File size: 13,170 Bytes
a9002e6
 
 
1f34280
 
b3b712b
a9002e6
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
 
1f34280
a9002e6
 
1f34280
a9002e6
 
1f34280
a9002e6
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f34280
 
a9002e6
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
1f34280
a9002e6
 
 
 
 
1f34280
a9002e6
 
 
 
1f34280
a9002e6
1f34280
a9002e6
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
1f34280
a9002e6
 
1f34280
a9002e6
 
1f34280
a9002e6
 
 
 
 
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
1f34280
a9002e6
 
1f34280
a9002e6
 
 
1f34280
a9002e6
1f34280
a9002e6
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
1f34280
a9002e6
 
 
 
 
 
 
1f34280
a9002e6
 
eef2a73
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


import random
import asyncio
from playwright.async_api import async_playwright
import random

async def fetch_html(url, max_retries=5, min_delay=1, max_delay=3, headless=True, timeout=30000):
    """
    Fetch HTML using Playwright with retries and anti-bot measures.
    
    Args:
        url (str): The URL to fetch
        max_retries (int): Maximum number of retry attempts
        min_delay (float): Minimum delay between retries in seconds
        max_delay (float): Maximum delay between retries in seconds
        headless (bool): Whether to run browser in headless mode
        timeout (int): Page load timeout in milliseconds
        
    Returns:
        str or None: HTML content as string or None if failed
    """
    for attempt in range(1, max_retries + 1):
        print(f"[INFO] Fetching {url} (Attempt {attempt}/{max_retries})")
        
        try:
            async with async_playwright() as p:
                # Launch browser with realistic settings
                browser = await p.chromium.launch(
                    headless=headless,
                    args=[
                        '--no-sandbox',
                        '--disable-blink-features=AutomationControlled',
                        '--disable-dev-shm-usage',
                        '--disable-web-security',
                        '--disable-features=VizDisplayCompositor',
                        '--user-agent=Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
                    ]
                )
                
                # Create context with realistic settings
                context = await browser.new_context(
                    user_agent=(
                        "Mozilla/5.0 (X11; Linux x86_64) "
                        "AppleWebKit/537.36 (KHTML, like Gecko) "
                        "Chrome/120.0.0.0 Safari/537.36"
                    ),
                    locale='ar-SA',
                    timezone_id='Asia/Riyadh',
                    viewport={'width': 1920, 'height': 1080},
                    extra_http_headers={
                        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
                        "Accept-Language": "ar,en-US;q=0.9,en;q=0.8",
                        "Accept-Encoding": "gzip, deflate, br",
                        "DNT": "1",
                        "Connection": "keep-alive",
                        "Upgrade-Insecure-Requests": "1",
                        "Referer": "https://shamela.ws/",
                    }
                )
                
                # Create page and set additional stealth measures
                page = await context.new_page()
                
                # Hide webdriver traces
                await page.add_init_script("""
                    Object.defineProperty(navigator, 'webdriver', {
                        get: () => undefined,
                    });
                    
                    window.chrome = {
                        runtime: {},
                    };
                    
                    Object.defineProperty(navigator, 'plugins', {
                        get: () => [1, 2, 3, 4, 5],
                    });
                    
                    Object.defineProperty(navigator, 'languages', {
                        get: () => ['ar', 'en-US', 'en'],
                    });
                """)
                
                # Navigate to the page
                response = await page.goto(url, wait_until='domcontentloaded', timeout=timeout)
                
                if response and response.status == 200:
                    # Wait a bit for any dynamic content
                    await page.wait_for_timeout(random.randint(1000, 3000))
                    
                    # Optional: Wait for specific elements if needed
                    # await page.wait_for_selector('body', timeout=5000)
                    
                    # Get the HTML content
                    html = await page.content()
                    
                    if len(html.strip()) > 500:
                        # ✅ Got valid HTML
                        preview = html[:300].replace("\n", " ")
                        print(f"[OK] {url} (Attempt {attempt}) | Preview: {preview[:150]}...")
                        await browser.close()
                        return html
                    else:
                        print(f"[WARN] Short HTML content ({len(html)} chars) on attempt {attempt}")
                else:
                    status = response.status if response else "No response"
                    print(f"[WARN] Status {status} on attempt {attempt}")
                
                await browser.close()
        
        except Exception as e:
            print(f"[ERROR] Attempt {attempt}: {e}")
        
        # Wait before retrying
        if attempt < max_retries:
            wait_time = random.uniform(min_delay, max_delay)
            print(f"[INFO] Waiting {wait_time:.1f} seconds before retry...")
            await asyncio.sleep(wait_time)
    
    print(f"[FAIL] Could not fetch {url} after {max_retries} attempts.")
    return None


async def fetch_html_with_js_execution(url, max_retries=5, min_delay=1, max_delay=3, headless=True, timeout=30000, wait_for_js=True):
    """
    Enhanced version that can execute JavaScript and wait for dynamic content.
    
