完整代碼

# encoding:UTF-8

# from bs4 import BeautifulSoup

import urlparse

import urllib2

import re

import robotparser

import datetime

import time

import itertools

import Queue? # 同步的、線程安全的隊(duì)列類

import lxml.html

import lxml.cssselect

import csv

def crawl_sitemap(url, scrape_callback=None):

"""

1.通過robots文件記錄的鏈接爬蟲

:param url:

:return:如果有回調(diào)函數(shù)，返回回調(diào)結(jié)果

"""

sitemap = urllib2.urlopen(url).read()

links = re.findall('(.*?)', sitemap)

if scrape_callback:

for link in links:

html = urllib2.urlopen(link).read()

scrape_callback(link, html)

def crawl_id(url, scrape_callback=None):

"""

2.通過ID爬蟲,連續(xù)發(fā)生多次下載錯(cuò)誤才會(huì)退出

:param url:含有ID的鏈接的公共部分,沒有/

:return:

"""

max_error = 5

num_error = 0

throttle = Throttle(5)

for page in itertools.count(1):? # 迭代器，從1開始

link = url + ("/-%d" % page)

html = urllib2.urlopen(link).read()

if html is None:

num_error += 1

if num_error == max_error:

break

else:? # 網(wǎng)頁存在

throttle.wait(link)

scrape_callback(link, html)

num_error = 0

def link_crawler(seed_url, link_regex=None, delay=-1, max_depth=1, max_urls=-1,

headers=None, user_agent="wswp", proxy=None, num_retries=2, scrape_callback=None):

"""

3.通過鏈接爬蟲,深度優(yōu)先，禁用某些功能可將其參數(shù)設(shè)為負(fù)數(shù)

待爬蟲隊(duì)列存在，逐一判斷robots訪問權(quán)限，在等待一定時(shí)間后進(jìn)行下載，

并根據(jù)訪問深度決定是否繼續(xù)進(jìn)行訪問。如繼續(xù)，根據(jù)正則表達(dá)式匹配獲

取鏈接集，逐一規(guī)范化后，若某鏈接沒有被訪問過，且域名和種子網(wǎng)址域名相同，

則歸入待爬蟲隊(duì)列。每完成一次訪問，鏈接總數(shù)+1

:param seed_url:種子鏈接

:param link_regex:目標(biāo)鏈接識(shí)別正則表達(dá)式

:param user_agent:用戶代理

:return:爬蟲結(jié)果

"""

crawl_queue = Queue.deque([seed_url])

seen = {seed_url: 0}

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()

depth = seen[url]

if rp.can_fetch(user_agent, url):

throttle.wait(url)

html = download(url, headers, proxy=proxy, num_retries=num_retries)

links = []

if scrape_callback:

# links.extend(scrape_callback(url, html) or [])

scrape_callback(url, html)

if depth != max_depth:

# 獲取鏈接

if link_regex:

links.extend(link for link in get_links(html) if re.match(link_regex, link))

# 如果沒有被訪問過，且域名相同，歸入連接誒隊(duì)列

for link in links:

link = normalize(seed_url, link)

if link not in seen:

seen[link] = depth + 1

if same_domain(seed_url, link):

crawl_queue.append(link)

num_urls += 1

if num_urls == max_urls:

break

else:

print("Blocked by robots.txt:", url)

class Throttle:

"""

在兩次下載之間添加時(shí)間延遲

"""

def __init__(self, delay):

self.delay = delay? # 延遲多長(zhǎng)時(shí)間

self.domains = {}? # 字典記錄域名最后一次被訪問的時(shí)間地圖

def wait(self, url):

"""

功能：頁面休眠

urlparse將url(http：//開頭)解析成組件

組件：協(xié)議(scheme)、位置(netloc)、路徑(path)、可選參數(shù)(parameters)、查詢(query)、片段(fragment)

:param url:

:return:

"""

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:

time.sleep(sleep_secs)

self.domains[domain] = datetime.datetime.now()

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):

"""

