问题遇到的现象和发生背景
如下javascript中的内容,在使用python哦啊去的时候,不知道获取方法
问题相关代码,请勿粘贴截图
@staticmethod
def request_url(url, headers=None, params=None, method='GET'):
if not headers:
headers = SpiderHeader
retry = 0
while retry < AnnDef.MaxRetry:
retry += 1
try:
if method == 'GET':
r = requests.get(url, headers=headers, params=params)
elif method == 'POST':
r = requests.post(url, headers=headers, params=params)
else:
return None
if r.status_code != 200:
LogUtils.debug(f"get {url} 失败: {r}, remain retry= {retry}")
time.sleep(5)
continue
r.encoding = 'utf-8'
return BeautifulSoup(r.text, 'lxml')
except Exception as err:
LogUtils.error(f"get {url}, remain retry= {retry}, error:{err}")
time.sleep(5)
return None
def download_detail(ann):
if not ann.excel_prepare(): # 处理准备信息
ann.excel_ending()
return False
headers = SpiderHeader
test_url = 'http://www.ccgp-hebei.gov.cn/ts/ts_lx/cggg/zhbggAAAA/202208/t20220805_1649861.html'
soup = ann.request_url(test_url, headers)
# xx = soup.find('table', id='SupplierInfos') # 实际最后封装在这个表格中
xx = soup.find_all('script', type='text/javascript')
for t in xx:
print(t.text)
运行结果及报错内容
无法获取内容
我想要达到的结果
获取如下内容