comic.py 文件源码

def get_pages(self):
        '''
        ??Phantomjs??????????????????url
        Get all pages' urls using selenium an phantomJS
        return:
            a list of tuple (page_num,page_url)
        '''
        r_slt=r'onchange="select_page\(\)">([\s\S]*?)</select>'
        r_p=r'<option value="(.*?)".*?>?(\d*?)?<'
        try:
            dcap = dict(DesiredCapabilities.PHANTOMJS)
            # ???????????????
            dcap["phantomjs.page.settings.loadImages"] = False
            driver = webdriver.PhantomJS(desired_capabilities=dcap)
            driver.get(self.chapter_url)
            text=driver.page_source
            st=re.findall(r_slt,text)[0]
            self.pages = [(int(p[-1]),p[0]) for p in re.findall(r_p,st)]
        except Exception:
            traceback.print_exc()
            self.pages = []
        except KeyboardInterrupt:
            raise KeyboardInterrupt
        finally:
            driver.quit()
            print('Got {l} pages in chapter {ch}'.format(l=len(self.pages),ch=self.chapter_title))
            return self.pages