|
|
|
|
import random
|
|
|
|
|
import string
|
|
|
|
|
import jieba
|
|
|
|
|
from collections import Counter
|
|
|
|
|
import time
|
|
|
|
|
|
|
|
|
|
###############################################################################
|
|
|
|
|
# 本主题通用代码
|
|
|
|
|
###############################################################################
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Crawler:
|
|
|
|
|
"""爬虫父类,为子类爬虫提供基础变量与函数"""
|
|
|
|
|
def __init__(self) -> None:
|
|
|
|
|
|
|
|
|
|
self.stop_words = self.get_stop_words()
|
|
|
|
|
|
|
|
|
|
# 一共有三个可以切换的数据源，来自三个不同的网站
|
|
|
|
|
self.data_source_1 = [
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/4a68ebac-571f-4860-82b3-32d397b2ff59',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/19838f9a-9672-46d5-bd98-ca56973eb5fa',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/39018cd4-a3aa-4888-9a07-7316b52aefbc',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/12191fa5-2818-4557-b665-dbae88e557a4',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/5296105f-f1b6-4296-b2ee-8ddb0945d017',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/5c6b66b6-2699-4664-9024-0bfc4d7b6800',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/c4df7e12-ec56-4078-aebb-fb1b142ae622',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/27f4e535-16f8-47ae-be83-499cdf61f522',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/689ab245-cc98-440d-91d5-9784beb0a675',
|
|
|
|
|
'https://data.tpdc.ac.cn/zh-hans/data/dc672fe7-7b00-4626-a9d5-8a0e00d791c3'
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
self.data_source_2 = [
|
|
|
|
|
f'https://wen.lzep.cn/wen/186{i}.html' for i in range(100, 130)
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
self.data_source_3 = [
|
|
|
|
|
f'https://www.gutenberg.org/cache/epub/73208/pg73{i}.txt'
|
|
|
|
|
for i in range(200, 210)
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
def get_stop_words(self) -> list:
|
|
|
|
|
"""返回常用停用词列表"""
|
|
|
|
|
# 创建停用词列表
|
|
|
|
|
stop_words = [
|
|
|
|
|
'a', 'able', 'about', 'across', 'after', 'all', 'almost', 'also',
|
|
|
|
|
'am', 'among', 'an', 'and', 'any', 'are', 'as', 'at', 'be',
|
|
|
|
|
'because', 'been', 'but', 'by', 'can', 'cannot', 'could', 'dear',
|
|
|
|
|
'did', 'do', 'does', 'either', 'else', 'ever', 'every', 'for',
|
|
|
|
|
'from', 'get', 'got', 'had', 'has', 'have', 'he', 'her', 'hers',
|
|
|
|
|
'him', 'his', 'how', 'however', 'i', 'if', 'in', 'into', 'is',
|
|
|
|
|
'it', 'its', 'just', 'least', 'let', 'like', 'likely', 'may', 'me',
|
|
|
|
|
'might', 'most', 'must', 'my', 'neither', 'no', 'nor', 'not', 'of',
|
|
|
|
|
'off', 'often', 'on', 'only', 'or', 'other', 'our', 'own',
|
|
|
|
|
'rather', 'said', 'say', 'says', 'she', 'should', 'since', 'so',
|
|
|
|
|
'some', 'than', 'that', 'the', 'their', 'them', 'then', 'there',
|
|
|
|
|
'these', 'they', 'this', 'tis', 'to', 'too', 'twas', 'us', 'wants',
|
|
|
|
|
'was', 'we', 'were', 'what', 'when', 'where', 'which', 'while',
|
|
|
|
|
'who', 'whom', 'why', 'will', 'with', 'would', 'yet', 'you',
|
|
|
|
|
'your', '的', '是', '一些', '将', '它们', '这个', '用于', '包含', '用于', '示例'
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
# 将小写字母添加到停用词列表中
|
|
|
|
