python爬虫入门
每个网站都应该提供API，以结构化的格式共享数据。但现实情况下，虽然有提供，但是通常会限制可以抓取的数据，以及访问这些数据的频率。对于网站开发者而言，维护前端界面比维护后端API接口优先级更高。所以应该学习网络爬虫的相关知识。
前期准备：
１．检查robots.txt文件，了解限制，减少爬虫被封禁的可能性。
２.检查网站地图（Sitemap文件),帮助定位网站最新的内容。
３.估算网站大小(使用串行还是分布式)
４.识别网站所用技术(builtwith模块)
import builtwith
print(builtwith.parse('http://example.webscraping.com'))
＃{'web-servers': ['Nginx'], 'web-frameworks': ['Web2py', 'Twitter Bootstrap'], 'programming-languages': ['Python'], 'javascript-frameworks': ['jQuery', 'Modernizr', 'jQuery UI']}5.寻找网站所有者，用WHOIS协议查询域名的注册者是谁
import whois
print(whois.whois('appspot.com')){
“domain_name”: [
“APPSPOT.COM”,
“appspot.com”
],
“registrar”: “MarkMonitor, Inc.”,
“whois_server”: “whois.markmonitor.com”,
“referral_url”: null,
“updated_date”: [
“2018-02-06 10:30:28”,
“2018-02-06 02:30:29”
],
“creation_date”: [
“2005-03-10 02:27:55”,
“2005-03-09 18:27:55”
],
“expiration_date”: [
“2019-03-10 01:27:55”,
“2019-03-09 00:00:00”
],
“name_servers”: [
“NS1.GOOGLE.COM”,
“NS2.GOOGLE.COM”,
“NS3.GOOGLE.COM”,
“NS4.GOOGLE.COM”,
“ns3.google.com”,
“ns1.google.com”,
“ns4.google.com”,
“ns2.google.com”
],
“status”: [
“clientDeleteProhibited https://icann.org/epp#clientDeleteProhibited“,
“clientTransferProhibited https://icann.org/epp#clientTransferProhibited“,
“clientUpdateProhibited https://icann.org/epp#clientUpdateProhibited“,
“serverDeleteProhibited https://icann.org/epp#serverDeleteProhibited“,
“serverTransferProhibited https://icann.org/epp#serverTransferProhibited“,
“serverUpdateProhibited https://icann.org/epp#serverUpdateProhibited“,
“clientUpdateProhibited (https://www.icann.org/epp#clientUpdateProhibited)”,
“clientTransferProhibited (https://www.icann.org/epp#clientTransferProhibited)”,
“clientDeleteProhibited (https://www.icann.org/epp#clientDeleteProhibited)”,
“serverUpdateProhibited (https://www.icann.org/epp#serverUpdateProhibited)”,
“serverTransferProhibited (https://www.icann.org/epp#serverTransferProhibited)”,
“serverDeleteProhibited (https://www.icann.org/epp#serverDeleteProhibited)”
],
“emails”: [
“[email protected]”,
“[email protected]”
],
“dnssec”: “unsigned”,
“name”: null,
“org”: “Google LLC”,
“address”: null,
“city”: null,
“state”: “CA”,
“zipcode”: null,
“country”: “US”
}
重试下载功能：
import urllib3
＃num_retries，限制重试次数
def downlaod(url,num_retries=2):
print('Downloading:',url)
try:
html=urllib3.urlopen(url).read()
except urllib3.URLERROR as e:
print('Download error:',e.reason)
html=None
if num_retries>0:
if(hasattr(e,'code') and 500<=e.code<600):
return downlaod(url,num_retries-1)
return html设置用户代理：
import urllib3
#num_retries，限制重试次数
def downlaod(url,user_agent='wswp',num_retries=2):
print('Downloading:',url)
headers={'User_agent':user_agent}
request=urllib3.Request(url,headers=headers)
try:
html=urllib3.urlopen(request).read()
except urllib3.URLError as e:
print('Download error:',e.reason)
html=None
if num_retries>0:
if(hasattr(e,'code') and 500<=e.code<600):
#retry 5XX HTTP errors
return downlaod(url,user_agent,num_retries-1)
return html网站地图爬虫
sitemap
# -*- coding: utf-8 -*-
import re
from common import download
def crawl_sitemap(url):
# download the sitemap file
sitemap = download(url)
# extract the sitemap links
links = re.findall('(.*?) ', sitemap)
# download each link
for link in links:
html = download(link)
# scrape html here
# ...
if __name__ == '__main__':
crawl_sitemap('http://example.webscraping.com/sitemap.xml')ID遍历爬虫
URL包含页面别名，对优化搜索引擎有帮助，同时这是网站结构的弱点，一般情况下，Web服务器会忽略这个字符串，只使用ID来匹配数据库中的相关记录。
链接爬虫
爬虫限速（延时）
避免爬虫陷阱（设置深度）
（python2.7)
高级链接爬虫：
import re
import urlparse
import urllib2
import time
from datetime import datetime
import robotparser
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:
"""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):
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.now() - last_accessed).seconds
if sleep_secs > 0:
time.sleep(sleep_secs)
self.domains[domain] = 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.code
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 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
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 get_links(html):
"""Return a list of links from html
"""
# a regular expression to extract all links from the webpage
webpage_regex = re.compile(']+href=["\'](.*?)["\']' , re.IGNORECASE)
# list of all links from the webpage
return webpage_regex.findall(html)
if __name__ == '__main__':
link_crawler('http://example.webscraping.com', '/(index|view)', delay=0, num_retries=1, user_agent='BadCrawler')
link_crawler('http://example.webscraping.com', '/(index|view)', delay=0, num_retries=1, max_depth=1,
user_agent='GoodCrawler')