting', 'rallies', 'carrying', 'Miraculous,', 'Billionaires', 'two.Number', 'America,', 'More', 'numbers.', 'radical', 'debate-Because', 'say,', 'it’d', 'smarter,', 'Floyd.', 'law.', 'them', '00:55:51]-No.That', 'able', 'support', 'People', 'offered', 'across', 'Suburbs', 'proud', 'It’s', 'school', 'young', 'governing', 'Nothing.', 'protective', 'Service', 'basically', 'peaceful', 'give', 'steel,', 'vaccine', 'light', 'situation', 'asked', 'resent-I’m', 'friends', 'excuse', 'running', 'Florida,', 'polluting', '23', 'dollars.Because', 'Senate.', 'jobs.', 'protest', 'way-Do', 'court', 'else', 'cuts.And', 'somehow', 'Stand', 'apart.', 'coming', 'none,', 'dog', 'Nobody’s', 'recovery', 'for,', '“I’m', 'pressure', 'stay', 'socially', 'rid', 'Democrats', 'all?', 'Director', 'qualify', 'said', 'years,', 'number,', 'Pray', 'poll', 'CDC', 'mask', 'matter', 'manifesto,', 'irresponsible', 'administration.', 'this', 'America', 'true.', 'different', 'mean', 'grow', 'safe.People', 'clown.', 'Sanders.I', 'racist', 'know', 'way,', 'this.', 'heroes.And', 'PPE,', 'tell', 'morning', '15%', 'her', 'sicker,', 'come', 'eye', 'infected', 'probably', 'And,', 'not-Not', 'wasn’t', 'methane', 'we’ve', 'guy-We', 'was', 'past,', 'seems', 'occur,', 'elected', 'infrastructure', 'mask.', 'President-', '750', 'old', 'because,', 'men', 'significantly', 'violent', 'nominee', 'decency.', 'anything.I', 'Fewer', 'hour,', 'exact', 'is.', 'plan,', 'large', 'poor', 'body', 'family’s', 'plan', 'actually', 'Americans', 'totally', 'military…', 'Accord.For', 'night.', 'fund', 'single', 'soldiers.By', 'Senators.I’m', 'facing', 'it.Yeah,', 'still.', 'defunding', 'matters.No', 'analysis', 'table', 'bring', 'create', 'away', 'healthcare', 'cars', 'people.Look-…', 'Deal.Prepare', 'being', 'watch.He', 'themselves', 'you', '500,000', 'floods,', 'as', '200,000', 'phone', 'code', 'happen', 'saying', 'all', 'fleet', 'stations', 'issue', 'true.Is', 'Star.', 'require', 'truth.', 'absolutely', 'Green', 'back', 'literally,', 'chair', '00:58:14]', 'approved', 'gratitude', 'done.14,000', 'world’s', 'point,', 'bulging,', 'real', 'Irish', 'true.We', 'nation,', 'fundamentally', 'things', 'oil', 'administration', 'ask', 'That’s', 'person', 'hole.', 'service', 'answer', 'couldn’t', 'healthcare.Because', 'including', 'votes', 'quickly,', 'occurs', 'done.', 'don’t,', 'more', 'no', 'constantly', 'highways', 'COVID?', 'first', 'gigantic', 'torches,', 'demeaning', 'miracle.', 'rising', 'which', 'Manufacturing', 'point.It’s', 'risk', '1000', 'population,', 'established', 'open', 'suburbs.', 'already-And', 'opposed', 'ships,', 'some', 'watchers', 'weapon', 'trap', 'fact', 'last', 'discredited.My', 'not…', 'sufficient', 'mistake', 'just', 'office,', 'counting', 'forward.', 'July,', 'policy.', 'Floyd', 'cuts.', 'dying', 'stock', 'not.', 'deaths', 'true.And', 'about.I', 'concerned', 'anyone', 'Peaceful', 'spend', 'changed', 'Schumer,', 'that’ll', '17%,', 'suburb', 'women.', 'warm', 'perfected', 'at', 'racial', 'safer.', 'one,', 'Hispanic', 