Python crawler gets file site resources (based on Python 3.6)

Source: Internet
Author: User

Import Urllib.request

From BS4 import BeautifulSoup

From Urllib.parse import Urljoin

From cat.findlinks import Get_link

From cat.load import Schedule

Import OS
Import time
Import errno

-------the rest of the package code for import----------------
def get_link (page):  # Looking for a linked href
LinkData = []
For page in Page.find_all (' TD '):
Links = page.select ("a")
For each in Links:
# if STR (each.get (' href ')) [: 1] = = '/': Filter if code
Data=each.get (' href ')
Linkdata.append (data)
Return (LinkData)

def Schedule (a,b,c):  #当数据过大, loading display module
‘‘‘‘‘
A: Data blocks that have already been downloaded
B: Size of the data block
C: The size of the remote file
‘‘‘
per = 100.0 * A * b/c
If per > 100:
per = 100
Print ('%.2f%% '% per)
----------End-------------------


def mkdir_p (path): #递归创建多级目录
Try
Os.makedirs (PATH)
Except OSError as exc: # Python >2.5 (except OSError, exc:for Python <2.5)
if Exc.errno = = errno. Eexist and Os.path.isdir (path):
Pass
Else:raise

def file_down (connet,file):
Urllib.request.urlretrieve (connet, file, Schedule)

def decice (data):
A = '/'
If a in data:
Return 1



Def findAll (): #主函数
Url= ' http://www.nco.ncep.noaa.gov/pmb/codes/nwprod/nosofs.v3.0.4/'
page = Urllib.request.urlopen (URL). Read ()
Soup = beautifulsoup (page, ' lxml ') #利用BeautifulSoup取得网页代码
Links=get_link (soup)
# Print (links)

For Childlink in range (len (links)-1):
Childlink =childlink +1
connet = Urljoin (URL, links[childlink]) #拼接网址路径
Page_next = Urllib.request.urlopen (connet). Read ()
Soup_next = BeautifulSoup (Page_next, ' lxml ')
Link_next=get_link (soup_next) #第2次链接内的 <a href=?
File = Os.path.join (' d:\\test\\index ' + "\ \" + Links[childlink])
# Decice (Links[childlink])
# file_cre=os.path.join (' D:\\test\\index ', Links[childlink])
If Decice (Links[childlink]):
Mkdir_p (file)
Else
File_down (connet, file)

Print (connet)
For Child_next in range (len (link_next)-1):
Child_next =child_next +1
Connet_next=urljoin (Connet,link_next[child_next])
Page_next = Urllib.request.urlopen (connet_next). Read ()
SOUP_NEXTF = BeautifulSoup (Page_next, ' lxml ')
LINK_NEXTF = Get_link (SOUP_NEXTF) # <a href= within the 3rd link?
Filef = Os.path.join (' d:/test/index ' + "/", Links[childlink]+link_next[child_next])
If Decice (Links[childlink]):
Mkdir_p (Filef)
Else
File_down (Connet, Filef)
Print ("Start:%s"% time.ctime ())
Time.sleep (4)
Print ("End:%s"% time.ctime ())
Print (Connet_next)
For CHILD_NEXTT in range (len (LINK_NEXTF)-1):
CHILD_NEXTT = child_nextt + 1
Connet_nextt = Urljoin (Connet_next, Link_nextf[child_nextt])
Filet = Os.path.join (' d:/test/index ' + "/", Links[childlink] + link_next[child_next]+link_nextf[child_nextt])
If Decice (link_nextf[child_nextt]) = = 1:
Mkdir_p (Filet)
Else
File_down (connet, filet)
Print (CONNET_NEXTT)


if __name__ = = ' __main__ ':
FindAll ()


Python crawler gets file site resources (based on Python 3.6)

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.