25个值得收藏的Python文本处理案例

# pip install PyPDF2  安装 PyPDF2
import PyPDF2
from PyPDF2 import PdfFileReader
 
# Creating a pdf file object.
pdf = open("test.pdf", "rb")
 
# Creating pdf reader object.
pdf_reader = PyPDF2.PdfFileReader(pdf)
 
# Checking total number of pages in a pdf file.
print("Total number of Pages:", pdf_reader.numPages)
 
# Creating a page object.
page = pdf_reader.getPage(200)
 
# Extract data from a specific page number.
print(page.extractText())
 
# Closing the object.
pdf.close()

# pip install python-docx  安装 python-docx


import docx
 
 
def main():
    try:
        doc = docx.Document('test.docx')  # Creating word reader object.
        data = ""
        fullText = []
        for para in doc.paragraphs:
            fullText.append(para.text)
            data = '\n'.join(fullText)
 
        print(data)
 
    except IOError:
        print('There was an error opening the file!')
        return
 
 
if __name__ == '__main__':
    main()

# pip install bs4  安装 bs4

from urllib.request import Request, urlopen
from bs4 import BeautifulSoup
 
req = Request('http://www.cmegroup.com/trading/products/#sortField=oi&sortAsc=false&venues=3&page=1&cleared=1&group=1',
              headers={'User-Agent': 'Mozilla/5.0'})
 
webpage = urlopen(req).read()
 
# Parsing
soup = BeautifulSoup(webpage, 'html.parser')
 
# Formating the parsed html file
strhtm = soup.prettify()
 
# Print first 500 lines
print(strhtm[:500])
 
# Extract meta tag value
print(soup.title.string)
print(soup.find('meta', attrs={'property':'og:description'}))
 
# Extract anchor tag value
for x in soup.find_all('a'):
    print(x.string)
 
# Extract Paragraph tag value    
for x in soup.find_all('p'):
    print(x.text)

import requests
import json

r = requests.get("https://support.oneskyapp.com/hc/en-us/article_attachments/202761727/example_2.json")
res = r.json()

# Extract specific node content.
print(res['quiz']['sport'])

# Dump data as string
data = json.dumps(res)
print(data)

import csv

with open('test.csv','r') as csv_file:
    reader =csv.reader(csv_file)
    next(reader) # Skip first row
    for row in reader:
        print(row)

import re
import string
 
data = "Stuning even for the non-gamer: This sound track was beautiful!\
It paints the senery in your mind so well I would recomend\
it even to people who hate vid. game music! I have played the game Chrono \
Cross but out of all of the games I have ever played it has the best music! \
It backs away from crude keyboarding and takes a fresher step with grate\
guitars and soulful orchestras.\
It would impress anyone who cares to listen!"
 
# Methood 1 : Regex
# Remove the special charaters from the read string.
no_specials_string = re.sub('[!#?,.:";]', '', data)
print(no_specials_string)
 
 
# Methood 2 : translate()
# Rake translator object
translator = str.maketrans('', '', string.punctuation)
data = data.translate(translator)
print(data)

from nltk.corpus import stopwords
 
 
data = ['Stuning even for the non-gamer: This sound track was beautiful!\
It paints the senery in your mind so well I would recomend\
it even to people who hate vid. game music! I have played the game Chrono \
Cross but out of all of the games I have ever played it has the best music! \
It backs away from crude keyboarding and takes a fresher step with grate\
guitars and soulful orchestras.\
It would impress anyone who cares to listen!']
 
# Remove stop words
stopwords = set(stopwords.words('english'))
 
output = []
for sentence in data:
    temp_list = []
    for word in sentence.split():
        if word.lower() not in stopwords:
            temp_list.append(word)
    output.append(' '.join(temp_list))
 
 
print(output)

from textblob import TextBlob

data = "Natural language is a cantral part of our day to day life, and it's so antresting to work on any problem related to langages."

output = TextBlob(data).correct()
print(output)

import nltk
from textblob import TextBlob


data = "Natural language is a central part of our day to day life, and it's so interesting to work on any problem related to languages."

nltk_output = nltk.word_tokenize(data)
textblob_output = TextBlob(data).words

print(nltk_output)
print(textblob_output)

from nltk.stem import PorterStemmer
 
st = PorterStemmer()
text = ['Where did he learn to dance like that?',
        'His eyes were dancing with humor.',
        'She shook her head and danced away',
        'Alex was an excellent dancer.']
 
output = []
for sentence in text:
    output.append(" ".join([st.stem(i) for i in sentence.split()]))
 
for item in output:
    print(item)
 
print("-" * 50)
print(st.stem('jumping'), st.stem('jumps'), st.stem('jumped'))

from nltk.stem import WordNetLemmatizer

wnl = WordNetLemmatizer()
text = ['She gripped the armrest as he passed two cars at a time.',
        'Her car was in full view.',
        'A number of cars carried out of state license plates.']

