1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

import urllib.request
from bs4 import BeautifulSoup
from wordcloud import WordCloud

url = "https://www.gov.cn/zhuanti/2021lhzfgzbg/index.htm"
response = urllib.request.urlopen(url)
html = response.read().decode("utf-8")

soup = BeautifulSoup(html, "html.parser")
content = soup.find("div", class_="zhj-bbqw-cont").text

w = WordCloud(font_path="/Fonts/simhei.ttf").generate(content)
w.to_file("政府工作报告y1.png")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

#引入第三方库
import wordcloud
wordcloud.WordCloud().generate(text)
#另一种
from wordcloud import WordCloud
WordCloud().generate(text)

#预设一段文本
text = "Life is short, I use Python"

#读取文本文件
text = open('Harry Potter and The Half Blood Prince.txt').read()

#生成 text 对应的词云对象
w = WordCloud().generate(text)

#输出词云图像文件
w.to_file('filename')

1
2
3
4

from wordcloud import WordCloud
text = "Life is short, I use Python"
w = WordCloud().generate(text)
w.to_file('usePython.png')

1
2
3
4
5
6
7
8

from wordcloud import WordCloud,STOPWORDS
text = "Life is short, I use Python"

w = WordCloud(background_color="white",
              stopwords=STOPWORDS.add("use"))

w = w.generate(text)
w.to_file("usePython.png")

1
2
3
4

清热凉血解毒药：石膏、菊花、知母、柴胡、银胡、白薇、决明子、夏枯草、栀子、芦根、牛黄、玄参、黄芩
、黄连、黄柏、龙胆草、金银花、连翘。蒲公英、白头翁、与齿范、柴草根、青箱子、西瓜、虎耳草
祛风湿药：姜活、独活、五加皮、木瓜、威灵仙、白芷、秦艽、稀签草、苍耳子、桑枝、臭梧桐
发散风寒药：麻黄、根、桂枝、肉桂、紫苏叶、梗，细辛、防风、荆芥、生姜、干姜法、炮姜、葱白、辛夷

1
2
3
4
5

from wordcloud import WordCloud
text = open(r'E:\OneDrive\桌面\Python\CNMed.txt', encoding='utf-8').read()
font = '/Fonts/simhei.ttf'
wcloud = WordCloud(font_path = font).generate(text)
wcloud.to_file('CNMed.png')

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

import urllib.request
from bs4 import BeautifulSoup
from wordcloud import WordCloud
from imageio import imread
import matplotlib.pyplot as plt

url = "https://www.gov.cn/zhuanti/2021lhzfgzbg/index.htm"
response = urllib.request.urlopen(url)
html = response.read().decode("utf-8")

soup = BeautifulSoup(html, "html.parser")
content = soup.find("div", class_="zhj-bbqw-cont").text

font = '/Fonts/simhei.ttf'
t = WordCloud(background_color = 'white', font_path = font, mask = im)
wcloud = t.generate(text)

plt.imshow(wcloud)
plt.axis("off")
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79

import urllib.request
from bs4 import BeautifulSoup
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

# ========================
# 1. 获取网页
# ========================
url = "https://www.gov.cn/zhuanti/2021lhzfgzbg/index.htm"
response = urllib.request.urlopen(url)
html = response.read().decode("utf-8")

# ========================
# 2. 解析网页正文
# ========================
soup = BeautifulSoup(html, "html.parser")
content_div = soup.find("div", class_="zhj-bbqw-cont")

if content_div is None:
    raise RuntimeError("未找到正文内容，请检查网页结构是否变化")

content = content_div.get_text()

# ========================
# 3. 文本清洗
# ========================
punctuation = '，。“”、：；（）！——《》|#￥%$*+_./:;{}[]=-!@~`“'
for ch in punctuation:
    content = content.replace(ch, " ")

# ========================
# 4. 中文分词 + 停用词过滤
# ========================
stopwords = {
    "的", "和", "是", "在", "为", "等",
    "要", "以", "及", "对", "把", "着"
}

words = jieba.cut(content)

counts = {}
for word in words:
    word = word.strip()
    if not word or word in stopwords or len(word) == 1:
        continue
    counts[word] = counts.get(word, 0) + 1

# ========================
# 5. 输出 Top20 词频
# ========================
items = sorted(counts.items(), key=lambda x: x[1], reverse=True)

print("Top 20 关键词：")
for word, count in items[:20]:
    print(f"{word:<10} {count:>5}")

# ========================
# 6. 生成词云
# ========================
wc = WordCloud(
    font_path="C:/Windows/Fonts/simhei.ttf",  # 中文字体（必须）
    width=900,
    height=600,
    background_color="white",
    max_words=200,
    collocations=False  # 避免重复词组
)

wc.generate_from_frequencies(counts)

# ========================
# 7. 保存 + 显示
# ========================
wc.to_file("政府工作报告词云.png")

plt.imshow(wc)
plt.axis("off")
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image

