def parse_epg(self, response):
content_div = response.xpath("//div[@class='schedule']/div[@class='outer-container']/"
"div[@class='inner-container']/div[contains(@class,'schedule-row')]")
if len(content_div) == 0:
raise CloseSpider('no epg info!')
day = response.url.split("/")[-1];
nextday = next_day(self.formats, day)
for div in content_div:
starttime = div.xpath(".//div[contains(@class,'program-time')]/text()").extract()[0].strip()
if starttime < "06:00":
starttime = trans_format(nextday+starttime, self.formats+"%H:%M")
else:
starttime = trans_format(day+starttime, self.formats+"%H:%M")
title = div.xpath(".//div[contains(@class,'program-info')]/h4").extract()[0].strip()
reg = re.compile(r'\<h4.*?\>\s*(?:\<a href.*?\>)*(.*?)(?:\</a\>)*\s*\</h4\>', re.S)
s = reg.search(title)
title = s.group(1)
meta = div.xpath(".//div[contains(@class,'program-info')]/p/text()").extract()[0]
meta = meta.split(":")[0].strip()
name = "%s %s" % (title, meta)
desc = div.xpath(".//div[contains(@class,'program-info')]/div[contains(@class,'program-synopsis')]/p/text()").extract()[0]
item = EpgItem()
item['name'] = name
item['desc'] = desc.strip()
item['starttime'] = starttime
item['endtime'] = ''
yield item
def parse_epg(self, response):
json_str = json.loads(response.body)
for channel in json_str:
if channel['channelName'] == "si4a":
programs = channel['channels']
for program in programs:
name = program['genre']
starttime = program['date'] + " " + program['start_time']
endtime = program['date'] + " " + program['end_time']
starttime = trans_format(starttime, "%m/%d/%Y %H:%M:%S")
endtime = trans_format(endtime, "%m/%d/%Y %H:%M:%S")
item = EpgItem()
item['name'] = name
item['starttime'] = starttime
item['endtime'] = endtime
item['desc'] = ''
yield item
def parse(self, response):
program_position = response.xpath("//div[@class='box-container-wrapper']/div[contains(@class,'date-program-wrapper')]")
for dates in program_position:
date = dates.xpath("./div[@class='box-inner-container-header']/h2/text()").extract()[0][-10:]
date = trans_format(date, "%d-%m-%Y", "%Y.%m.%d")
programs = dates.xpath("./div[@class='box-inner-container-wrapper']/div")
for program in programs:
name = program.xpath("./div[@class='title']/h2/text()").extract()[0]
times = program.xpath("./div[@class='timing']/time/text()").extract()[0]
times = times.split("/")[0][0:7].strip().replace(":", ".")
times = time12to24(times)
starttime = trans_format("%s %s" % (date, times), "%Y.%m.%d %H:%M")
ftime = datetime.datetime.strptime(starttime, "%Y.%m.%d %H:%M:%S")
ftime = ftime + datetime.timedelta(hours=8)
starttime = ftime.strftime("%Y.%m.%d %H:%M:%S")
item = EpgItem()
item['name'] = name
item['starttime'] = starttime
item['endtime'] = ''
item['desc'] = ''
yield item
def parse_epg(self, response):
date_str = response.url[-8:]
program_position = response.xpath("//div[@class='schedule_grid ']")
reg = re.compile(r"\s\s+")
for dates in program_position:
program = dates.xpath("./div[@class='schedule_details']")
program_time = program.xpath("./p[@class='info']/text()").extract()[0]
title = program.xpath("./p[@class='title']/a/text()").extract()[0]
try:
subtitle = program.xpath("./p[@class='title']/a/span/text()").extract()[0]
except IndexError:
subtitle = ""
except ValueError:
subtitle = ""
program_time = time12to24(reg.sub("", program_time).replace(" ", ""))
starttime = trans_format("%s %s" % (date_str, program_time), self.formats + " %H:%M")
item = EpgItem()
item["name"] = reg.sub("", title.strip() + subtitle.strip())
item["starttime"] = starttime
item["endtime"] = ""
item["desc"] = ""
yield item