python爬取指定内容_如何用python提取指定内容？

这是部分代码，基本逻辑就是jieba分词，制作语料库，利用tfidf建模，最后找出计算相似度和给出相似度排名前十的。希望对你有帮助。

#训练文本分词

train_doc_list = []

for doc in TRAIN_LIST_1:

doc_list = [word for word in jieba.cut(doc)]

train_doc_list.append(doc_list)

#对训练文本分词创建词袋字典

from gensim import corpora,models,similarities

dictionary = corpora.Dictionary(list_1)

#使用doc2bow制作语料库

corpus = [dictionary.doc2bow(doc) for doc in list_1]

#TF_IDF模型对语料库建模

tfidf = models.TfidfModel(corpus)

#TF 词频 词条在文档d中出现的频率

#IDF逆向文件频率 包含词条t的文档越少，也就是n越小，IDF越大，则说明词条t具有很好的类别区分能力

writer = pd.ExcelWriter(r'C:\Users\zlk52\Desktop\工伤认定相似结果kan1.xlsx')

for i in range(TEST_1.shape[0]):

test_data0 = TEST_1.iloc[i:i+1,:]

# test_data0 = TEST_1

# test_doc = str(test_data0['join'])

test_doc = str(test_data0['Injury_AccidentSketch'])

test_doc = test_doc.replace('点','时')

test_doc_list = [word for word in jieba.cut(test_doc) if word in pick_words]

test_doc_vec = dictionary.doc2bow(test_doc_list)

index = similarities.SparseMatrixSimilarity(tfidf[corpus],num_features = len(dictionary.keys()))

sim = index[tfidf[test_doc_vec]]

sim_sorted = sorted(enumerate(sim),key = lambda item:-item[1])

k = 10

k_index = [sim_sorted[:k][i][0] for i in range(k)]

k_value = [sim_sorted[:k][i][1] for i in range(k)]

result = TRAIN_1.iloc[k_index,:]

result['K_VALUE'] = k_value

test_data0.to_excel(writer,sheet_name = '序号为{0}的工伤认定测试文本'.format(i+1))

result.to_excel(writer,sheet_name = '序号为{0}的相似文本'.format(i+1))