'appropriate.', 'guy,', 'Act?I’m', 'lives,', 'they', 'line.', 'inherited', 'Those', 'United', 'allies.By', 'want', 'ridiculous.Absolutely', 'overtaking', 'proposal.That', '1950.', 'Some', 'dangerous', 'police', 'issue.', 'oil.', 'tested?', 'I’d', 'true.Not', 'related', 'me.', 'You,', 'what’s', 'talking', 'written', 'spokesperson', 'laid', 'will…', 'final', 'justice,', 'pieces', 'distribution', 'wouldn’t', 'problems', 'And', '$300', 'Once', 'buddy.All', 'distanced', 'relaxed', 'much', 'loser.', 'American', 'end', 'billion', 'came', 'she’s', 'enforced.', 'determine', 'time', 'remember', 'Breonna', 'Barisma-He', 'rest', 'anything.', 'use', 'outcome.', '00:17:14].Sure.Whatever', 'bit', 'costs', 'emergency.', 'manufacturing', 'this.The', 'correct', 'thrown', 'standing', 'color.', '00:15:43].The', 'not.It', 'protest.Nobody’s', 'caused', 'person.He', 'Instead', 'true.My', 'fields,', 'going', 'Klan.', 'looked', 'now,', 'safely.', 'raised', 'lot', 'settle', 'died,', 'ballot', 'home.', '$750', 'hurricanes,', 'done', 'can-by', 'respond.', 'crisis', 'corporate', 'living', 'Tens', 'proposed', 'vehicles.', 'record', '00:48:23]', 'when…', 'office.', 'officers,', 'Accord', 'anybody.', 'States.', 'instead', 'through', 'family.', 'speak.', 'build', 'up,', 'that-Play', 'three.No.This', 'minute?Nancy', 'fact.It’s', 'economy,', 'count', 'Republican,', 'absorbed', 'Affordable', 'automatically', 'me,', 'then', 'scientists.Everybody', 'driving', 'this.”', 'over.', 'act,', 'Republican', 'a-', 'that-The', 'crime-I’m', 'be…That', 'my', 'disagrees', 'very', 'groups,', 'anymore.', 'believe', 'mask,', 'lines.', 'maybe', 'guy-', 'early', 'eliminate', 'Bible.', 'on', 'Catholics,', 'opportunity', 'does,', 'up.Let', 'own', 'Now,', 'during', 'divided.', 'itself', 'carbon', 'occur', 'generate', 'without', 'warning', 'open?', 'Act,', 'She', 'affidavit.', 'sure', 'private', 'acknowledging', 'worst', 'show', 'such', 'stake', 'Bishop', 'possible.', 'Medal.', 'election', 'down,', 'you-…', 'insisting', 'Beau', 'Desk', 'savior', 'counted,', 'plan.I', 'Hunter?That’s', 'listen', 'aware', 'man?This', 'even', 'decide', 'walk', 'guess', 'break.Well,', 'see', 'all-It’s', 'happen.', 'pre-existing', 'and/or', 'Look,', 'sorted', 'hatred,', 'since', 'heat', 'worried', 'You', 'insensitivity.', 'ridiculous.Violent', 'distance.', 'steel.', 'What', 'elect', 'discussion.Number', 'does', 'people,', 'is.”', 'drug', 'encouraged', 'honest.', 'integrated.', 'man?I’m', 'economic', 'How', 'He', 'director,', 'divided', 'because', 'pregnancy.', 'growth,', 'Close', 'former', 'should', 'safe.Show', 'one.Number', 'costing', 'forest.', 'yapping,', 'order', 'one’s', 'change,', 'art', '“Here’s', 'wore', 'spent', 'wait.', 'pray', 'veins', 'race', 'First', 'I.Why', 'rile', 'plants-Pardon', 'thought.', 'he', 'Biden,', 'way', 'state', 'black', 'country', 'Court', 'left', 'statements', 'Vice-That', 'community.I’ve', 'expand', 'walked', 'it', 'wherewithal', 'reason.So', 'environment', 'little', 'give,', 'Oval', 'pointed', 'clear', 'hurricanes.', 