    Args:
        url (str): The URL to fetch
        max_retries (int): Maximum number of retry attempts
        min_delay (float): Minimum delay between retries in seconds
        max_delay (float): Maximum delay between retries in seconds
        headless (bool): Whether to run browser in headless mode
        timeout (int): Page load timeout in milliseconds
        wait_for_js (bool): Whether to wait for JavaScript to execute
        
    Returns:
        str or None: HTML content as string or None if failed
    """
    for attempt in range(1, max_retries + 1):
        print(f"[INFO] Fetching {url} with JS execution (Attempt {attempt}/{max_retries})")
        
        try:
            async with async_playwright() as p:
                browser = await p.chromium.launch(
                    headless=headless,
                    args=[
                        '--no-sandbox',
                        '--disable-blink-features=AutomationControlled',
                        '--disable-dev-shm-usage',
                        '--disable-web-security',
                        '--disable-features=VizDisplayCompositor'
                    ]
                )
                
                context = await browser.new_context(
                    user_agent=(
                        "Mozilla/5.0 (X11; Linux x86_64) "
                        "AppleWebKit/537.36 (KHTML, like Gecko) "
                        "Chrome/120.0.0.0 Safari/537.36"
                    ),
                    locale='ar-SA',
                    timezone_id='Asia/Riyadh',
                    viewport={'width': 1920, 'height': 1080},
                    java_script_enabled=True
                )
                
                page = await context.new_page()
                
                # Navigate and wait for network to be idle
                response = await page.goto(url, wait_until='networkidle', timeout=timeout)
                
                if response and response.status == 200:
                    if wait_for_js:
                        # Wait for common dynamic content indicators
                        try:
                            await page.wait_for_load_state('networkidle', timeout=10000)
                        except:
                            pass  # Continue even if network doesn't idle
                        
                        # Additional wait for any remaining dynamic content
                        await page.wait_for_timeout(random.randint(2000, 5000))
                    
                    html = await page.content()
                    
                    if len(html.strip()) > 500:
                        preview = html[:300].replace("\n", " ")
                        print(f"[OK] {url} (Attempt {attempt}) | Preview: {preview[:150]}...")
                        await browser.close()
                        return html
                    else:
                        print(f"[WARN] Short HTML content ({len(html)} chars) on attempt {attempt}")
                else:
                    status = response.status if response else "No response"
                    print(f"[WARN] Status {status} on attempt {attempt}")
                
                await browser.close()
        
        except Exception as e:
            print(f"[ERROR] Attempt {attempt}: {e}")
        
        if attempt < max_retries:
            wait_time = random.uniform(min_delay, max_delay)
            print(f"[INFO] Waiting {wait_time:.1f} seconds before retry...")
            await asyncio.sleep(wait_time)
    
    print(f"[FAIL] Could not fetch {url} after {max_retries} attempts.")
    return None


async def fetch_html_with_browser(url, browser_type='chromium', max_retries=5, min_delay=1, max_delay=3, headless=True, timeout=30000):
    """
    Fetch HTML using different browser types (chromium, firefox, webkit).
    
    Args:
        url (str): The URL to fetch
        browser_type (str): Browser type ('chromium', 'firefox', 'webkit')
        max_retries (int): Maximum number of retry attempts
        min_delay (float): Minimum delay between retries in seconds
        max_delay (float): Maximum delay between retries in seconds
        headless (bool): Whether to run browser in headless mode
        timeout (int): Page load timeout in milliseconds
        
    Returns:
        str or None: HTML content as string or None if failed
    """
    for attempt in range(1, max_retries + 1):
        print(f"[INFO] Fetching {url} with {browser_type} (Attempt {attempt}/{max_retries})")
        
        try:
            async with async_playwright() as p:
                # Get the appropriate browser
                if browser_type.lower() == 'firefox':
                    browser = await p.firefox.launch(headless=headless)
                    user_agent = "Mozilla/5.0 (X11; Linux x86_64; rv:120.0) Gecko/20100101 Firefox/120.0"
                elif browser_type.lower() == 'webkit':
                    browser = await p.webkit.launch(headless=headless)
                    user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Safari/605.1.15"
                else:  # default to chromium
                    browser = await p.chromium.launch(
                        headless=headless,
                        args=[
                            '--no-sandbox',
                            '--disable-blink-features=AutomationControlled',
                            '--disable-dev-shm-usage',
                            '--disable-web-security',
                            '--disable-features=VizDisplayCompositor'
                        ]
                    )
                    user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
                
                context = await browser.new_context(
                    user_agent=user_agent,
                    locale='ar-SA',
                    timezone_id='Asia/Riyadh',
                    viewport={'width': 1920, 'height': 1080}
                )
                
                page = await context.new_page()
                
                # Navigate to the page
                response = await page.goto(url, wait_until='domcontentloaded', timeout=timeout)
                
                if response and response.status == 200:
                    # Wait a bit for any dynamic content
                    await page.wait_for_timeout(random.randint(1000, 3000))
                    
                    html = await page.content()
                    
                    if len(html.strip()) > 500:
                        preview = html[:300].replace("\n", " ")
                        print(f"[OK] {url} with {browser_type} (Attempt {attempt}) | Preview: {preview[:150]}...")
                        await browser.close()
                        return html
                    else:
                        print(f"[WARN] Short HTML content ({len(html)} chars) on attempt {attempt}")
                else:
                    status = response.status if response else "No response"
                    print(f"[WARN] Status {status} on attempt {attempt}")
                
                await browser.close()
        
        except Exception as e:
            print(f"[ERROR] Attempt {attempt} with {browser_type}: {e}")
        
        if attempt < max_retries:
            wait_time = random.uniform(min_delay, max_delay)
            print(f"[INFO] Waiting {wait_time:.1f} seconds before retry...")
            await asyncio.sleep(wait_time)
    
    print(f"[FAIL] Could not fetch {url} with {browser_type} after {max_retries} attempts.")
    return None