def query_user_page(url, retry=10, timeout=60):
"""
Returns the scraped user data from a twitter user page.
:param url: The URL to get the twitter user info from (url contains the user page)
:param retry: Number of retries if something goes wrong.
:return: Returns the scraped user data from a twitter user page.
"""
try:
proxy = next(proxy_pool)
logger.info('Using proxy {}'.format(proxy))
response = requests.get(url, headers=HEADER, proxies={"http": proxy})
html = response.text or ''
user_info = User.from_html(html)
if not user_info:
return None
return user_info
except requests.exceptions.HTTPError as e:
logger.exception('HTTPError {} while requesting "{}"'.format(e, url))
except requests.exceptions.ConnectionError as e:
logger.exception('ConnectionError {} while requesting "{}"'.format(
e, url))
except requests.exceptions.Timeout as e:
logger.exception('TimeOut {} while requesting "{}"'.format(e, url))
if retry > 0:
logger.info('Retrying... (Attempts left: {})'.format(retry))
return query_user_page(url, retry - 1)
logger.error('Giving up.')
return None
def query_user_page(url, retry=10):
"""
Returns the scraped user data from a twitter user page.
:param url: The URL to get the twitter user info from (url contains the user page)
:param retry: Number of retries if something goes wrong.
:return: Returns the scraped user data from a twitter user page.
"""
try:
response = requests.get(url, headers=HEADER)
html = response.text or ""
user = User()
user_info = user.from_html(html)
if not user_info:
return None
return user_info
except requests.exceptions.HTTPError as e:
logger.exception('HTTPError {} while requesting "{}"'.format(e, url))
except requests.exceptions.ConnectionError as e:
logger.exception('ConnectionError {} while requesting "{}"'.format(
e, url))
except requests.exceptions.Timeout as e:
logger.exception('TimeOut {} while requesting "{}"'.format(e, url))
if retry > 0:
logger.info("Retrying... (Attempts left: {})".format(retry))
return query_user_page(url, retry - 1)
logger.error("Giving up.")
return None
def query_user_page(url, retry=10):
"""
Returns the scraped user data from a twitter user page.
:param url: The URL to get the twitter user info from (url contains the user page)
:param retry: Number of retries if something goes wrong.
:return: Returns the scraped user data from a twitter user page.
"""
try:
response = requests.get(url, headers=HEADER)
html = response.text or ''
user = User()
user_info = user.from_html(html)
if not user_info:
return None
return user_info
except requests.exceptions.HTTPError as e:
logger.exception('HTTPError {} while requesting "{}"'.format(
e, url))
except requests.exceptions.ConnectionError as e:
logger.exception('ConnectionError {} while requesting "{}"'.format(
e, url))
except requests.exceptions.Timeout as e:
logger.exception('TimeOut {} while requesting "{}"'.format(
e, url))
if retry > 0:
logger.info('Retrying... (Attempts left: {})'.format(retry))
return query_user_page(url, retry-1)
logger.error('Giving up.')
return None
