def get_page(self, type, tab):
"""获取页面，为了简便，在url后面添加了所有可能用到的数据，即使有多余的参数也不影响
Args:
tab: 访问页面时在url后面所用到的数据。1 工商公示信息， 2 企业公示信息， 3 其他部门公示信息
"""
url = CrawlerUtils.add_params_to_url(
self.urls[type], {
'entId': self.ent_id,
'ent_id': self.ent_id,
'entid': self.ent_id,
'credit_ticket': self.credit_ticket,
'entNo': self.ent_number,
'entName': '',
'timeStamp': self.generate_time_stamp(),
'clear': 'true',
'str': tab
})
logging.error('get %s, url:\n%s\n' % (type, url))
resp = self.crawl_page_by_url(url)
if resp.status_code != 200:
logging.error('get page failed by url %s' % url)
return
page = resp.content
time.sleep(random.uniform(0.2, 1))
return page
def get_page(self, type, tab):
"""获取页面，为了简便，在url后面添加了所有可能用到的数据，即使有多余的参数也不影响
Args:
tab: 访问页面时在url后面所用到的数据。1 工商公示信息， 2 企业公示信息， 3 其他部门公示信息
"""
url = CrawlerUtils.add_params_to_url(
self.urls[type], {
'entId': self.ent_id,
'ent_id': self.ent_id,
'entid': self.ent_id,
'credit_ticket': self.credit_ticket,
'entNo': self.ent_number,
'entName': '',
'timeStamp': self.generate_time_stamp(),
'clear': 'true',
'str': tab
})
settings.logger.info('get %s, url:\n%s\n' % (type, url))
resp = self.reqst.get(url)
if resp.status_code != 200:
settings.logger.warn('get page failed by url %s' % url)
return
page = resp.content
time.sleep(random.uniform(0.2, 1))
if settings.save_html:
CrawlerUtils.save_page_to_file(
self.html_restore_path + type + '.html', page)
return page
def get_detail_link(self, bs4_tag, page):
"""获取详情链接 url，在bs tag中或者page中提取详情页面
Args:
bs4_tag： beautifulsoup 的tag
page: 页面数据
"""
detail_op = bs4_tag.get('onclick')
pat_view_info = re.compile(r'viewInfo\(\'([\w]+)\'\)')
pat_show_dialog = re.compile(r'showDialog\(\'([^\'\n]+)\'')
next_url = ''
if detail_op and pat_view_info.search(detail_op):
m = pat_view_info.search(detail_op)
val = m.group(1)
#detail link type 1, for example : ind_comm_pub info --- registration info -- shareholders info
pat = re.compile(
r'var +url += +rootPath +\+ +\"(.+\?)([\w]+)=\"\+[\w]+\+\"')
m1 = pat.search(page)
if m1:
addition_url = m1.group(1)
query_key = m1.group(2)
next_url = CrawlerUtils.add_params_to_url(
self.crawler.urls['host'] + addition_url, {
query_key: val,
'entId': self.crawler.ent_id,
'ent_id': self.crawler.ent_id,
'entid': self.crawler.ent_id,
'credit_ticket': self.crawler.credit_ticket,
'entNo': self.crawler.ent_number
})
elif detail_op and pat_show_dialog.search(detail_op):
#detail link type 2, for example : ind_comm_pub_info --- registration info ---- modify info
m = pat_show_dialog.search(detail_op)
val = m.group(1)
next_url = self.crawler.urls['host'] + val
elif 'href' in bs4_tag.attrs.keys():
#detail link type 3, for example : ent pub info ----- enterprise annual report
next_url = self.crawler.urls['host'] + bs4_tag['href']
return next_url
