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
| """
网站数据抓取与汇总工具（含登录验证版）
"""
import os
import re
import time
import requests
from bs4 import BeautifulSoup
import pandas as pd
from typing import List, Dict, Optional
from urllib.parse import urljoin
from requests.adapters import HTTPAdapter
from requests.exceptions import RequestException
class Config:
"""爬虫配置参数"""
def __init__(self):
self.base_url = "https://example.com"
self.login_url = "https://example.com/login"
self.list_url_template = "/news?page={page}"
self.start_page = 1
self.end_page = 3
self.username = "your_username"
self.password = "your_password"
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Referer': 'https://example.com/'
}
self.timeout = 10
self.retries = 3
self.retry_delay = 5
self.output_dir = "scraped_data"
self.excel_file = "summary.xlsx"
os.makedirs(self.output_dir, exist_ok=True)
class WebScraper:
"""网站爬取处理器"""
def __init__(self, config: Config):
self.config = config
self.session = requests.Session()
self.session.mount('https://', HTTPAdapter(max_retries=config.retries))
def login(self) -> bool:
"""执行登录操作"""
try:
login_page = self._safe_request(
'GET',
self.config.login_url,
allow_redirects=False
)
soup = BeautifulSoup(login_page.text, 'html.parser')
csrf_token = soup.find('input', {'name': 'csrf_token'})['value']
login_data = {
'username': self.config.username,
'password': self.config.password,
'csrf_token': csrf_token
}
response = self._safe_request(
'POST',
self.config.login_url,
data=login_data,
allow_redirects=False
)
if response.status_code == 302 and 'sessionid' in response.cookies:
print("登录成功")
return True
print("登录失败")
return False
except Exception as e:
print(f"登录过程发生异常: {str(e)}")
return False
def fetch_pages(self) -> List[Dict]:
"""抓取所有页面数据"""
all_data = []
for page in range(self.config.start_page, self.config.end_page + 1):
print(f"正在处理第 {page} 页...")
list_url = urljoin(
self.config.base_url,
self.config.list_url_template.format(page=page)
)
try:
list_response = self._safe_request('GET', list_url)
article_links = self._parse_list_page(list_response.text)
for i, link in enumerate(article_links, 1):
article_url = urljoin(self.config.base_url, link)
print(f" 正在处理文章 {i}/{len(article_links)}: {article_url}")
article_data = self._fetch_article(article_url)
if article_data:
all_data.append(article_data)
time.sleep(1)
except Exception as e:
print(f"第 {page} 页处理失败: {str(e)}")
continue
return all_data
def _fetch_article(self, url: str) -> Optional[Dict]:
"""抓取单篇文章内容"""
try:
response = self._safe_request('GET', url)
return self._parse_article_page(response.text, url)
except Exception as e:
print(f"文章抓取失败: {url} - {str(e)}")
return None
def _parse_list_page(self, html: str) -> List[str]:
"""解析列表页获取文章链接"""
soup = BeautifulSoup(html, 'html.parser')
links = []
for item in soup.select('.article-list .title a'):
if href := item.get('href'):
links.append(href)
return links
def _parse_article_page(self, html: str, url: str) -> Dict:
"""解析文章详情页"""
soup = BeautifulSoup(html, 'html.parser')
def safe_extract(selector: str, default: str = "") -> str:
element = soup.select_one(selector)
return element.text.strip() if element else default
return {
'title': safe_extract('h1.article-title'),
'author': safe_extract('.author-name'),
'publish_date': safe_extract('.publish-time'),
'content': safe_extract('.article-content'),
'url': url
}
def _safe_request(self, method: str, url: str, **kwargs) -> requests.Response:
"""带异常处理和重试机制的请求方法"""
for attempt in range(self.config.retries + 1):
try:
response = self.session.request(
method=method,
url=url,
headers=self.config.headers,
timeout=self.config.timeout,
**kwargs
)
response.raise_for_status()
return response
except RequestException as e:
if attempt < self.config.retries:
print(f"请求失败，第 {attempt+1} 次重试: {str(e)}")
time.sleep(self.config.retry_delay)
else:
raise
class DataHandler:
"""数据处理与存储"""
@staticmethod
def save_text(data: Dict, output_dir: str) -> str:
"""保存为文本文件"""
try:
filename = re.sub(r'[^\w\-_\. ]', '_', data.get('title', 'untitled'))[:50]
filename = f"{filename}.txt"
filepath = os.path.join(output_dir, filename)
with open(filepath, 'w', encoding='utf-8') as f:
for key, value in data.items():
f.write(f"=== {key.upper()} ===\n{value}\n\n")
return filepath
except Exception as e:
print(f"文件保存失败: {str(e)}")
return ""
@staticmethod
def save_excel(data: List[Dict], filename: str) -> bool:
"""保存为Excel文件"""
try:
df = pd.DataFrame(data)
df['publish_date'] = pd.to_datetime(df['publish_date'], errors='coerce')
df.to_excel(
filename,
index=False,
engine='openpyxl',
encoding='utf-8'
)
return True
except Exception as e:
print(f"Excel保存失败: {str(e)}")
return False
def main():
config = Config()
scraper = WebScraper(config)
if not scraper.login():
print("登录失败，程序终止")
return
try:
articles = scraper.fetch_pages()
print(f"共抓取到 {len(articles)} 篇文章")
except Exception as e:
print(f"抓取过程发生严重错误: {str(e)}")
return
saved_files = []
for article in articles:
if path := DataHandler.save_text(article, config.output_dir):
saved_files.append(path)
if DataHandler.save_excel(articles, config.excel_file):
print(f"数据已汇总保存至 {config.excel_file}")
if __name__ == "__main__":
main()
|