Skip to content

解决auth验证登录的网络问题 ，以及更新beautiful_soup find 不匹配的问题 #77

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Oh-Little-Papaya wants to merge 2 commits into
base: master
Choose a base branch
from
Open

解决auth验证登录的网络问题 ，以及更新beautiful_soup find 不匹配的问题 #77

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bcac5d0
modified: auth.py
Jul 9, 2016
82000fb
modified: zhihu.py
Jul 10, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 27 additions & 3 deletions auth.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,15 @@ def __init__(self, message):

def download_captcha():
url = "https://www.zhihu.com/captcha.gif"
r = requests.get(url, params={"r": random.random(), "type": "login"}, verify=False)
headers = {
'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36",
'Host': "www.zhihu.com",
'Origin': "http://www.zhihu.com",
'Pragma': "no-cache",
'Referer': "http://www.zhihu.com/",
'X-Requested-With': "XMLHttpRequest"
}
r = requests.get(url, params={"r": random.random(), "type": "login"}, verify=False, headers=headers)
if int(r.status_code) != 200:
raise NetworkError(u"验证码请求失败")
image_name = u"verify." + r.headers['content-type'].split("/")[1]
Expand Down Expand Up @@ -96,7 +104,15 @@ def download_captcha():

def search_xsrf():
url = "http://www.zhihu.com/"
r = requests.get(url, verify=False)
headers = {
'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36",
'Host': "www.zhihu.com",
'Origin': "http://www.zhihu.com",
'Pragma': "no-cache",
'Referer': "http://www.zhihu.com/",
'X-Requested-With': "XMLHttpRequest"
}
r = requests.get(url, verify=False, headers=headers)
if int(r.status_code) != 200:
raise NetworkError(u"验证码请求失败")
results = re.compile(r"\<input\stype=\"hidden\"\sname=\"_xsrf\"\svalue=\"(\S+)\"", re.DOTALL).findall(r.text)
Expand Down Expand Up @@ -163,7 +179,15 @@ def upload_form(form):
def islogin():
# check session
url = "https://www.zhihu.com/settings/profile"
r = requests.get(url, allow_redirects=False, verify=False)
headers = {
'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36",
'Host': "www.zhihu.com",
'Origin': "http://www.zhihu.com",
'Pragma': "no-cache",
'Referer': "http://www.zhihu.com/",
'X-Requested-With': "XMLHttpRequest"
}
r = requests.get(url, allow_redirects=False, verify=False, headers=headers)
status_code = int(r.status_code)
if status_code == 301 or status_code == 302:
# 未登录
Expand Down
9 changes: 5 additions & 4 deletions zhihu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -314,7 +314,7 @@ def get_title(self):
if self.soup == None:
self.parser()
soup = self.soup
title = soup.find("h2", class_="zm-item-title").string.encode("utf-8").replace("\n", "")
title = soup.find("span", class_="zm-editable-content").string.encode("utf-8").replace("\n", "")
self.title = title
if platform.system() == 'Windows':
title = title.decode('utf-8').encode('gbk')
Expand Down Expand Up @@ -662,7 +662,7 @@ def get_topics_num(self):
if self.soup == None:
self.parser()
soup = self.soup
topics_num = soup.find_all("div", class_="zm-profile-side-section-title")[1].strong.string.encode("utf-8")
topics_num = soup.find_all("div", class_="zm-profile-side-section-title")[2].strong.string.encode("utf-8")
I=''
for i in topics_num:
if i.isdigit():
Expand Down Expand Up @@ -1067,7 +1067,7 @@ def get_question(self):
if self.soup == None:
self.parser()
soup = self.soup
question_link = soup.find("h2", class_="zm-item-title zm-editable-content").a
question_link = soup.find("h2", class_="zm-item-title").a
url = "http://www.zhihu.com" + question_link["href"]
title = question_link.string.encode("utf-8")
question = Question(url, title)
Expand Down Expand Up @@ -1144,7 +1144,8 @@ def to_txt(self):
if platform.system() == 'Windows':
anon_user_id = "匿名用户".decode('utf-8').encode('gbk')
else:
anon_user_id = "匿名用户"
anon_uget_titleser_id = "匿名用户"
anon_user_id = "匿名用户".decode('utf-8').encode('gbk')
if self.get_author().get_user_id() == anon_user_id:
if not os.path.isdir(os.path.join(os.path.join(os.getcwd(), "text"))):
os.makedirs(os.path.join(os.path.join(os.getcwd(), "text")))
Expand Down