content.py
4.45 KB
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
import csv
import json
import time
import random
import os
import re
import pandas as pd
import numpy as np
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from hanspell import spell_checker
from bs4 import BeautifulSoup
from datetime import datetime, timedelta
BASE_DIR = os.path.dirname(os.path.realpath(__file__))
def sleeptime():
time.sleep(random.randint(1, 3))
def Click(xpath, driver):
element = driver.find_element_by_xpath(xpath)
driver.execute_script("arguments[0].click();", element)
sleeptime()
def TextPreprocess(text):
text = re.sub(pattern='[^\w\s]', repl='', string=text)
text = re.sub(pattern='\n', repl='. ', string=text)
spelled_sent = spell_checker.check(text)
text = spelled_sent.checked
return text
def GetData():
login_info = {
'userID' : 'qdw0313',
'userpw' : 'fejUfrQxHWwtcGcP0'
}
options = webdriver.ChromeOptions()
options.add_argument('headless')
options.add_argument('no-sandbox')
options.add_argument('window-size=1920x1080')
options.add_argument('disable-gpu')
options.add_argument('disable-dev-shm-usage')
options.add_argument('lang=ko_KR')
options.add_argument('user-agent=Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.183 Safari/537.36 Vivaldi/1.96.1147.47')
# driver = webdriver.Chrome(r'C:\Users\E_N__\Desktop\chromedriver.exe', options=options)
driver = webdriver.Chrome(BASE_DIR + '/chromedriver.exe', options=options)
driver.get('about:blank')
driver.execute_script("Object.defineProperty(navigator, 'plugins', {get: function() {return[1, 2, 3, 4, 5];},});")
sleeptime()
driver.get('https://everytime.kr/login')
sleeptime()
driver.find_element_by_name('userid').send_keys(login_info['userID'])
driver.find_element_by_name('password').send_keys(login_info['userpw'])
driver.find_element_by_class_name('submit').click()
sleeptime()
# 국제캠 자게
sleeptime()
yesterday = (datetime.today() - timedelta(1)).strftime('%m/%d %H:%M')
print(yesterday)
swt = True
page = 0
post_df = pd.DataFrame(columns=['title', 'content'])
while swt:
if page < 1:
Click('//*[@id="submenu"]/div/div[2]/ul/li[1]/a', driver)
page += 1
else:
if page == 1:
Click('//*[@id="container"]/div[2]/div[2]/a', driver)
page += 1
elif page == 2:
Click('//*[@id="container"]/div[2]/div[2]/a[2]', driver)
page += 1
else:
Click('//*[@id="container"]/div[2]/div[2]/a[3]', driver)
html = driver.page_source
soup = BeautifulSoup(html, 'html.parser')
TitleList = soup.select('#container > div.wrap.articles > article > a > h2')
DateList = soup.select('#container > div.wrap.articles > article > a > time')
for post in zip(TitleList, DateList):
title = TextPreprocess(post[0].text)
try:
Click("//h2[contains(text(), '{}')]".format(title), driver)
except NoSuchElementException:
continue
content = driver.find_element_by_xpath('//*[@id="container"]/div[2]/article/a/p').text
driver.back()
sleeptime()
if not (post_df['title'] == title).any():
content = TextPreprocess(content)
post_df = post_df.append(pd.DataFrame([[title, content]],
columns=['title', 'content']))
if post[1].text <= yesterday:
break
break
# post_df.to_csv('data.csv', mode='w', encoding='utf-8-sig', index=False)
# print("CVS file saved")
#
# with open('data.json', 'w+', encoding='utf-8-sig') as json_file:
# for post in zip(post_df['title'].tolist(), post_df['content'].tolist()):
# json.dump({
# "document" :
# {
# "type" : "PLAIN_TEXT",
# "content" : post[0] + post[1]
# },
# "encodingType" : "UTF8"
# }, json_file, ensure_ascii=False)
# print("JSON file saved")
with open('data.txt', 'w', encoding='utf-8-sig') as txt_file:
for post in zip(post_df['title'].tolist(), post_df['content'].tolist()):
txt_file.write(post[0] + post[1] + '.\n')
print("txt file saved")
GetData()