def parse_episodes(self, response):
episodes_d = xml_to_dict(response.body)
comicItem = response.request.meta["item"]
comicItem["episodes"].append(dict(name=response.request.meta["episode_name"], data=episodes_d["data"]))
if len(comicItem["episodes"]) == response.request.meta["episodes_num"]:
self.log(comicItem, "comicItem")
yield comicItem
def parse_detail_page(self, response):
vod_detail_d = xml_to_dict(response.body)
meta = response.request.meta
comicItem = ComicItem()
comicItem["actor"] = vod_detail_d["data"]["actor"]
comicItem["desc"] = vod_detail_d["data"]["desc"]
comicItem["director"] = vod_detail_d["data"]["director"]
comicItem["img"] = vod_detail_d["data"]["img"]
comicItem["name"] = vod_detail_d["data"]["name"]
comicItem["site"] = vod_detail_d["data"]["site"]
comicItem["title"] = meta["title"]
comicItem["detail_url"] = meta["detail_url"]
comicItem["thumbnail"] = meta["thumbnail"]
comicItem["tags"] = meta["tags"]
comicItem["episodes"] = []
vod_detail_d["data"]["url"]["foobar"] = self.make_dict_iterable(vod_detail_d["data"]["url"]["foobar"])
episodes_num = len(vod_detail_d["data"]["url"]["foobar"])
for url in vod_detail_d["data"]["url"]["foobar"]:
yield Request(
url["url"],
meta={"item": comicItem, "episode_name": url["name"], "episodes_num": episodes_num},
callback=self.parse_episodes,
)
def parse(self, response):
tv_live_d = xml_to_dict(response.body)
item = HDPLiveTVItem()
item['data'] = tv_live_d
return item
