def parse_movie_detail(self):
url = self.url
text = request_and_parse(url=url,
params=None,
headers=MTIME_HTML_HEADERS)
date_dict = self.extract_movie_detail(text)
return date_dict
def get_movie_stills(self):
"""
get movie's stills,contains img_id, img_220 ,img_1000,img_235
:return:
"""
url = movie_stills_url.format(id=self.id)
text = request_and_parse(url=url,
params=None,
headers=MTIME_STILLS_HEADERS)
result_json = extract_json(text, regex_pattern_stills)
return result_json
def parse_all_director_to_list(self):
url = self.url
text = request_and_parse(url=url,
params=None,
headers=MTIME_HTML_HEADERS)
html = etree.HTML(text)
directors = html.xpath('//dl[@class="info_l"]/dd[1]/a')
temp_dict, temp_list = {}, []
for director in directors:
temp_dict['name'] = director.xpath("./text()")[0]
temp_dict['url'] = director.xpath("./@href")[0]
temp_list.append(temp_dict.copy())
return temp_list
def parse_all_actor_to_list(self):
url = self.url + FULL_CREDITS_SUFFIX
text = request_and_parse(url=url,
params=None,
headers=MTIME_HTML_HEADERS)
html = etree.HTML(text)
main_actors = html.xpath('//div[@class="db_actor"]/dl[1]/dd')
temp_dict, temp_list = {}, []
for actor in main_actors:
temp_dict['img'] = actor.xpath(".//img/@src")[0]
temp_dict['name_cn'] = actor.xpath(".//h3/a/text()")[0]
temp_dict['name_en'] = actor.xpath(".//p/a/text()")[0]
temp_dict['actor_url'] = actor.xpath(".//p/a/@href")[0]
temp_dict['play_role'] = actor.xpath("./div[2]//h3/text()")[0]
temp_list.append(temp_dict.copy())
return temp_list
def get_movie_box_office(self):
movie_detail_params = {
"Ajax_CallBack": "true",
"Ajax_CallBackType": "Mtime.Library.Services",
"Ajax_CallBackMethod": "GetMovieOverviewRating",
"Ajax_CrossDomain": "1",
"Ajax_RequestUrl": self.url,
"t": get_current_date_str(),
"Ajax_CallBackArgument0": self.get_mid_from_url()
}
text = request_and_parse(url=movie_detail_API_url,
params=movie_detail_params,
headers=MTIME_SERVICE_HEADERS)
result = extract_json(text, regex_pattern_api)
return result
def get_photo_data(self):
url = self.person_url + PHOTO_SUFFIX
text = request_and_parse(url=url, params=None, headers=MTIME_PEOPLE_HEADERS)
result_json = extract_json(text, regex_pattern_director_picture)
return result_json
def request_with_url(url):
text = request_and_parse(url=url, params=None, headers=DIRECTOR_HEADERS)
html = etree.HTML(text)
return html