Python應用之爬取一本pdf

 

爬取https://max.book118.com網站的某一本書，其實也算不上爬取，只是下載。我這個只是拋磚引玉，大神們能夠寫個網站整個文檔的爬蟲。

以這本書爲列 https://max.book118.com/html/2017/0802/125615287.shtm，再加上批量img2pdf的方法，就能夠下載一本書了。具體的分析過程不在此贅述，直接上代碼（代碼只是用於本人學習，寫的有些low）

 

import requests import os import json def savePng(url, fileName): root = "//home//Desktop//" path = root + "//" + fileName if not os.path.exists(root): os.mkdir(root) if not os.path.exists(path): r = requests.get(url) r.raise_for_status() with open(path, "wb+") as f: f.write(r.content) def getPNGName(url): req = requests.get(url) json_req = req.content.decode() json_dict= json.loads(json_req) print(json_dict) return json_dict["NextPage"] def getNextPageURL(pngName): url = "https://view42.book118.com/pdf/GetNextPage/?f=dXAyMjI2LTIuYm9vazExOC5jb20uODBcMzQ4NDU0MS01OTgxMGI5MDMwM2JjLnBkZg==&img=%s&isMobile=false&isNet=True&readLimit=kVJSwRWfuu2BpuMVDJqlnw==&furl=o4j9ZG7fK94kkYRv4gktA2rYw4NlKHsQghNfCDpGDtCDuhClp@zqsXbBvWkfutt7oIxYGVjQwpqa2_7Y@T__cVzRwC_U6kA_a5K64MvXGRoemz@A5sruig==" % pngName return url def getCurPageUrl(pngName): url = "https://view42.book118.com/img/?img=%s" % pngName return url #url = getNextPageURL("7o@o7xcocmmKnrqreQGENvFMksKYwld1WTnrOUUaeADxViDtQ3Pv9cm31oOktykHcA4m4rqRBGs=")
url = "https://view42.book118.com/pdf/GetNextPage/?f=dXAyMjI2LTIuYm9vazExOC5jb20uODBcMzQ4NDU0MS01OTgxMGI5MDMwM2JjLnBkZg==&img=7o@o7xcocmmKnrqreQGENvFMksKYwld1WTnrOUUaeADxViDtQ3Pv9R7mPNB3WAYh&isMobile=false&isNet=True&readLimit=kVJSwRWfuu2BpuMVDJqlnw==&furl=o4j9ZG7fK94kkYRv4gktA2rYw4NlKHsQghNfCDpGDtCDuhClp@zqsXbBvWkfutt7oIxYGVjQwpqa2_7Y@T__cVzRwC_U6kA_a5K64MvXGRoemz@A5sruig=="   
for curPageIndex in range(0, 486): #根據當前圖片名字，請求下一張圖片名字
    pngName = getPNGName(url) #根據下一張圖片名字拼湊url
    url = getCurPageUrl(pngName) #下載PNG，記錄圖片名字
    savePng(url, str(curPageIndex) + ".PNG") #獲得下一頁圖片url
    url = getNextPageURL(pngName)