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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
import io
import json
import re
import sys
import time
import loguru
# import pymysql.cursors
import requests
from bs4 import BeautifulSoup
from datetime import datetime
from selenium.common import NoSuchElementException
from api.index import importJson, getReptileTask, importJsonPath
from utils.Logger import log
from utils.index import convert_to_traditional, create_directory_if_not_exists, delete_directory
# from requests_toolbelt import *
from utils.createBrowserDriver import create
import opencc
from utils.filse import save_json
import os
from config.settings import get_base_file_url
from utils.download_image import download_image
# --------------- selenium 依赖 start ----------------
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
# --------------- selenium 依赖 end ----------------
'''
爬取台湾PTT论坛的热门帖子，包括帖子的标题、内容【文本、图片、视频】
爬取流程：创建驱动--》打开浏览器--》打开网页--》爬取分类元素--》循环点击--》爬取热门帖子标题--》循环点击--》爬取帖子详情
'''
def reptile(browser=None, search_word=""):
url = "https://www.ptt.cc/bbs/hotboards.html"
browser = browser or create(no_headless=False, using_user_data=True)
# 有头模式执行
# browser = browser or create()
# 打开网页
browser.get(url)
# log.debug("已打开浏览器")
classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
for index, item_element in enumerate(classify_item_list):
# 只爬取综合分类
if 0 <= index < 1:
type_title = classify_item_list[index].text
# 进入分类页面
classify_item_list[index].click()
time.sleep(0.1)
# 综合分类需要确认已满18周岁
if index == 0:
try:
button = browser.find_element("xpath", "//form/div[1]//button")
button.click()
except:
error = ""
wait = WebDriverWait(browser, 10)
wait.until(EC.presence_of_element_located((By.XPATH, "//div[@class='r-ent']")))
page = 1
# element_meta_list = browser.find_elements("xpath", "//div[@class='r-ent']//div[@class='meta']")
def process_data():
# 增加搜索
search_input = browser.find_element("xpath", "//div[@class='search-bar']//input")
if search_word != search_input.get_attribute("value"):
# 输入搜索关键词
search_input.send_keys(search_word)
# 点击输入框
# browser.execute_script("arguments[0].click();", search_input)
# 确认搜索关键词
# search_input.click()
search_input.submit()
# 程序睡眠300ms，等待页面加载完成
time.sleep(0.3)
element_list = browser.find_elements('xpath', "//div[@class='r-ent']//div[@class='title']//a")
nonlocal page
print(f"当前为第：{page} 页，共 {len(element_list)} 条数据")
for index_two, item in enumerate(element_list):
# print(element_list[index_two].text)
try:
re.findall("公告", item.text)
except IndexError:
error = ""
# log.debug(f"正在爬取分类：{type_title}-第{index_two + 1}条")
# print("当前连接：" + str(browser.current_url))
# print(data[len(data) - 1]["title"])
# 标题不包含"公告"和"看板"
if re.findall("公告", element_list[index_two].text) or re.findall("看板",
element_list[index_two].text):
a = 1
else:
element_list[index_two].click()
time.sleep(0.2)
# 原链接
browser_current_url = browser.current_url
try:
# 获取帖子详情
element_title = browser.find_element('xpath',
"//div[@id='main-content']/div[3]//span[@class='article-meta-value']")
except:
log.error(
"xpath 找不到元素：//div[@id='main-content']/div[3]//span[@class='article-meta-value']")
log.debug(f'页面链接：{browser_current_url}')
# 浏览器返回上一页
browser.back()
element_list = browser.find_elements('xpath',
"//div[@class='r-ent']//div[@class='title']//a")
break
# 内容可能包含图片和视频，需要后处理
element_content = browser.find_element('xpath', "//div[@id='main-content']")
# 去除herf属性值包含'img'的a标签
# ------------------------------------
# 使用BeautifulSoup解析HTML
soup = BeautifulSoup(element_content.get_attribute('outerHTML'), 'html.parser')
# 作者
element_author = browser.find_element('xpath',
"//div[@id='main-content']/div[@class='article-metaline'][1]/span[2]")
# 发布时间
element_release = browser.find_element('xpath',
"//div[@id='main-content']/div[@class='article-metaline'][3]/span[2]")
# log.debug('开始判断类型')
try:
# 找到所有第一级标签为 `div` 的元素
div_elements = soup.find_all('div')
# log.debug("一级div数量：" + str(len(div_elements)))
# 逐个删除这些元素
for key, div in enumerate(div_elements):
if key > 0:
div.extract()
# 删除第一级span
span_element = soup.find_all('span')
# log.debug("一级span数量：" + str(len(span_element)))
for span in span_element:
span.extract()
except:
# log.debug("删除第一级div失败")
a = 2
# ---------------- 判断类型 start ----------
# 类型
content_type = ""
# 查找所有img标签
image_list = soup.find_all('img')
try:
if len(image_list) > 0:
content_type = "图文"
else:
content_type = "文字"
except:
content_type = "文字"
picture_url = []
