@@ -57,3 +57,40 @@ def wait_for_redirect(self, url = None, wait = 0.1, timeout=10):
5757 return self .dryscrape_session .url ()
5858 logger .error (f'Maybe { self .dryscrape_session .url ()} \' t a redirect URL?' )
5959 raise Exception ('Timed out on the zipru redirect page.' )
60+ 61+ def solve_captcha (self , img , width = 1280 , height = 800 ):
62+ # take a screenshot of the page
63+ self .dryscrape_session .set_viewport_size (width , height )
64+ filename = tempfile .mktemp ('.png' )
65+ self .dryscrape_session .render (filename , width , height )
66+ 67+ # inject javascript to find the bounds of the captcha
68+ js = 'document.querySelector("img[src *= captcha]").getBoundingClientRect()'
69+ rect = self .dryscrape_session .eval_script (js )
70+ box = (int (rect ['left' ]), int (rect ['top' ]), int (rect ['right' ]), int (rect ['bottom' ]))
71+ 72+ # solve the captcha in the screenshot
73+ image = Image .open (filename )
74+ os .unlink (filename )
75+ captcha_image = image .crop (box )
76+ captcha = pytesseract .image_to_string (captcha_image )
77+ logger .debug (f'Solved the Zipru captcha: "{ captcha } )
78+ 79+ # submit the captcha
80+ input = self .dryscrape_session .xpath ('//input[@id = "solve_string"]' )[0 ]
81+ input .set (captcha )
82+ button = self .dryscrape_session .xpath ('//button[@id = "button_submit"]' )[0 ]
83+ url = self .dryscrape_session .url ()
84+ button .click ()
85+ 86+ # try again if it we redirect to a threat defense URL
87+ if self .is_threat_defense_url (self .wait_for_redirect (url )):
88+ return self .bypass_threat_defense ()
89+ 90+ # otherwise return the cookies as a dict
91+ cookies = {}
92+ for cookie_string in self .dryscrape_session .cookies ():
93+ if 'domain=zipru.to' in cookie_string :
94+ key , value = cookie_string .split (';' )[0 ].split ('=' )
95+ cookies [key ] = value
96+ return cookies
0 commit comments