#!/usr/bin/env python3
# -*- coding: utf-8 -*-
__author__ = "7sDream"
import functools
import re
import os
import requests
from bs4 import BeautifulSoup as _Bs
try:
__import__("lxml")
BeautifulSoup = lambda makeup: _Bs(makeup, "lxml")
except ImportError:
BeautifulSoup = lambda makeup: _Bs(makeup, "html.parser")
Default_Header = {
"X-Requested-With": "XMLHttpRequest",
"Referer": "http://www.zhihu.com",
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; " "rv:39.0) Gecko/20100101 Firefox/39.0",
"Host": "www.zhihu.com",
}
Zhihu_URL = "http://www.zhihu.com"
Login_URL = Zhihu_URL + "/login/email"
Captcha_URL_Prefix = Zhihu_URL + "/captcha.gif?r="
Get_Profile_Card_URL = "http://www.zhihu.com/node/MemberProfileCardV2"
Get_More_Answer_URL = "http://www.zhihu.com/node/QuestionAnswerListV2"
Get_More_Followers_URL = "http://www.zhihu.com/node/ProfileFollowersListV2"
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import functools
import re
import os
from requests import Session
from bs4 import BeautifulSoup as _Bs
from bs4 import Tag, NavigableString
try:
__import__('lxml')
BeautifulSoup = lambda makeup: _Bs(makeup, 'lxml')
except ImportError:
BeautifulSoup = lambda makeup: _Bs(makeup, 'html.parser')
Default_Header = {
'X-Requested-With': 'XMLHttpRequest',
'Referer': 'http://www.zhihu.com',
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; '
'rv:39.0) Gecko/20100101 Firefox/39.0',
'Host': 'www.zhihu.com'
}
Zhihu_URL = 'http://www.zhihu.com'
Login_URL = Zhihu_URL + '/login/email'
Captcha_URL_Prefix = Zhihu_URL + '/captcha.gif?r='
Get_Profile_Card_URL = Zhihu_URL + '/node/MemberProfileCardV2'
Question_Get_More_Answer_URL = Zhihu_URL + '/node/QuestionAnswerListV2'
Answer_Add_Comment_URL = Zhihu_URL + '/node/AnswerCommentAddV2'
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import functools
import re
import os
from requests import Session
from bs4 import BeautifulSoup as _Bs
from bs4 import Tag, NavigableString
from requests.packages.urllib3.util import Retry
try:
__import__('lxml')
BeautifulSoup = lambda makeup: _Bs(makeup, 'lxml')
except ImportError:
BeautifulSoup = lambda makeup: _Bs(makeup, 'html.parser')
Default_Header = {'X-Requested-With': 'XMLHttpRequest',
'Referer': 'http://www.zhihu.com',
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; '
'rv:39.0) Gecko/20100101 Firefox/39.0',
'Host': 'www.zhihu.com'}
Zhihu_URL = 'https://www.zhihu.com'
Login_URL = Zhihu_URL + '/login/email'
Captcha_URL_Prefix = Zhihu_URL + '/captcha.gif?r='
Get_Profile_Card_URL = Zhihu_URL + '/node/MemberProfileCardV2'
Question_Get_More_Answer_URL = Zhihu_URL + '/node/QuestionAnswerListV2'
Answer_Add_Comment_URL = Zhihu_URL + '/node/AnswerCommentAddV2'
Answer_Comment_Box_URL = Zhihu_URL + '/node/AnswerCommentBoxV2'
"""Usage:link-verifier.py <pageUrl>
Example:
linkVerifier.py https://www.python.org
"""
import re
import sys
import chardet
import requests
from urllib.parse import urlparse, urlunparse
from concurrent.futures import ThreadPoolExecutor, as_completed
from bs4 import BeautifulSoup as _Bs
try:
__import__('lxml')
BeautifulSoup = (lambda markup: _Bs(markup, 'lxml'))
except ImportError:
BeautifulSoup = (lambda markup: _Bs(markup, 'html.parser'))
TIMEOUT = 6
HEADERS = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:48.0) Gecko/20100101 Firefox/48.0'
}
PATTERN_URL = re.compile(
r'(?:(?:(?:https?|ftp|file):)?//)?[-A-Za-z0-9+&@#/%?=~_|!:,.;]+[-A-Za-z0-9+&@#/%=~_|]'
)
def download(url, params=None, **kwargs):
if 'timeout' not in kwargs: