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
| import requests
from fake_useragent import UserAgent
from threading import Thread,Lock,BoundedSemaphore
import json
import re
from typing import Dict, List
from bs4 import BeautifulSoup
import logging
import time
import os
from queue import Queue
import random
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
stream_handler = logging.StreamHandler()
stream_handler.setLevel(logging.INFO)
logger.addHandler(stream_handler)
lock = Lock()
semaphore = BoundedSemaphore(5)
def get_proxy():
api_url = 'http*******************'
try:
time.sleep(0.2)
response = requests.get(api_url, timeout=10)
response.raise_for_status()
data = json.loads(response.content)
proxy_list = data.get('data', [])
proxy_list = proxy_list.get('proxy_list',[])
item = proxy_list[0]
if isinstance(item, str) and ':' in item:
ip, remain = item.split(':', 1)
port = remain.split(',')[0]
return f"http://{ip}:{port}"
except Exception as e:
logger.error(f"获取代理失败: {e}")
return None
def get_url(stock,page):
return f"https://guba.eastmoney.com/list,{stock}_{page}.html"
def extract_posts(data: Dict,stock_num:int) -> List[Dict]:
"""Extract and format post information from raw data."""
posts = []
for post in data.get('re', []):
try:
title = post.get('post_title', '').strip()
post_info = {
'id': post.get('post_id'),
'title': post['post_title'],
'author': post.get('user_nickname', '').strip(),
'click_count': post.get('post_click_count', 0),
'comment_count': post.get('post_comment_count', 0),
'publish_time': post.get('post_publish_time', ''),
'last_time': post.get('post_last_time', ''),
'source_url': f"https://guba.eastmoney.com/news,{stock_num},{post.get('post_id')}.html"
}
posts.append(post_info)
except (KeyError, AttributeError) as e:
logger.warning(f"Skipping malformed post: {str(e)}")
return posts
def parse_page(page_source: str, page: int,stock_num:int) -> List[Dict]:
soup = BeautifulSoup(page_source, 'html.parser')
script_tags = soup.find_all('script')
for script in script_tags:
if script.string and 'var article_list' in script.string:
try:
match = re.search(r'var article_list\s*=\s*({.*?});', script.string, re.DOTALL)
if match:
json_str = match.group(1)
json_str = re.sub(r',\s*}(?=\s*$)', '}', json_str)
json_str = re.sub(r',\s*](?=\s*$)', ']', json_str)
data = json.loads(json_str)
return extract_posts(data,stock_num)
except (json.JSONDecodeError, AttributeError, KeyError) as e:
logger.error(f"解析页面{page}错误: {str(e)}")
continue
def get_page(stock, page, proxy):
headers = {
'User-Agent': UserAgent().random,
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Connection': 'keep-alive',
}
proxies = {
"http": proxy,
"https": proxy
}
url = get_url(stock, page)
try:
response = requests.get(url, headers=headers, proxies=proxies, timeout=10)
print(f"Page {page} of stock {stock} fetched successfully.")
return response.content.decode()
except Exception as e:
print(f"Failed to fetch page {page} of stock {stock}: {e}")
def save_to_json(posts: List[Dict], file_path: str):
"""将帖子信息保存到 JSON 文件中"""
with lock:
if os.path.exists(file_path):
with open(file_path, 'r', encoding='utf-8') as f:
existing_data = json.load(f)
existing_data.extend(posts)
posts = existing_data
with open(file_path, 'w', encoding='utf-8') as f:
json.dump(posts, f, ensure_ascii=False, indent=4)
logger.info(f"数据已保存到 {file_path}")
def load_progress(progress_file: str) -> int:
"""从进度文件中加载已爬取的最大页数"""
if os.path.exists(progress_file):
with open(progress_file, 'r', encoding='utf-8') as f:
try:
return int(f.read().strip())
except ValueError:
pass
return 0
def update_progress(progress_file: str, current_page: int):
"""更新进度文件中的最大页数"""
with open(progress_file, 'a+', encoding='utf-8') as f:
f.write(str(current_page)+'\n')
logger.info(f"进度已更新到 {progress_file}，当前页数：{current_page}")
def process_pages(stock_code: str, start_page: int, end_page: int, output_file: str):
"""处理指定范围内的多个页面"""
semaphore.acquire()
proxy = get_proxy()
if not proxy:
logger.error("未能获取代理 IP，跳过线程创建。")
semaphore.release()
return
try:
for page in range(start_page, end_page + 1):
page_source = get_page(stock_code, page, proxy)
if not page_source:
logger.error(f"无法获取页面源码，跳过页面 {page}。")
continue
posts = parse_page(page_source, page, stock_code)
if posts:
logger.info(f"成功提取页面 {page} 的 {len(posts)} 条帖子信息。")
save_to_json(posts, output_file)
update_progress("./log", page)
else:
logger.warning(f"页面 {page} 未提取到任何帖子信息。")
time.sleep(abs(random.uniform(3,7)))
finally:
semaphore.release()
def main(stock_code: str, total_pages: int, pages_per_thread: int):
"""主函数：动态分配任务给多个线程"""
output_file = f"{stock_code}_posts.json"
threads = []
num_threads = total_pages // pages_per_thread + (1 if total_pages % pages_per_thread != 0 else 0)
for i in range(num_threads):
start_page = i * pages_per_thread + 1
end_page = min((i + 1) * pages_per_thread, total_pages)
thread = Thread(target=process_pages, args=(stock_code, start_page, end_page, output_file))
threads.append(thread)
thread.start()
for t in threads:
t.join()
def process_missing_pages(stock_code: str, pages: list, output_file: str):
"""处理缺失的多个页面"""
semaphore.acquire()
proxy = get_proxy()
if not proxy:
logger.error("未能获取代理 IP，跳过线程创建。")
semaphore.release()
return
try:
for page in pages:
page_source = get_page(stock_code, page, proxy)
if not page_source:
logger.error(f"无法获取页面源码，跳过页面 {page}。")
continue
posts = parse_page(page_source, page, stock_code)
if posts:
logger.info(f"成功提取页面 {page} 的 {len(posts)} 条帖子信息。")
save_to_json(posts, output_file)
update_progress("./log", page)
else:
logger.warning(f"页面 {page} 未提取到任何帖子信息。")
time.sleep(abs(random.uniform(3,7)))
finally:
semaphore.release()
def crawl_missing_pages(stock_code: str, missing_pages: list, batch_size: int = 20):
"""主函数：多线程爬取缺失的页面"""
output_file = f"{stock_code}_posts.json"
threads = []
for i in range(0, len(missing_pages), batch_size):
batch = missing_pages[i:i + batch_size]
thread = Thread(
target=process_missing_pages,
args=(stock_code, batch, output_file)
)
threads.append(thread)
thread.start()
time.sleep(1)
for t in threads:
t.join()
if __name__ =='__main__':
stock_code = "300750"
total_pages = 3300
threads_count = 5
try:
with open("./log", "r", encoding='utf-8') as f:
codes = f.read().split('\n')
except FileNotFoundError:
codes = []
codes = list(set(codes))
codes = [int(i) for i in codes if i.isdigit()]
codes.sort()
missing_pages = []
for i in range(1, total_pages + 1):
if i not in codes:
print(f"缺失页码：{i}")
missing_pages.append(i)
print(f"共发现 {len(missing_pages)} 个缺失页面")
if missing_pages:
crawl_missing_pages(stock_code, missing_pages)
print("缺失页面爬取完成！")
else:
print("没有缺失页面需要爬取。")
print("没有缺失页面需要爬取。")
|