def retrieve_page(self): url = "http://weibo.cn/%d/fans" % (self.uid) pm = mparameter.Parameter() headers = pm.get_headers() headers["Cookie"] = COOKIE soup = "Flag" try: response = requests.get(url, headers=headers, timeout=5) status = response.status_code if status == 200: soup = bs4.BeautifulSoup(response.text, "lxml") else: print("%s error to reach the server %s" % (status, url)) except Exception: print("Error happens! Please check your requests.") return soup
def retrieve_page(self, cur_page): url = self.url % (str((cur_page) * 25)) pm = mparameter.Parameter() headers = pm.get_headers() proxies = pm.get_proxies() soup = "FLAG" try: response = requests.get(url, proxies, headers=headers, timeout=5) status = response.status_code if status == 200: soup = bs4.BeautifulSoup(response.text, "lxml") else: print("%s error to reach the server %s" % (status, url)) except Exception: print("Error happens! Please check your requests.") return soup
def get_img(self, url, fileloc): pm = mparameter.Parameter() headers = pm.get_headers() proxies = pm.get_proxies() try: response = requests.get(url, proxies, headers=headers, timeout=5, stream=True) status = response.status_code if status == 200: with open(fileloc, 'wb') as f: response.raw.decode_content = True shutil.copyfileobj(response.raw, f) for chunk in response.iter_content(1024): f.write(chunk) else: print("%s error to reach the server %s" % (status, url)) except Exception: print("Error happens! Please check your requests.")