output = []
for sentence in text:
    output.append(" ".join([wnl.lemmatize(i) for i in sentence.split()]))

for item in output:
    print(item)

print("*" * 10)
print(wnl.lemmatize('jumps', 'n'))
print(wnl.lemmatize('jumping', 'v'))
print(wnl.lemmatize('jumped', 'v'))

print("*" * 10)
print(wnl.lemmatize('saddest', 'a'))
print(wnl.lemmatize('happiest', 'a'))
print(wnl.lemmatize('easiest', 'a'))

import nltk
from nltk.corpus import webtext
from nltk.probability import FreqDist
 
nltk.download('webtext')
wt_words = webtext.words('testing.txt')
data_analysis = nltk.FreqDist(wt_words)
 
# Let's take the specific words only if their frequency is greater than 3.
filter_words = dict([(m, n) for m, n in data_analysis.items() if len(m) > 3])
 
for key in sorted(filter_words):
    print("%s: %s" % (key, filter_words[key]))
 
data_analysis = nltk.FreqDist(filter_words)
 
data_analysis.plot(25, cumulative=False)

import nltk
from nltk.corpus import webtext
from nltk.probability import FreqDist
from wordcloud import WordCloud
import matplotlib.pyplot as plt
 
nltk.download('webtext')
wt_words = webtext.words('testing.txt')  # Sample data
data_analysis = nltk.FreqDist(wt_words)
 
filter_words = dict([(m, n) for m, n in data_analysis.items() if len(m) > 3])
 
wcloud = WordCloud().generate_from_frequencies(filter_words)
 
# Plotting the wordcloud
plt.imshow(wcloud, interpolation="bilinear")
 
plt.axis("off")
(-0.5, 399.5, 199.5, -0.5)
plt.show()

import nltk
from nltk.corpus import webtext
from nltk.probability import FreqDist
from wordcloud import WordCloud
import matplotlib.pyplot as plt
 
words = ['data', 'science', 'dataset']
 
nltk.download('webtext')
wt_words = webtext.words('testing.txt')  # Sample data
 
points = [(x, y) for x in range(len(wt_words))
          for y in range(len(words)) if wt_words[x] == words[y]]
 
if points:
    x, y = zip(*points)
else:
    x = y = ()
 
plt.plot(x, y, "rx", scalex=.1)
plt.yticks(range(len(words)), words, color="b")
plt.ylim(-1, len(words))
plt.title("Lexical Dispersion Plot")
plt.xlabel("Word Offset")
plt.show()

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
 
# Sample data for analysis
data1 = "Java is a language for programming that develops a software for several platforms. A compiled code or bytecode on Java application can run on most of the operating systems including Linux, Mac operating system, and Linux. Most of the syntax of Java is derived from the C++ and C languages."
data2 = "Python supports multiple programming paradigms and comes up with a large standard library, paradigms included are object-oriented, imperative, functional and procedural."
data3 = "Go is typed statically compiled language. It was created by Robert Griesemer, Ken Thompson, and Rob Pike in 2009. This language offers garbage collection, concurrency of CSP-style, memory safety, and structural typing."
 
df1 = pd.DataFrame({'Java': [data1], 'Python': [data2], 'Go': [data2]})
 
# Initialize
vectorizer = CountVectorizer()
doc_vec = vectorizer.fit_transform(df1.iloc[0])
 
# Create dataFrame
df2 = pd.DataFrame(doc_vec.toarray().transpose(),
                   index=vectorizer.get_feature_names())
 
# Change column headers
df2.columns = df1.columns
print(df2)

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer

# Sample data for analysis
data1 = "Java is a language for programming that develops a software for several platforms. A compiled code or bytecode on Java application can run on most of the operating systems including Linux, Mac operating system, and Linux. Most of the syntax of Java is derived from the C++ and C languages."
data2 = "Python supports multiple programming paradigms and comes up with a large standard library, paradigms included are object-oriented, imperative, functional and procedural."
data3 = "Go is typed statically compiled language. It was created by Robert Griesemer, Ken Thompson, and Rob Pike in 2009. This language offers garbage collection, concurrency of CSP-style, memory safety, and structural typing."

df1 = pd.DataFrame({'Java': [data1], 'Python': [data2], 'Go': [data2]})

# Initialize
vectorizer = TfidfVectorizer()
doc_vec = vectorizer.fit_transform(df1.iloc[0])

# Create dataFrame
df2 = pd.DataFrame(doc_vec.toarray().transpose(),
                   index=vectorizer.get_feature_names())

# Change column headers
df2.columns = df1.columns
print(df2)

import nltk
from nltk.util import ngrams

# Function to generate n-grams from sentences.
def extract_ngrams(data, num):
    n_grams = ngrams(nltk.word_tokenize(data), num)
    return [ ' '.join(grams) for grams in n_grams]

data = 'A class is a blueprint for the object.'

print("1-gram: ", extract_ngrams(data, 1))
print("2-gram: ", extract_ngrams(data, 2))
print("3-gram: ", extract_ngrams(data, 3))
print("4-gram: ", extract_ngrams(data, 4))

from textblob import TextBlob
 
# Function to generate n-grams from sentences.
def extract_ngrams(data, num):
    n_grams = TextBlob(data).ngrams(num)
    return [ ' '.join(grams) for grams in n_grams]
 
data = 'A class is a blueprint for the object.'
 
