def get_data(s):
error_msg = "请开启JavaScript并刷新该页"
url = "http://wenshu.court.gov.cn/CreateContentJS/CreateContentJS.aspx"
params = {
"DocID": s,
}
#time.sleep(2)
response = session.get(url,
params=params,
proxies=random.choice(proxy_list))
text = response.content.decode()
if error_msg in text:
retry = 3
for _ in range(retry):
redirect_url = decrypt_wzws(text)
response = session.get(redirect_url)
text = response.content.decode()
if error_msg not in text:
break
else:
print("连续{}次获取数据失败".format(retry))
group_dict = parse_detail(response.text)
#pprint(group_dict)
return group_dict
def detail_page(self):
"""文书详情页"""
url = "http://wenshu.court.gov.cn/CreateContentJS/CreateContentJS.aspx"
params = {
"DocID": "029bb843-b458-4d1c-8928-fe80da403cfe",
}
response = self.session.get(url, params=params) # 请求1
text = response.content.decode()
if "请开启JavaScript并刷新该页" in text:
# 如果使用代理，确保请求1和请求2的ip为同一个，否则将继续返回"请开启JavaScript并刷新该页"
redirect_url = decrypt_wzws(text)
response = self.session.get(redirect_url) # 请求2
group_dict = parse_detail(response.text)
pprint(group_dict)
def test_list_page(self):
url = "http://wenshu.court.gov.cn/List/ListContent"
data = {
"Param": "案件类型:执行案件",
"Index": 1,
"Page": 10,
"Order": "法院层级",
"Direction": "asc",
"vl5x": Vl5x(self.session.cookies.setdefault("vjkl5", Vjkl5())),
"number": Number(),
"guid": Guid(),
}
response = self.session.post(url, data=data)
text = response.content.decode()
if self.error_msg in text:
retry = 3
for _ in range(retry):
redirect_url = decrypt_wzws(text)
response = self.session.post(redirect_url, data=data)
text = response.content.decode()
if self.error_msg not in text:
break
else:
self.fail("连续{}次获取数据失败".format(retry))
json_data = json.loads(response.json())
print("列表数据:", json_data)
run_eval = json_data.pop(0)["RunEval"]
try:
key = decrypt_runeval(run_eval)
except ValueError as e:
raise ValueError("返回脏数据") from e
else:
print("RunEval解析完成:", key, "\n")
key = key.encode()
for item in json_data:
cipher_text = item["文书ID"]
print("解密:", cipher_text)
plain_text = decrypt_doc_id(doc_id=cipher_text, key=key)
print("成功, 文书ID:", plain_text, "\n")
def test_detail_page(self):
url = "http://wenshu.court.gov.cn/CreateContentJS/CreateContentJS.aspx"
params = {
"DocID": "a8b745f3-43ac-402c-99bf-68b9a9cae635",
}
response = self.session.get(url, params=params)
text = response.content.decode()
if self.error_msg in text:
retry = 3
for _ in range(retry):
redirect_url = decrypt_wzws(text)
response = self.session.get(redirect_url)
text = response.content.decode()
if self.error_msg not in text:
break
else:
self.fail("连续{}次获取数据失败".format(retry))
group_dict = parse_detail(response.text)
pprint(group_dict)
def list_page(self):
"""文书列表页"""
url = "http://wenshu.court.gov.cn/List/ListContent"
data = {
"Param": "案件类型:刑事案件",
"Index": 1,
"Page": 10,
"Order": "法院层级",
"Direction": "asc",
"vl5x": Vl5x(self.session.cookies.setdefault("vjkl5", Vjkl5())),
"number": Number(),
"guid": Guid(),
}
response = self.session.post(url, data=data) # 请求1
text = response.content.decode()
if "请开启JavaScript并刷新该页" in text:
# 如果使用代理，确保请求1和请求2的ip为同一个，否则将继续返回"请开启JavaScript并刷新该页"
redirect_url = decrypt_wzws(text)
response = self.session.post(redirect_url, data=data) # 请求2
json_data = json.loads(response.json())
print("列表数据:", json_data)
run_eval = json_data.pop(0)["RunEval"]
try:
key = decrypt_runeval(run_eval)
except ValueError as e:
raise ValueError("返回脏数据") from e
else:
print("RunEval解析完成:", key, "\n")
key = key.encode()
for item in json_data:
cipher_text = item["文书ID"]
print("解密:", cipher_text)
plain_text = decrypt_doc_id(doc_id=cipher_text, key=key)
print("成功, 文书ID:", plain_text, "\n")