#-*- coding:UTF-8 -*- #原来创建对象时或者是调用类以外的方法时提示没有定义是因为这些类或方法的位置不应该放在主函数后面,而应该放在主函数前面 import urlparse import urllib2 import random import time from datetime import datetime, timedelta import socket import robotparser import csv import re import lxml.html DEFAULT_AGENT = 'wswp' DEFAULT_DELAY = 5 DEFAULT_RETRIES = 1 DEFAULT_TIMEOUT = 60 def link_crawler(seed_url, link_regex=None, max_depth=-1, max_urls=-1, user_agent='wswp', scrape_callback=None, cache=None): """Crawl from the given seed URL following links matched by link_regex """ # the queue of URL's that still need to be crawled 双向队列里面存储url crawl_queue = [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)#获取robots.txt D = Downloader(DEFAULT_DELAY, DEFAULT_AGENT, None, DEFAULT_RETRIES, DEFAULT_TIMEOUT, None, None) while crawl_queue: url = crawl_queue.pop()#移除列表中的元素,并且返回该元素的值 depth = seen[url] # check url passes robots.txt restrictions if rp.can_fetch(user_agent, url):#确定指定的用户代理是否允许访问网页 html = D(url) links = [] if scrape_callback: links.extend(scrape_callback(url, html) or []) 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) #返回绝对链接 # 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 def get_robots(url): """Initialize robots parser for this domain """ rp = robotparser.RobotFileParser() rp.set_url(urlparse.urljoin(url, '/robots.txt'))#绝对链接 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 urldefrag(url)将url分解成去掉fragment的新url和去掉的fragment的二元组 return urlparse.urljoin(seed_url, link)#绝对链接 def same_domain(url1, url2): """Return True if both URL's belong to same domain """ #将url分解成部件的6元组 return urlparse.urlparse(url1).netloc == urlparse.urlparse(url2).netloc def get_links(html): """Return a list of links from html """ # a regular expression to extract all links from the webpage #re.compile()函数将正则表达式的字符串形式编译为Pattern实例,然后使用Pattern实例处理文本并获得匹配结果(一个Match实例),最后使用Match实例获得信息,进行其他的操作。 webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE) # list of all links from the webpage return webpage_regex.findall(html) class Downloader: def __init__(self, delay=DEFAULT_DELAY, user_agent=DEFAULT_AGENT, proxies=None, num_retries=DEFAULT_RETRIES, timeout=DEFAULT_TIMEOUT, opener=None, cache=None): socket.setdefaulttimeout(timeout) self.throttle = Throttle(delay) self.user_agent = user_agent self.proxies = proxies self.num_retries = num_retries self.opener = opener self.cache = cache def __call__(self, url): result = None if self.cache: try: result = self.cache[url] except KeyError: # url is not available in cache pass else: if self.num_retries > 0 and 500 <= result['code'] < 600: # server error so ignore result from cache and re-download result = None if result is None: # result was not loaded from cache so still need to download self.throttle.wait(url) proxy = random.choice(self.proxies) if self.proxies else None headers = {'User-agent': self.user_agent} result = self.download(url, headers, proxy=proxy, num_retries=self.num_retries) if self.cache: # save result to cache self.cache[url] = result return result['html'] def download(self, url, headers, proxy, num_retries, data=None): print 'Downloading:', url request = urllib2.Request(url, data, headers or {}) opener = self.opener or 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 Exception as e: print 'Download error:', str(e) html = '' if hasattr(e, 'code'): code = e.code if num_retries > 0 and 500 <= code < 600: # retry 5XX HTTP errors return self._get(url, headers, proxy, num_retries - 1, data) else: code = None return {'html': html, 'code': code} class ScrapeCallback: def __init__(self): self.writer = csv.writer(open('countries.csv', 'w')) self.fields = ('area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code', 'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages') self.writer.writerow(self.fields) def __call__(self, url, html): if re.search('view', url): tree = lxml.html.fromstring(html) row = [] for field in self.fields: row.append(tree.cssselect('table > tr#places_{}__row > td.w2p_fw'.format(field))[0].text_content()) self.writer.writerow(row) class Throttle: """Throttle downloading by sleeping between requests to 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): """Delay if have accessed this domain recently """ domain = urlparse.urlsplit(url).netloc last_accessed = self.domains.get(domain) if self.delay > 0 and last_accessed is not None: sleep_secs = self.delay - (datetime.now() - last_accessed).seconds if sleep_secs > 0: time.sleep(sleep_secs) self.domains[domain] = datetime.now() if __name__ == '__main__': link_crawler('http://example.webscraping.com', '/(index|view)', scrape_callback=ScrapeCallback()) C:\Anaconda\python.exe C:/Users/Administrator/PythonWorkSpace/python04.py Downloading: http://example.webscraping.com Downloading: http://example.webscraping.com/index/1 Downloading: http://example.webscraping.com/index/2 Process finished with exit code 1
为链接爬虫添加缓存支持
最新推荐文章于 2023-08-26 14:20:33 发布