|
stop_words.extend(list(string.ascii_lowercase))
|
|
|
|
|
|
|
|
|
|
return stop_words
|
|
|
|
|
|
|
|
|
|
def get_headers(self) -> dict:
|
|
|
|
|
"""返回标头"""
|
|
|
|
|
agent_list = [
|
|
|
|
|
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:87.0) Gecko/20100101 \
|
|
|
|
|
Firefox/87.0",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, li\
|
|
|
|
|
ke Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0",
|
|
|
|
|
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHT\
|
|
|
|
|
ML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 7.0; SM-G950U Build/NRD90M) AppleWebK\
|
|
|
|
|
it/537.36 (KHTML, like Gecko) Chrome/62.0.3202.84 Mobile Safari/53\
|
|
|
|
|
7.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 8.0.0; SM-G965U Build/R16NW) AppleWeb\
|
|
|
|
|
Kit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.111 Mobile Safari/\
|
|
|
|
|
537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 8.1.0; SM-T837A) AppleWebKit/537.36 (\
|
|
|
|
|
KHTML, like Gecko) Chrome/70.0.3538.80 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; U; en-us; KFAPWI Build/JDQ39) AppleWebKit/535\
|
|
|
|
|
.19 (KHTML, like Gecko) Silk/3.13 Safari/535.19 Silk-Accelerated=t\
|
|
|
|
|
rue",
|
|
|
|
|
"Mozilla/5.0 (Windows Phone 10.0; Android 4.2.1; Microsoft; Lumia \
|
|
|
|
|
550) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2486.0 Mob\
|
|
|
|
|
ile Safari/537.36 Edge/14.14263",
|
|
|
|
|
"Mozilla/5.0 (Windows Phone 10.0; Android 4.2.1; Microsoft; Lumia \
|
|
|
|
|
950) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2486.0 Mob\
|
|
|
|
|
ile Safari/537.36 Edge/14.14263",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 11; moto g power (2022)) AppleWebKit/\
|
|
|
|
|
537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 6.0.1; Moto G (4)) AppleWebKit/537.36\
|
|
|
|
|
(KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 6.0.1; Nexus 10 Build/MOB31T) AppleWe\
|
|
|
|
|
bKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWeb\
|
|
|
|
|
Kit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.\
|
|
|
|
|
36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKi\
|
|
|
|
|
t/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36\
|
|
|
|
|
",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 8.0.0; Nexus 5X Build/OPR4.170623.006\
|
|
|
|
|
) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile S\
|
|
|
|
|
afari/537.36",
|
|
|
|
|
]
|
|
|
|
|
headers = {
|
|
|
|
|
"user_agent": random.choice(agent_list),
|
|
|
|
|
}
|
|
|
|
|
return headers
|
|
|
|
|
|
|
|
|
|
def get_freqs(self, content: str) -> list[tuple[any, int]]:
|
|
|
|
|
"""获取中文文本content的词频"""
|
|
|
|
|
# 分词
|
|
|
|
|
words = jieba.cut(content)
|
|
|
|
|
|
|
|
|
|
word_freqs = Counter()
|
|
|
|
|
for word in words:
|
|
|
|
|
if word not in self.stop_words:
|
|
|
|
|
word_freqs[word] += 1
|
|
|
|
|
|
|
|
|
|
word_freqs = word_freqs.most_common(10)
|
|
|
|
|
return word_freqs
|
|
|
|
|
|
|
|
|
|
def print_freqs(self, word_freqs: list[tuple[any, int]]) -> None:
|
|
|
|
|
"""打印词频"""
|
|
|
|
|
cnt = 1
|
|
|
|
|
for keyword, freq in word_freqs:
|
|
|
|
|
if len(keyword) > 1:
|
|
|
|
|
print(f"{keyword}: {freq}")
|
|
|
|
|
cnt += 1
|
|
|
|
|
if cnt > 10:
|
|
|
|
|
return
|
