python实训day05

爬虫数据库

• sqlite数据库

import sqlite3
contect = sqlite3.connect('./testsqlite.db')
cursor = contect.cursor()
cursor.execute("""
    create table if not exists student (
        id integer primary key,
        name Text,
        age integer
    );
""")
cursor.execute(("""
    insert into student (name,age) values ('小明',13);
"""))

• jieba分词

import jieba
import sqlite3
connect = sqlite3.connect('./testsqlite.db')
cursor = connect.cursor()
cursor.execute("""select * from jdcom;""")
comments_rs = cursor.fetchall()
# [(id, cid, content, product. color), (]
# comments = []
#处理列表里的每一一项，生成新列老，这个结构非常宿用。
# for c in comments_rs:
comments = [c[2] for c in comments_rs]
comments = ''. join(comments)
#把所有评论拼成一个长字符出。
words = jieba. cut(comments,cut_all=False)
print('/' .join(words))

• 停止词

comment_word_list = ['苹果','手机','外形外观','不错','还','苹果','8','，','。']
with open('./dict/stop_words_zh.txt',mode = 'r',encoding='utf-8') as f:
    stop_words = f.readlines()
    stop_words = [stop_word.strip() for stop_word in stop_words]
    print(stop_words)
filered_comment_word_list = []
for word in comment_word_list:
    if word not in stop_words:
        filered_comment_word_list.append(word)
print(filered_comment_word_list)