def getVideo(self): newsoup = self.getNextStep() script = newsoup.find("div", id = "play").find("script").getText() script = stringutils.get_after(script, "playlist: '") script = stringutils.get_before(script, "',") xmlsoup = self.getPageSoup(self.getBaseUrl() + script) return xmlsoup.find("media:content").get("url")
def getVideo(self): newsoup = self.getNextStep() script = newsoup.find("div", id="play").find("script").getText() script = stringutils.get_after(script, "playlist: '") script = stringutils.get_before(script, "',") xmlsoup = self.getPageSoup(self.getBaseUrl() + script) return xmlsoup.find("media:content").get("url")
def getVideo(self): newsoup = self.getStep2() scripts = newsoup.findAll("script") for script in scripts: text = script.getText() if text[0:4] == "eval" and "SWFObject" in text: script = stringutils.decode_packed_javascript(text) after = get_after(script, "addVariable('file','") middle = get_before(after, "');") return middle
def getVideo(self): newsoup = self.getStep2() scripts = newsoup.findAll("script") for script in scripts: text = script.getText() if text[0:4] == "eval" and "SWFObject" in text: script = stringutils.decode_packed_javascript(text) after = get_after(script, "addVariable('file','") middle = get_before(after,"');") return middle
def getVideo(self): newsoup = self.getStep2() scripts = newsoup.find("div", {"id":"player_code"}).findAll("script") #could either be the 2nd or 3rd script... have to check each one. for script in scripts: if 'file: "' in script.getText(): targetScriptText = script.getText() targetScriptPart = stringutils.get_after(targetScriptText, 'file: "') targetScriptPart = stringutils.get_before(targetScriptPart, '",') return targetScriptPart
def getHostSiteTypes(self, season, episode): assert isinstance(season, int) assert isinstance(episode, int) sites = self.getEpisodeSoup(season, episode).findAll("span", {"class":"version_host"}) types = [] for site in sites: site = str(site.getText()) site = stringutils.get_after(site, "('") site = stringutils.get_before(site, "')") types.append(site) return types
def getMetadata(self): soup = self.getNextStep() scripts = soup.find("div", id = "divxshowboxt").findAll("script") ret = dict() for script in scripts: text = script.getText() if len(text) > 0 and text.count("var file_name = escape('") > 0: namepart = stringutils.get_after(text, "var file_name = escape('") ret["name"] = stringutils.get_before(namepart, "');\n") ret["extension"] = ret["name"][-3:] return ret
def getMetadata(self): ret = dict() soup = self.getStep2() scripts = soup.find("div", {"id": "player_code"}).findAll("script") #could either be the 2nd or 3rd script... have to check each one. for script in scripts: scriptText = script.getText() #makes sure it's the right script (there are multiple) if 'file: "' in script.getText(): namepart = stringutils.get_after(scriptText, 'file: "') ret["name"] = stringutils.get_before(namepart, '"') ret["extension"] = ret["name"][-3:] durpart = stringutils.get_after(scriptText, 'duration:"') ret["duration"] = stringutils.get_before(durpart, '"') heightpart = stringutils.get_after(scriptText, 'height: "') ret["height"] = stringutils.get_before(heightpart, '"') widthpart = stringutils.get_after(scriptText, 'width: "') ret["width"] = stringutils.get_before(widthpart, '"') imagepart = stringutils.get_after(scriptText, 'image: "') ret["image"] = stringutils.get_before(imagepart, '"') return ret
def getMetadata(self): soup = self.getNextStep() scripts = soup.find("div", id="divxshowboxt").findAll("script") ret = dict() for script in scripts: text = script.getText() if len(text) > 0 and text.count("var file_name = escape('") > 0: namepart = stringutils.get_after(text, "var file_name = escape('") ret["name"] = stringutils.get_before(namepart, "');\n") ret["extension"] = ret["name"][-3:] return ret
def getVideo(self): newsoup = self.getStep2() target_div = newsoup.find("div", {"class": "getpremium_heading4"}) links = target_div.findAll("center") return stringutils.get_after(links[1].input["onclick"], "document.location='")[:-1]
def getVideo(self): newsoup = self.getStep2() target_div = newsoup.find("div", {"class":"getpremium_heading4"}) links = target_div.findAll("center") return stringutils.get_after(links[1].input["onclick"],"document.location='")[:-1]