Python 学习笔记---爬取海贼王动漫

最近无聊整理的爬虫代码，可以自动爬取腾讯动漫的任意漫画，思路如下：

1. 先获取想下载的动漫url， 这里用了 getUrls ，直接获取动漫的最后一章

2. 然后进入到该动漫去获取要下载的图片url

3. 下载到本地

import os
import random
import time
from random import randint

from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver import DesiredCapabilities
import urllib.request as urllib2

ROOT_URL = "http://ac.qq.com"
target_url = [
    ROOT_URL + "/Comic/comicInfo/id/505430",  # 海贼王
]
ua_list = [
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"
]

user_agent=random.choice(ua_list)
dir_path="D:/py/海贼王/"

def getImageUrls(comic_url):
    '''
    通过Selenium和Phantomjs获取动态生成的数据
    '''
    urls = []

    dcap = dict(DesiredCapabilities.PHANTOMJS)
    dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/4.0 (compatible; MSIE 5.5; windows NT)")
    browser = webdriver.PhantomJS(executable_path=r"E:\py\littlepy\tencent_cartoon\phantomjs-2.1.1-windows\bin\phantomjs.exe",
                                  desired_capabilities=dcap)
    browser.get(comic_url)

    imgs = browser.find_elements_by_xpath("//div[@id='mainView']/ul[@id='comicContain']//img")
    for i in range(0, len(imgs) - 1):
        if i == 1:  # 略过广告图片
            continue
        urls.append(imgs[i].get_attribute("src"))
        js = 'window.scrollTo( 800 ,' + str((i + 1) * 1280) + ')'
        browser.execute_script(js)
        time.sleep(randint(3, 6))

    browser.quit()
    print("urls=",urls)
    return urls

def getUrls(comic_url):
    result = dict()
    req = urllib2.Request(comic_url)
    req.add_header('User-Agent', user_agent)
    print("url=",comic_url)
    response = urllib2.urlopen(req)
    soup = BeautifulSoup(response, "lxml")
    #print("soup=",soup)
    # 返回最近漫画中的最新20话
    page = soup.find(attrs={"class": "chapter-page-new works-chapter-list"}).find_all(
        "a")  # 全部漫画 chapter-page-new works-chapter-list
    title = page[-1]['title']
    result[title] = ROOT_URL + page[-1]['href']
    print("title=",title)
    print("result=",result[title])
    return title,result[title]

def downloadComics(dir_path, urls):
    for url in urls:
        urllib2.urlretrieve(url, dir_path + url[-8:-2])
        #print("url=",url[-9:-2])

if __name__ == "__main__":
    title,result_url=getUrls(target_url[0])
    urls=getImageUrls(result_url)
    path=dir_path+title+"/"
    isExists = os.path.exists(path)
    if not isExists:
        os.makedirs(path)
        print(path + '    创建成功')
    downloadComics(path,urls)