Common anti crawling mechanisms in Python and their cracking methods
- 2021-11-10 10:00:52
- OfStack
1. Common anti-crawling mechanisms and their cracking methods
Banning IP and using cookie have been mentioned in previous articles
Now I will mainly put the following:
~ Verification code
-
>
Text verification code-
>
OCR (Optical Character Recognition)
>
Interface/easyocr
If the program can't solve the problem by itself, you can consider using the 3-party interface (paid/free)
-
>
Behavioral verification code
>
Super Eagle
~ Mobile phone number + SMS verification code
-
>
Coding platform
~ Dynamic content
-
>
JavaScript Reverse--
>
Locate the API interface that provides the data
-
>
Mobile phone grasping interface-
>
Pack Grab Tool (Charles/Fiddler)
-
>
Selenium directly simulates browser operation to obtain dynamic content
~ find_element_by_xxx / find_elements_by_xxx
~ page_source--
>
Get the source code of a Web page containing dynamic content
-
>
JavaScript Encryption and Obfuscation Technology
>
Reading JavaScript is the premise of anti-crawling
~ Font anti-crawling/content from matting
-
>
Example
bytes--
>
Invariant byte string
>
Binary-
>
BytesIO
str--
>
Invariant string
>
Readable characters-
>
StringIO
2. Call 3-party API interface data (skyline data)
import requests
for page in range(1, 6):
response = requests.get(
'http://api.tianapi.com/topnews/index',
params={
'key': 'd5eace66dccd771e36767ce3563efa09',
'page': page,
'num': 20,
'word': ' Huawei ',
'src': ' People's Daily '
}
)
result = response.json()
for news in result['newslist']:
print(news['title'])
print(news['url'])
3. OCR (Optical Character Recognition) Library
easyocr Library with python
import easyocr
reader = easyocr.Reader(['ch_sim', 'en'], gpu=False)
print(reader.readtext('./files/captcha.jpg', detail=0))
Example: Automatic login of Alibaba Cloud mailbox
import io
import easyocr
from PIL import Image
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.wait import WebDriverWait
browser = webdriver.Chrome()
browser.set_window_size(1280, 960)
browser.get('http://mail.1000phone.com/')
# Implicit wait (the following method waits if it can't be retrieved while working 10 Seconds)
browser.implicitly_wait(10)
# Explicit wait
wait = WebDriverWait(browser, 10)
wait.until(expected_conditions.presence_of_element_located((By.CSS_SELECTOR, '.login_panel_iframe')))
iframe1 = browser.find_element_by_css_selector('.login_panel_iframe')
# Record iframe1 Position of (relative position)
x1, y1 = iframe1.location['x'], iframe1.location['y']
# Chrome Object's switch_to Property of frame Method, you can switch from the page to the iframe Medium
browser.switch_to.frame(iframe1)
iframe2 = browser.find_element_by_css_selector('#ding-login-iframe')
x2, y2 = iframe2.location['x'], iframe2.location['y']
browser.switch_to.frame(iframe2)
username_input = browser.find_element_by_css_selector('#username')
# Analog user input
username_input.send_keys('xx@1000phone.com')
password_input = browser.find_element_by_css_selector('#password')
password_input.send_keys('xxxxx!!')
# Create 1 Waiting objects
wait = WebDriverWait(browser, 10)
wait.until(expected_conditions.element_to_be_clickable((By.CSS_SELECTOR, '#login_checkcode_ico')))
captcha_img = browser.find_element_by_css_selector('#login_checkcode_ico')
# WebElement Object's size Attributes represent the width and height of the element, location Attribute represents the position of the element in the window
size, location = captcha_img.size, captcha_img.location
x3, y3, width, height = location['x'], location['y'], size['width'], size['height']
# Intercept the picture of the whole browser window to get the picture 2 Binary data
image_data = browser.get_screenshot_as_png()
# bytes (Read-only byte string) ----> io.BytesIO (Writable byte string) ---> getvalue() ---> bytes
# str (Read-only string) ----> io.StringIO (Writable string) ---> getvalue() ---> str
browser_image = Image.open(io.BytesIO(image_data))
# Cut out the picture of the verification code from the screenshot
x, y = x1 + x2 + x3, y1 + y2 + y3
# Windows Systematic writing ---> If there is something wrong with the screenshot, write the coordinates to death
# print(x, y, width, height)
checkcode_image = browser_image.crop((x * 1.25, y * 1.25, (x + width) * 1.25, (y + height) * 1.25))
# macOS Systematic writing
# checkcode_image = browser_image.crop((x * 2, y * 2, (x + width) * 2, (y + height) * 2))
checkcode_image.save('result.png')
# Pass easyocr Do optical character recognition
reader = easyocr.Reader(['en'], gpu=False)
code = reader.readtext('result.png', detail=0)[0]
# Enter the recognized verification code into the text box
checkcode_input = browser.find_element_by_css_selector('#login_checkcode')
checkcode_input.send_keys(code)
login_button = browser.find_element_by_css_selector('#login_submit_btn')
# Simulate user clicks
login_button.click()
4. Third Party Coding Platform (Super Eagle Coding Platform)
Add: Need to use python's own pillow library
"""
Pillow Library ---> PIL ---> Python Image Library
"""
from PIL import Image, ImageFilter
# Load image
guido_image = Image.open('guido.jpg')
# Tailoring
guido_image.crop((80, 40, 310, 350)).show()
# Filter
guido_image.filter(ImageFilter.CONTOUR).show()
# Thumbnail
guido_image.thumbnail((125, 185))
# Display image
guido_image.show()
Write Super Eagle Coding Platform Class
from hashlib import md5
import requests
