cwx/PyComicPackRouMan
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fixt

Browse Source
This commit is contained in:
caiwx86 2022-12-08 01:03:58 +08:00
parent 2553de0a9d
commit ebb49ce04c
1 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
utils/HtmlUtils.py
View File

@ -11,7 +11,7 @@ class htmlUtils:
url_data = {} url_data = {}
@classmethod @classmethod
def getHTML(cls, curl): def getHTML(cls, curl,type=None):
rstr = r"[\/\\\:\*\?\"\<\>\|\.]" #  '/ \ : * ? " < > |' rstr = r"[\/\\\:\*\?\"\<\>\|\.]" #  '/ \ : * ? " < > |'
#file_url = re.sub(rstr, "_", curl) #file_url = re.sub(rstr, "_", curl)
keys = cls.url_data.keys() keys = cls.url_data.keys()
@ -29,7 +29,10 @@ class htmlUtils:
try: try:
print("请求地址：",curl) print("请求地址：",curl)
res = s.get(curl,stream=True, headers=cls.headers, timeout=20) res = s.get(curl,stream=True, headers=cls.headers, timeout=20)
url_text = html.fromstring(res.text) if type == "json":
url_text = res.json()
else:
url_text = html.fromstring(res.text)
except: except:
print(f'Retry! 第{count}次') print(f'Retry! 第{count}次')
time.sleep(3) time.sleep(3)
@ -43,15 +46,9 @@ class htmlUtils:
cls.url_data.update(data) cls.url_data.update(data)
return url_text return url_text
@classmethod
def getBytes(cls, url):
return requests.get(url, headers=cls.headers,stream=True,timeout=30)
@classmethod @classmethod
def getJSON(cls,curl): def getJSON(cls,curl):
res = requests.get(curl, headers=cls.headers,timeout=30) return cls.getHTML(curl,type="json")
data_json = res.json()
return data_json
@classmethod @classmethod
def xpathData(cls,c_xpath,url=None,num=None,not_eq=None): def xpathData(cls,c_xpath,url=None,num=None,not_eq=None):