程序未按预期工作

Question

我正在尝试运行一个网络爬虫from netinstructions.com的示例程序，但它不工作。我使用以下命令运行该程序：

spider("http://www.netinstructions.com/", "python", 50)

但它总是会返回

1 Visiting: http://www.netinstructions.com
Word never found

无论我输入什么url。程序代码如下：

from html.parser import HTMLParser  
from urllib.request import urlopen  
from urllib import parse

# We are going to create a class called LinkParser that inherits some
# methods from HTMLParser which is why it is passed into the definition
class LinkParser(HTMLParser):

    # This is a function that HTMLParser normally has
    # but we are adding some functionality to it
    def handle_starttag(self, tag, attrs):
        # We are looking for the begining of a link. Links normally look
        # like <a href="www.someurl.com"></a>
        if tag == 'a':
            for (key, value) in attrs:
                if key == 'href':
                    # We are grabbing the new URL. We are also adding the
                    # base URL to it. For example:
                    # www.netinstructions.com is the base and
                    # somepage.html is the new URL (a relative URL)
                    #
                    # We combine a relative URL with the base URL to create
                    # an absolute URL like:
                    # www.netinstructions.com/somepage.html
                    newUrl = parse.urljoin(self.baseUrl, value)
                    # And add it to our colection of links:
                    self.links = self.links + [newUrl]

    # This is a new function that we are creating to get links
    # that our spider() function will call
    def getLinks(self, url):
        self.links = []
        # Remember the base URL which will be important when creating
        # absolute URLs
        self.baseUrl = url
        # Use the urlopen function from the standard Python 3 library
        response = urlopen(url)
        # Make sure that we are looking at HTML and not other things that
        # are floating around on the internet (such as
        # JavaScript files, CSS, or .PDFs for example)
        if response.getheader('Content-Type')=='text/html':
            htmlBytes = response.read()
            # Note that feed() handles Strings well, but not bytes
            # (A change from Python 2.x to Python 3.x)
            htmlString = htmlBytes.decode("utf-8")
            self.feed(htmlString)
            return htmlString, self.links
        else:
            return "",[]

# And finally here is our spider. It takes in an URL, a word to find,
# and the number of pages to search through before giving up
def spider(url, word, maxPages):  
    pagesToVisit = [url]
    numberVisited = 0
    foundWord = False
    # The main loop. Create a LinkParser and get all the links on the page.
    # Also search the page for the word or string
    # In our getLinks function we return the web page
    # (this is useful for searching for the word)
    # and we return a set of links from that web page
    # (this is useful for where to go next)
    while numberVisited < maxPages and pagesToVisit != [] and not foundWord:
        numberVisited = numberVisited +1
        # Start from the beginning of our collection of pages to visit:
        url = pagesToVisit[0]
        pagesToVisit = pagesToVisit[1:]
        try:
            print(numberVisited, "Visiting:", url)
            parser = LinkParser()
            data, links = parser.getLinks(url)
            if data.find(word)> -1:
                foundWord = True
                # Add the pages that we visited to the end of our collection
                # of pages to visit:
                pagesToVisit = pagesToVisit + links
                print(" **Success!**")
        except:
            print(" **Failed!**")
    if foundWord:
        print("The word", word, "was found at", url)
    else:
        print("Word never found")

有人知道这是怎么回事吗？我使用的是Python 3.5 (32位)，运行在Windows 10上。

Answer 1

response.getheader('Content-Type')返回text/html; charset=utf-8，它不等于text/html，所以你永远得不到任何链接。您可以查看它是否包含在字符串中：

def getLinks(self, url):
    self.links = []
    # Remember the base URL which will be important when creating
    # absolute URLs
    self.baseUrl = url
    # Use the urlopen function from the standard Python 3 library
    response = urlopen(url)
    # Make sure that we are looking at HTML and not other things that
    # are floating around on the internet (such as
    # JavaScript files, CSS, or .PDFs for example)
    if 'text/html' in response.getheader('Content-Type')

此外，pagesToVisit = pagesToVisit + links应该在if之外，因为只有在find as != -1的情况下才会添加链接。进行以下更改，您的代码将运行：

def getLinks(self, url):
        self.links = []
        # Remember the base URL which will be important when creating
        # absolute URLs
        self.baseUrl = url
        # Use the urlopen function from the standard Python 3 library
        response = urlopen(url)
        # Make sure that we are looking at HTML and not other things that
        # are floating around on the internet (such as
        print(response.getheader('Content-Type'))
        # JavaScript files, CSS, or .PDFs for example)
        if 'text/html' in response.getheader('Content-Type'):
            htmlBytes = response.read()
            # Note that feed() handles Strings well, but not bytes
            # (A change from Python 2.x to Python 3.x)
            htmlString = htmlBytes.decode("utf-8")
            self.feed(htmlString)
            return htmlString, self.links
        return "",[]

# And finally here is our spider. It takes in an URL, a word to find,
# and the number of pages to search through before giving up
def spider(url, word, maxPages):
    pagesToVisit = [url]
    foundWord = False
    # The main loop. Create a LinkParser and get all the links on the page.
    # Also search the page for the word or string
    # In our getLinks function we return the web page
    # (this is useful for searching for the word)
    # and we return a set of links from that web page
    # (this is useful for where to go next)
    for ind, url in enumerate(pagesToVisit, 1):
        if ind >= maxPages or foundWord:
            break
        # Start from the beginning of our collection of pages to visit:
        try:
            print(ind, "Visiting:", url)
            parser = LinkParser()
            data, links = parser.getLinks(url)
            if data.find(word)> -1:
                foundWord = True
                # Add the pages that we visited to the end of our collection
                # of pages to visit:
                print(" **Success!**")
            pagesToVisit.extend(links)
        except Exception as e:
            print(" **Failed!**")
    if foundWord:
        print("The word", word, "was found at", url)
    else:
        print("Word never found")

spider("http://www.netinstructions.com/", "python", 50)