:param url:判斷是否是目標(biāo)鏈接

:param html:下載數(shù)據(jù)的頁面

:return:

"""

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)

def download(url, headers, proxy, num_retries, data=None):

"""

設(shè)置一般的請(qǐng)求后，根據(jù)爬蟲代理參數(shù)選擇是否使用特定處理器來獲取鏈接

若遇到50X網(wǎng)頁暫時(shí)無法訪問的情況，嘗試多次后無果則退出

:param url:鏈接

:param user_agent:用戶代理

:param proxy:協(xié)議，ip端口

:param num_retries:出錯(cuò)是嘗試訪問多少次

:return: 整個(gè)網(wǎng)頁的源代碼

"""

print("Downloading:", url)

request = urllib2.Request(url, data, headers)

opener = urllib2.build_opener()? # 用特定處理器來獲取urls

if proxy:

proxy_params = {urlparse.urlparse(url).scheme: proxy}

opener.add_handler(urllib2.ProxyHandler(proxy_params))

try:

html = urllib2.urlopen(request).read()

# # 數(shù)據(jù)獲取方式1：正則表達(dá)式(C、快、使用困難、靈活性差)

# result = re.findall('

(.*?)', html)

# if result:

#? ? print(result[1])

# # 數(shù)據(jù)獲取方式2：通過beautifulsoup(Python、慢、安裝簡(jiǎn)單)

# soup = BeautifulSoup(html, 'html.parser')

# tr = soup.find(attrs={'id': 'places_area__row'})

# if tr:

#? ? td = tr.find(attrs={'class': 'w2p_fw'})

#? ? area = td.text

#? ? print(area)

# # 數(shù)據(jù)獲取方式3：通過lxml(快、大量數(shù)據(jù)抓取效果更明顯、安裝相對(duì)困難)

# tree = lxml.html.fromstring(html)

# td = tree.cssselect('tr#places_neighbours__row > td.w2p_fw')

# if td:

#? ? area = td[0].text_content()

#? ? print(area)

except urllib2.URLError as e:

print("Download error:", e.reason)

html = None

if num_retries > 0:

if hasattr(e, 'code') and 500 <= e.code <= 600:

return download(url, headers, proxy, num_retries - 1, data)

return html

def get_links(html):

"""

提取網(wǎng)頁中的所有鏈接

:param html:

:return:

"""

webpage_regex = re.compile(']+href=["\'](.*?)["\']',

re.IGNORECASE)? # re.compile()函數(shù)將字符串形式的正則表達(dá)式轉(zhuǎn)換成模式

return webpage_regex.findall(html)

def get_robots(url):

"""

:param url:

:return: 包含robots信息的對(duì)象

"""

rp = robotparser.RobotFileParser()

rp.set_url(urlparse.urljoin(url, '/robots.txt'))

rp.read()

return rp

def normalize(seed_url, link):

"""

鏈接規(guī)范化，相對(duì)路徑轉(zhuǎn)化成絕對(duì)路徑

:param seed_link:

:param link:

:return:

"""

link, _ = urlparse.urldefrag(link)? # 去掉碎部(鏈接#后的部分)

return urlparse.urljoin(seed_url, link)

def same_domain(url1, url2):

"""

兩個(gè)鏈接的域名相同，為True

:param url1:

:param url2:

:return:

"""

return urlparse.urlparse(url1).netloc == urlparse.urlparse(url2).netloc

def main():

## 1.通過robots文件記錄的鏈接爬蟲

# crawl_sitemap('http://example.webscraping.com/sitemap.xml', scrape_callback=ScrapeCallback())

# # 2.通過ID爬蟲

# crawl_id('http://example.webscraping.com/places/default/view',scrape_callback=ScrapeCallback())

# 3.通過鏈接爬蟲

link_crawler('http://example.webscraping.com', '/places/default/(view|index)',

delay=0, num_retries=5, max_depth=2, user_agent='GoodCrawler', scrape_callback=ScrapeCallback())

main()

總結(jié)

以上是生活随笔為你收集整理的python简单网络爬虫_【Python】简单的网络爬虫的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。