class ChaojiyingClient:
def __init__(self, username, password, soft_id):
self.username = username
password = password.encode('utf8')
self.password = md5(password).hexdigest()
self.soft_id = soft_id
self.base_params = {
'user': self.username,
'pass2': self.password,
'softid': self.soft_id,
}
self.headers = {
'Connection': 'Keep-Alive',
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
}
def post_pic(self, image_data, code_type):
"""
image_data: Picture byte
code_type: Verification code type Reference http://www.chaojiying.com/price.html
"""
params = {
'codetype': code_type,
}
params.update(self.base_params)
files = {'userfile': ('ccc.jpg', image_data)}
response = requests.post(
url='http://upload.chaojiying.net/Upload/Processing.php',
data=params,
files=files,
headers=self.headers
)
return response.json()
# Super Eagle error feedback function (only used to give feedback to Super Eagle platform)
def report_error(self, im_id):
"""
im_id: Picture of error report ID
"""
params = {
'id': im_id,
}
params.update(self.base_params)
r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
return r.json()
if __name__ == '__main__':
chaojiying = ChaojiyingClient(' Accounts ', ' Password x', 'ID') # User center >> Software ID Generate 1 Substitution 96001
with open('img.png', 'rb') as file:
image_data = file.read() # Local picture file path To replace a.jpg Sometimes WIN System requirements //
print(chaojiying.post_pic(image_data, 1902)) # 1902 Verification code type Official website >> Price system 3.4+ Version print Add after ()
Example: Automatic login of Alibaba Cloud mailbox using Super Eagle
import io
import easyocr
from PIL import Image
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.wait import WebDriverWait
from chaojiying import ChaojiyingClient
browser = webdriver.Chrome()
browser.set_window_size(1280, 960)
browser.get('http://mail.1000phone.com/')
# Implicit wait (the following method waits if it can't be retrieved while working 10 Seconds)
browser.implicitly_wait(10)
# Explicit wait
wait = WebDriverWait(browser, 10)
wait.until(expected_conditions.presence_of_element_located((By.CSS_SELECTOR, '.login_panel_iframe')))
iframe1 = browser.find_element_by_css_selector('.login_panel_iframe')
# Record iframe1 Position of (relative position)
x1, y1 = iframe1.location['x'], iframe1.location['y']
# Chrome Object's switch_to Property of frame Method, you can switch from the page to the iframe Medium
browser.switch_to.frame(iframe1)
iframe2 = browser.find_element_by_css_selector('#ding-login-iframe')
x2, y2 = iframe2.location['x'], iframe2.location['y']
browser.switch_to.frame(iframe2)
username_input = browser.find_element_by_css_selector('#username')
# Analog user input
username_input.send_keys('xxxx.com')
password_input = browser.find_element_by_css_selector('#password')
password_input.send_keys('xxxx!!')
# Create 1 Waiting objects
wait = WebDriverWait(browser, 10)
wait.until(expected_conditions.element_to_be_clickable((By.CSS_SELECTOR, '#login_checkcode_ico')))
captcha_img = browser.find_element_by_css_selector('#login_checkcode_ico')
# WebElement Object's size Attributes represent the width and height of the element, location Attribute represents the position of the element in the window
size, location = captcha_img.size, captcha_img.location
x3, y3, width, height = location['x'], location['y'], size['width'], size['height']
# Intercept the picture of the whole browser window to get the picture 2 Binary data
image_data = browser.get_screenshot_as_png()
# bytes (Read-only byte string) ----> io.BytesIO (Writable byte string) ---> getvalue() ---> bytes
# str (Read-only string) ----> io.StringIO (Writable string) ---> getvalue() ---> str
browser_image = Image.open(io.BytesIO(image_data))
# Cut out the picture of the verification code from the screenshot
x, y = x1 + x2 + x3, y1 + y2 + y3
# Windows Systematic writing ---> If there is something wrong with the screenshot, write the coordinates to death
# print(x, y, width, height)
checkcode_image = browser_image.crop((x * 1.25, y * 1.25, (x + width) * 1.25, (y + height) * 1.25))
# macOS Systematic writing
# checkcode_image = browser_image.crop((x * 2, y * 2, (x + width) * 2, (y + height) * 2))
checkcode_image.save('result.png')
# Coding through Super Eagle Coding Platform
chaojiying = ChaojiyingClient(' Accounts ', ' Password ', 'ID')
with open('result.png', 'rb') as file:
image_data = file.read()
result_dict = chaojiying.post_pic(image_data, 1902)
# Enter the recognized verification code into the text box
checkcode_input = browser.find_element_by_css_selector('#login_checkcode')
checkcode_input.send_keys(result_dict['pic_str'])
login_button = browser.find_element_by_css_selector('#login_submit_btn')
# Simulate user clicks
login_button.click()
5. Receive the mobile phone verification code through the code receiving platform (private SMS platform)
Receive verification code through private SMS platform (free)
import re
import bs4
import requests
pattern = re.compile(r'\d{4,6}')
resp = requests.get('https://www.yinsiduanxin.com/china-phone-number/verification-code-16521686439.html')
soup = bs4.BeautifulSoup(resp.text, 'html.parser')
# print(resp.text)
td = soup.select_one('body > div.container > div:nth-child(4) > div:nth-child(3) > div.main > div.layui-row > table > tbody > tr:nth-child(1) > td:nth-child(2)')
results = pattern.findall(td.text)
print(results[0])