def handle_job_info(info): tools.sleep_some_time() title,link,release_time=info url=url_host+link info={} info['title']=title info['web_url']=url info['release_time']=tools.get_real_time(release_time) info['job_type']=0 info['authentication']=0 info.update(get_message_jobs(url)) print(info['title'],info['company'],info['release_time']) return info
def handle_job_message(obj): """ 处理兼职信息 :param obj: :return: """ tools.sleep_some_time() response = requests.get(obj['web_url']) if response.status_code != 200: log.error("网址(%s)无法访问,状态码:%d" % (obj['web_url'], response.status_code)) return obj obj['web_html'] = response.content obj['company'] = tools.get_company_name(obj['web_html']) obj['position'] = tools.get_work_position(obj['web_html']) obj['work_city'] = tools.get_work_citys(obj['web_html']) return obj
def handle_all_data(url): """ 获取每一条信息 :param url: :return: """ tools.sleep_some_time() zhaopin_data = {} html = Get_html(url) zhaopin_data['web_url'] = url zhaopin_data['web_html'] = html zhaopin_data['title'] = get_title(html) zhaopin_data['release_time'] = tools.get_real_time(get_date(html)) zhaopin_data['company'] = tools.get_company_name(html) zhaopin_data['position'] = tools.get_work_position(html) zhaopin_data['work_city'] = tools.get_work_citys(html) zhaopin_data['message_source'] = '华农园艺学院官网' print(zhaopin_data['title'],zhaopin_data['release_time'],zhaopin_data['message_source'],zhaopin_data['company']) return zhaopin_data
def fetch(): result=[] infos = get_message_title_and_url_list(1) for info in infos: tools.sleep_some_time() title,link=info url=url_host+link info={} info['title']=title info['web_url']=url info['message_source']="生命科学学院官网" info['job_type']=0 info['authentication']=0 info.update(get_message_jobs(url)) result.append(info) print(info['title'],info['company'],info['release_time']) return result
def fetch(): result = [] infos = get_message_title_and_url_list(1) for info in infos: tools.sleep_some_time() title, link = info url = url_host + link info = {} info['title'] = title info['web_url'] = url info['message_source'] = "生命科学学院官网" info['job_type'] = 0 info['authentication'] = 0 info.update(get_message_jobs(url)) result.append(info) print(info['title'], info['company'], info['release_time']) return result
def handle_all_data(url): """ 获取每一条信息 :param url: :return: """ tools.sleep_some_time() zhaopin_data = {} html = Get_html(url) zhaopin_data['web_url'] = url zhaopin_data['web_html'] = html zhaopin_data['title'] = get_title(html) zhaopin_data['release_time'] = tools.get_real_time(get_date(html)) zhaopin_data['company'] = tools.get_company_name(html) zhaopin_data['position'] = tools.get_work_position(html) zhaopin_data['work_city'] = tools.get_work_citys(html) zhaopin_data['message_source'] = '华农资环学院官网' print(zhaopin_data['title'], zhaopin_data['release_time'], zhaopin_data['message_source'], zhaopin_data['company']) return zhaopin_data