python爬虫（一）

买了挺久的《用python写网络爬虫》，一直没有怎么细看。最近因为像测试下搜索，但是苦于自己没有海量的数据，

所以准备用python写个爬虫，爬取一些网站（瓜子二手车，下厨房等）的数据

今天将第一章的内容进行了测试：

环境准备如下：

python2.7(windows)

vscode(需要装python插件)

第一章主要实现了一个基本的爬虫。用于了解网站，用户代理，网站地图，爬取延时以及各种爬取策略。

代码部分如下：

import urllib2
import re
import itertools
import urlparse
import robotparser
import time
import datetime
import Queue

def link_crawler(seed_url, link_regex=None, delay=5, max_depth=-1, max_urls=-1, headers=None, user_agent='wswp', proxy=None, num_retries=1):
    """Crawl from the given seed URL following links matched by link_regex
    """
    # the queue of URL's that still need to be crawled
    crawl_queue = Queue.deque([seed_url])
    # the URL's that have been seen and at what depth
    seen = {seed_url: 0}
    # track how many URL's have been downloaded
    num_urls = 0
    rp = get_robots(seed_url)
    throttle = Throttle(delay)
    headers = headers or {}
    if user_agent:
        headers['User-agent'] = user_agent

    while crawl_queue:
        url = crawl_queue.pop()
        # check url passes robots.txt restrictions
        if rp.can_fetch(user_agent, url):
            throttle.wait(url)
            html = download(url, headers, proxy=proxy, num_retries=num_retries)
            links = []

            depth = seen[url]
            if depth != max_depth:
                # can still crawl further
                if link_regex:
                    # filter for links matching our regular expression
                    links.extend(link for link in get_links(html) if re.match(link_regex, link))

                for link in links:
                    link = normalize(seed_url, link)
                    # check whether already crawled this link
                    if link not in seen:
                        seen[link] = depth + 1
                        # check link is within same domain
                        if same_domain(seed_url, link):
                            # success! add this new link to queue
                            crawl_queue.append(link)

            # check whether have reached downloaded maximum
            num_urls += 1
            if num_urls == max_urls:
                break
        else:
            print 'Blocked by robots.txt:', url


class Throttle:
    """ Add a delay betweem downloads to the same domain """
    def __init__(self, delay):
        # amount of delay between downloads for each domain
        self.delay = delay
        # timestamp of when a domain was last accessed
        self.domains = {}

    def wait(self, url):
        domain = urlparse.urlparse(url).netloc
        last_accessed = self.domains.get(domain)

        if self.delay > 0 and last_accessed is not None:
            sleep_secs = self.delay - (datetime.datetime.now() - last_accessed).seconds

            if sleep_secs > 0:
                # domain has been accessed recently
                # so need to sleep
                time.sleep(sleep_secs)
        #update the last accessed time
        self.domains[domain] = datetime.datetime.now()

def download(url, headers, proxy, num_retries, data=None):
    print 'Downloading:', url
    request = urllib2.Request(url, data, headers)
    opener = urllib2.build_opener()
    if proxy:
        proxy_params = {urlparse.urlparse(url).scheme: proxy}
        opener.add_handler(urllib2.ProxyHandler(proxy_params))
    try:
        response = opener.open(request)
        html = response.read()
        code = response.code
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = ''
        if hasattr(e, 'code'):
            code = e.errno
            if num_retries > 0 and 500 <= code < 600:
                # retry 5XX HTTP errors
                return download(url, headers, proxy, num_retries-1, data)
        else:
            code = None
    return html

def get_links(html):
    """ REturn alist of links from html """
    # a regular expression to extract all links from the webpage
    webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)
    # list of all links from the webpage
    return webpage_regex.findall(html)


def get_robots(url):
    """Initialize robots parser for this domain
    """
    rp = robotparser.RobotFileParser()
    rp.set_url(urlparse.urljoin(url, '/robots.txt'))
    rp.read()
    return rp

def normalize(seed_url, link):
    """Normalize this URL by removing hash and adding domain
    """
    link, _ = urlparse.urldefrag(link) # remove hash to avoid duplicates
    return urlparse.urljoin(seed_url, link)

def same_domain(url1, url2):
    """Return True if both URL's belong to same domain
    """
    return urlparse.urlparse(url1).netloc == urlparse.urlparse(url2).netloc


#download('http://httpstat.us/500')
#crawl_sitemap('http://example.webscraping.com/sitemap.xml')


if __name__ == '__main__':
    link_crawler('http://example.webscraping.com/places/default/', '/places/default/(index|view)', delay=0, num_retries=1, max_depth=1, user_agent='BadCrawler')
    link_crawler('http://example.webscraping.com/places/default/', '/places/default/(index|view)', delay=0, num_retries=1, max_depth=1, user_agent='GoodCrawler')

参考资料：

http://example.webscraping.com/

书中代码部分：

https://bitbucket.org/wswp/code/src/9e6b82b47087c2ada0e9fdf4f5e037e151975f0f/chapter01/link_crawler3.py?at=default&fileviewer=file-view-default

pip国内源：https://blog.csdn.net/lambert310/article/details/52412059