'telling', 'did,', 'cops', 'that.', 'sometime', 'discredited.', 'down.I', 'War,', 'enrolled', 'zero,', 'written,', '15', 'that.Just', 'thoroughly', 'dotting', 'pays', 'don’t', 'Democrats.', 'company', 'States', 'In', 'returns.Show', 'problem.', 'It', 'country,', 'oath', 'totally-Totally', 'today.', 'matter,', 'lies.', 'fine', 'economy-Let', 'family,', 'weaker,', 'businesses', 'equality', 'organization-…', 'ran', 'hard', 'outcome', 'nuclear', 'plant', 'Patriot', 'company-By', 'winner', 'Homeland', 'well', '28%.', 'nomination', 'look', 'back?', 'recession.', 'me', 'police,', 'Deal', 'two,', 'poor,', 'China', 'shush', 'point', 'House', 'where', 'Trump', 'charge', 'offices.', 'money,', 'well.', 'four', 'weatherized', 'this-', 'us', 'exist', 'was.', 'done-The', 'the-Yes.', 'time.There', 'Security', 'strike', '…', 'profligate', 'voting', 'can', 'smart', 'delivers', 'folks', 'jobs', 'trillion', 'will', 'assistance.', '00:23:57]Well,', 'church', 'January,', 'storms', 'seventh,', 'scientist.God.This', 'need.', 'quiet', 'up?', 'They', 'by', 'job', 'Putin’s', 'every', 'whole', 'division.This', 'fact,', 'held', 'gathering', 'March,', 'dollars.', ...}
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-137-4334b5c4db64> in <module> ----> 1 targets.get_text() ~/.pyenv/versions/3.7.3/lib/python3.7/site-packages/bs4/element.py in __getattr__(self, key) 2164 """Raise a helpful exception to explain a common code fix.""" 2165 raise AttributeError( -> 2166 "ResultSet object has no attribute '%s'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?" % key 2167 ) AttributeError: ResultSet object has no attribute 'get_text'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?
for t in targets:
print(t.find('a').get_text())
01:20 02:10 02:49 02:51 02:51 03:11 04:01 04:53 05:22 05:29 05:34 05:36 06:12 07:08 07:34 08:01 08:02 08:24 08:25 08:29 08:31 08:32 08:33 08:58 09:00 09:02 09:05 09:08 09:09 09:11 09:12 09:39 09:47 09:48 09:58 10:00 10:04 10:04 10:05 10:06 10:11 10:25 10:31 10:32 10:33 10:34 10:35 10:36 10:40 10:51 10:51 11:05 11:05 11:07 11:08 11:11 11:11 11:25 11:26 11:28 11:31 11:32 11:35 11:36 11:38 11:38 11:44 11:44 11:46 11:52 11:53 12:16 12:40 12:40 12:41 12:42 13:03 13:04 13:06 13:17 13:17 13:23 13:25 13:26 13:29 13:32 13:57 14:04 14:05 14:06 14:10 14:10 14:12 14:12 14:14 14:17 14:18 14:21 14:23 14:23 14:25 14:25 14:34 14:41 14:43 14:44 14:46 14:47 14:51 14:55 14:57 14:58 14:58 14:59 15:01 15:13 15:14 15:20 15:21 15:41 15:45 15:46 15:47 15:49 15:54 15:59 16:42 16:45 16:45 16:47 16:48 16:50 16:52 16:52 17:13 17:15 17:16 17:55 18:05 18:07 18:08 18:09 18:12 18:17 18:18 18:18 18:20 18:23 18:25 18:25 18:27 18:30 18:35 18:37 18:37 18:40 19:33 20:30 20:43 20:43 20:57 20:57 20:57 20:57 21:30 21:31 21:31 22:06 22:07 22:54 23:15 23:18 23:25 23:27 23:32 23:33 23:57 24:03 24:25
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-143-f33b47045dac> in <module> 1 for t in targets: ----> 2 print(t.find('a').get_text()) AttributeError: 'NoneType' object has no attribute 'get_text'
[]