if len(image_list) > 0:
for key, element in enumerate(image_list):
# 下载图片至本地，替换标签中的src
id = str(int(time.time()))
# 下载地址
download_dir = f'{os.path.join(local_path, f"{id}.jpg")}'
# 访问地址
access_address = f'{get_base_file_url()}{table_name.split("_")[1]}/{local_path_name}/{id}.jpg'
# 下载状态
status = download_image(element['src'], download_dir)
if status:
element['src'] = access_address
picture_url.append(download_dir)
else:
# print("")
error = ""
# ---------------- 判断类型 end ----------
# log.debug('开始内容过滤')
# ------------------ content 过滤 start--------------
try:
# 查找所有的<a>标签
a_tags = soup.find_all('a', href=True)
# log.debug("a标签数量：" + str(len(a_tags)))
# 循环遍历<a>标签，检查每个<a>标签是否包含<img>元素，如果包含则删除该<a>标签
for tag in a_tags:
tag.decompose()
except:
# log.debug("查找所有的<a>标签失败")
a = 1
html = soup.prettify().replace('amp;', '')
# ------------------ content 过滤 end--------------
date_string = element_release.text
# date_string = "Wed Aug 9 15:39:26 2023 //update 20934353"
# 提取日期字符串
if "//" in date_string:
date_string = date_string.split("//")[0]
date_string = date_string.strip()
date_format = "%a %b %d %H:%M:%S %Y"
# 将日期字符串转换为datetime对象
date_time = datetime.strptime(date_string, date_format)
# 将datetime对象转换为时间戳（以秒为单位）
release_time = int(date_time.timestamp())
# 过滤时间
if beginFiltrationTime <= release_time <= endFiltrationTime:
# --------------- 组装数据 start---------------------
obj = {
"title": element_title.text,
"content": html,
"link": browser_current_url,
"reptileTime": str(int(time.time())),
"type": content_type,
"author": element_author.text,
"releaseTime": str(release_time),
"picture_url": ",".join(picture_url)
}
# --------------- 组装数据 end---------------------
data.append(obj)
# 浏览器返回上一页
browser.back()
time.sleep(0.2)
element_list = browser.find_elements('xpath', "//div[@class='r-ent']//div[@class='title']//a")
page = page + 1
# print("111111")
try:
prev_button = browser.find_element('xpath',
"//a[@class='btn wide' and text() = '‹ 上頁']")
prev_button.click()
time.sleep(0.3)
if page <= 10:
process_data()
except:
error = ""
process_data()
# # print("循环结束")
# # 浏览器返回上一页
# browser.back()
# if index == 0:
# browser.back()
# time.sleep(0.1)
# # 重新获取
# classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")
# 发送爬取数据到java服务
# print('----------------------')
# print(data)
if len(data) > 0:
# 保存json文件到本地
json_path = os.path.join(local_path, "data.json")
state_save = save_json(json_path, data)
# 保存task
task = {
# 爬取时间
"reptileTime": data[0]["reptileTime"],
# 本地路径
"localPath": local_path,
"beginFiltrationTime": beginFiltrationTime,
"endFiltrationTime": endFiltrationTime,
"keyword": keyword,
"total": len(data)
}
state_save = save_json(os.path.join(file_dir, "task.json"), task)
if state_save:
log.debug('save file success')
else:
log.debug('save file failed')
script_close(browser)
else:
# 爬取数据为空
log.info("未爬取到数据")
# 删除目录
delete_directory(local_path)
script_close(browser)
def script_close(browser):
# 关闭浏览器驱动
try:
browser.close()
browser.quit()
except:
log.debug("浏览器驱动关闭失败")
try:
# 一些代码...
sys.exit()
except SystemExit:
raise # 重新抛出SystemExit异常，让脚本退出
except Exception as e:
# 异常处理代码...
print("sys.exit() 执行失败")
def main():
"""
"""
# 请求关键词
response = getReptileTask()
global status_task
global beginFiltrationTime
global endFiltrationTime
global keyword
if response['status_code'] == 200 and response['data']['code'] == 200:
log.debug("call success")
search_word = ""
for item in response['data']['rows']:
if item['name'] == 'ptt':
search_word = item['keyword']
table_name = item['tableName']
status_task = int(item["status"])
keyword = str(item["keyword"])
beginFiltrationTime = int(item["beginFiltrationTime"])
endFiltrationTime = int(item["endFiltrationTime"])
# 简体转繁体
if status_task == 0 and len(search_word) > 0:
reptile(None, convert_to_traditional(search_word))
else:
log.debug("爬取任务未启用")
else:
log.debug("call failed")
# 请求超时
reptile(None, convert_to_traditional("新闻"))
# upload_control()
# 全局变量
data = []
# 任务详情
task = {}
table_name = "pms_ptt"
# 全局字段
keyword = ""
# 过滤时间开始
beginFiltrationTime = int(123)
# 过滤时间结束
endFiltrationTime = int(123)
# 文件根目录
file_dir = f'{os.path.join(os.path.abspath("../"), "network-assets-reptile", "reptile_data", table_name.split("_")[1])}'
# 任务目录名称
local_path_name = str(int(time.time()))
# 任务目录路径
local_path = f'{os.path.join(file_dir, local_path_name)}'
# 任务目录是否创建
local_path_status = create_directory_if_not_exists(local_path)
# 是否启用
status_task = 0
# 调用main函数
main()