# ========================
# 1. 读取英文小说文件
# ========================
with open(
    "Harry Potter and The Half Blood Prince.txt",
    "r",
    encoding="utf-8",
    errors="ignore"
) as file:
    txt = file.read().lower()

# ========================
# 2. 文本清洗（英文标点）
# ========================
for ch in '~!@#$%^&*()_+`-=|{}:"><[]\\;,./?\'':
    txt = txt.replace(ch, " ")

# ========================
# 3. 英文分词
# ========================
words = txt.split()

# ========================
# 4. 停用词（英文）
# ========================
stopwords = {
    # 冠词
    "the", "a", "an",
    # 介词
    "in", "on", "at", "by", "for", "with", "from", "to", "into", "out", "of", "about", "above", "below", "before", "after", "between", "among", "through", "during", "over", "around", "down",
    # 连词
    "and", "but", "or", "so", "because", "since", "while", "if", "though", "although", "as", "than",
    # 代词
    "i", "me", "my", "mine", "you", "your", "yours", "he", "him", "his", "she", "her", "hers", "it", "its", "we", "us", "our", "ours", "they", "them", "their", "theirs", "this", "that", "these", "those", "who", "whom", "whose", "which", "what",
    # 助动词/系动词
    "am", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had", "having", "do", "does", "did", "doing",
    # 情态动词
    "can", "could", "will", "would", "shall", "should", "may", "might", "must",
    # 副词/功能词
    "here", "there", "now", "then", "when", "where", "why", "how", "always", "never", "often", "sometimes", "just", "only", "very", "too", "quite", "rather", "well", "again",
    # 量词/填充词
    "all", "some", "any", "no", "none", "many", "much", "few", "little", "several", "one", "two", "three", "more",
    # 否定词
    "not", "no", "never",
    # 常见动词/口语词
    "know", "like", "think", "see", "got", "get", "go", "went",
    # 哈利波特文本高频无意义叙事词
    "said", "asked", "replied", "looked", "looking", "look", "back", "once", "right", "off"
}


# ========================
# 5. 词频统计
# ========================
counts = {}
for word in words:
    word = word.strip()
    if not word or word in stopwords or len(word) <= 2:
        continue
    counts[word] = counts.get(word, 0) + 1

# ========================
# 6. 输出 Top20
# ========================
items = sorted(counts.items(), key=lambda x: x[1], reverse=True)

print("Top 20 Words:")
for word, count in items[:20]:
    print(f"{word:<15} {count:>5}")


# ========================
# 8. 生成词云
# ========================
wc = WordCloud(
    width=1000,
    height=800,
    background_color="white",
    max_words=200,
    contour_width=2,
    contour_color="red",
    collocations=False
)

wc.generate_from_frequencies(counts)

# ========================
# 9. 保存 + 显示
# ========================
wc.to_file("HarryPotter_Heart_WordCloud.png")

plt.imshow(wc)
plt.axis("off")
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81

import urllib.request
from bs4 import BeautifulSoup
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

# ========================
# 1. 获取网页
# ========================
url = "https://www.gov.cn/zhuanti/2021lhzfgzbg/index.htm"
response = urllib.request.urlopen(url)
html = response.read().decode("utf-8")

# ========================
# 2. 解析网页正文
# ========================
soup = BeautifulSoup(html, "html.parser")
content_div = soup.find("div", class_="zhj-bbqw-cont")

if content_div is None:
    raise RuntimeError("未找到正文内容，请检查网页结构是否变化")

content = content_div.get_text()

# ========================
# 3. 文本清洗
# ========================
punctuation = '，。“”、：；（）！——《》|#￥%$*+_./:;{}[]=-!@~`“'
for ch in punctuation:
    content = content.replace(ch, " ")

# ========================
# 4. 中文分词 + 停用词过滤
# ========================
stopwords = {
    "的", "和", "是", "在", "为", "等",
    "要", "以", "及", "对", "把", "着"
}

words = jieba.cut(content)

counts = {}
for word in words:
    word = word.strip()
    if not word or word in stopwords or len(word) == 1:
        continue
    counts[word] = counts.get(word, 0) + 1

# ========================
# 5. 输出 Top20 词频
# ========================
items = sorted(counts.items(), key=lambda x: x[1], reverse=True)

print("Top 20 关键词：")
for word, count in items[:20]:
    print(f"{word:<10} {count:>5}")

# ========================
# 6. 生成词云
# ========================
wc = WordCloud(
    font_path="C:/Windows/Fonts/simhei.ttf",  # 中文字体（必须）
    width=900,
    height=600,
    background_color="white",
    max_words=200,
    collocations=False  # 避免重复词组
)

# wc.generate_from_frequencies(counts)
#wc = wc.fit_words(counts)


# ========================
# 7. 保存 + 显示
# ========================
wc.to_file("政府工作报告词云.png")

plt.imshow(wc)
plt.axis("off")
plt.show()