print("1-gram: ", extract_ngrams(data, 1))
print("2-gram: ", extract_ngrams(data, 2))
print("3-gram: ", extract_ngrams(data, 3))
print("4-gram: ", extract_ngrams(data, 4))

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
 
# Sample data for analysis
data1 = "Machine language is a low-level programming language. It is easily understood by computers but difficult to read by people. This is why people use higher level programming languages. Programs written in high-level languages are also either compiled and/or interpreted into machine language so that computers can execute them."
data2 = "Assembly language is a representation of machine language. In other words, each assembly language instruction translates to a machine language instruction. Though assembly language statements are readable, the statements are still low-level. A disadvantage of assembly language is that it is not portable, because each platform comes with a particular Assembly Language"
 
df1 = pd.DataFrame({'Machine': [data1], 'Assembly': [data2]})
 
# Initialize
vectorizer = CountVectorizer(ngram_range=(2, 2))
doc_vec = vectorizer.fit_transform(df1.iloc[0])
 
# Create dataFrame
df2 = pd.DataFrame(doc_vec.toarray().transpose(),
                   index=vectorizer.get_feature_names())
 
# Change column headers
df2.columns = df1.columns
print(df2)

from textblob import TextBlob

#Extract noun
blob = TextBlob("Canada is a country in the northern part of North America.")

for nouns in blob.noun_phrases:
    print(nouns)

import numpy as np
import nltk
from nltk import bigrams
import itertools
import pandas as pd
 
 
def generate_co_occurrence_matrix(corpus):
    vocab = set(corpus)
    vocab = list(vocab)
    vocab_index = {word: i for i, word in enumerate(vocab)}
 
    # Create bigrams from all words in corpus
    bi_grams = list(bigrams(corpus))
 
    # Frequency distribution of bigrams ((word1, word2), num_occurrences)
    bigram_freq = nltk.FreqDist(bi_grams).most_common(len(bi_grams))
 
    # Initialise co-occurrence matrix
    # co_occurrence_matrix[current][previous]
    co_occurrence_matrix = np.zeros((len(vocab), len(vocab)))
 
    # Loop through the bigrams taking the current and previous word,
    # and the number of occurrences of the bigram.
    for bigram in bigram_freq:
        current = bigram[0][1]
        previous = bigram[0][0]
        count = bigram[1]
        pos_current = vocab_index[current]
        pos_previous = vocab_index[previous]
        co_occurrence_matrix[pos_current][pos_previous] = count
    co_occurrence_matrix = np.matrix(co_occurrence_matrix)
 
    # return the matrix and the index
    return co_occurrence_matrix, vocab_index
 
 
text_data = [['Where', 'Python', 'is', 'used'],
             ['What', 'is', 'Python' 'used', 'in'],
             ['Why', 'Python', 'is', 'best'],
             ['What', 'companies', 'use', 'Python']]
 
# Create one list using many lists
data = list(itertools.chain.from_iterable(text_data))
matrix, vocab_index = generate_co_occurrence_matrix(data)
 
 
data_matrix = pd.DataFrame(matrix, index=vocab_index,
                             columns=vocab_index)
print(data_matrix)

from textblob import TextBlob


def sentiment(polarity):
    if blob.sentiment.polarity < 0:
        print("Negative")
    elif blob.sentiment.polarity > 0:
        print("Positive")
    else:
        print("Neutral")


blob = TextBlob("The movie was excellent!")
print(blob.sentiment)
sentiment(blob.sentiment.polarity)

blob = TextBlob("The movie was not bad.")
print(blob.sentiment)
sentiment(blob.sentiment.polarity)

blob = TextBlob("The movie was ridiculous.")
print(blob.sentiment)
sentiment(blob.sentiment.polarity)

import goslate

text = "Comment vas-tu?"

gs = goslate.Goslate()

translatedText = gs.translate(text, 'en')
print(translatedText)

translatedText = gs.translate(text, 'zh')
print(translatedText)

translatedText = gs.translate(text, 'de')
print(translatedText)

from textblob import TextBlob
 
blob = TextBlob("Comment vas-tu?")
 
print(blob.detect_language())
 
print(blob.translate(to='es'))
print(blob.translate(to='en'))
print(blob.translate(to='zh'))

from textblob import TextBlob
from textblob import Word
 
text_word = Word('safe')
 
print(text_word.definitions)
 
synonyms = set()
for synset in text_word.synsets:
    for lemma in synset.lemmas():
        synonyms.add(lemma.name())
         
print(synonyms)

from textblob import TextBlob
from textblob import Word

text_word = Word('safe')

antonyms = set()
for synset in text_word.synsets:
    for lemma in synset.lemmas():        
        if lemma.antonyms():
            antonyms.add(lemma.antonyms()[0].name())        

print(antonyms)