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
|
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options as ChromeOptions
from selenium import webdriver
from dotenv import load_dotenv
import requests
import time
import os
load_dotenv()
class SiteScraper:
def __init__(self, headless: bool = True, wait_time = 5):
"""
Initialize the SiteScraper with the path to ChromeDriver
:param chrome_driver_path: Path to the ChromeDriver executable
:param headless: Run the browser in headless mode if True
"""
self.wait_time = wait_time
try:
self.service = Service(os.environ.get("CHROME_DRIVER_PATH"))
self.chrome_options = ChromeOptions()
if headless:
self.chrome_options.add_argument("--headless")
self.chrome_options.add_argument("--disable-gpu")
self.chrome_options.add_argument("--disable-dev-shm-usage")
self.chrome_options.add_argument("--window-size=1920,1080")
self.chrome_options.add_argument("--no-sandbox")
self.chrome_options.add_argument("--disable-extensions")
self.chrome_options.add_argument("--disable-infobars")
self.chrome_options.add_argument("--disable-logging")
self.chrome_options.add_argument("--disable-background-networking")
self.chrome_options.add_argument("--disable-sync")
self.chrome_options.add_argument("--metrics-recording-only")
self.chrome_options.add_argument("--mute-audio")
self.chrome_options.add_argument("--remote-debugging-port=9222")
self.driver = webdriver.Chrome(service=self.service, options=self.chrome_options)
except FileNotFoundError:
print("The ChromeDriver executable was not found. Is it installed and accessible in PATH?")
quit()
except Exception as e:
print(f"An unknown error occurred: {e}")
quit()
def get_page_source(self, url) -> str:
"""
Get the page source of the given URL
:param url: The URL of the page to scrape
:param wait_time: The time to wait for the page to load (for JavaScript)
"""
try:
self.driver.get(url)
except Exception as e:
print(f"An error occurred while trying to get the page source: {e}")
return ""
if self.wait_time > 0:
time.sleep(self.wait_time)
return self.driver.page_source
def close(self):
"""
Close the WebDriver
"""
self.driver.quit()
self.service.stop()
print("WebDriver closed successfully")
def download_site_as_html(url: str, timeout: int = 10, response_encoding=None) -> str:
headers = {
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/122.0.0.0 Safari/537.36"
),
"Accept": (
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
),
"Accept-Language": "en-US,en;q=0.9",
"Connection": "keep-alive",
}
try:
response = requests.get(url, headers=headers, timeout=timeout)
if response_encoding:
response.encoding = response_encoding
response.raise_for_status()
return response.text
except requests.exceptions.Timeout as e:
print(f"Timeout error downloading {url}: {e}")
return None
except requests.RequestException as e:
print(f"Error downloading {url}: {e}")
return None
|
