Python Crawl Oh comics

1 ImportRequests2  fromlxmlImportetree3  fromBs4ImportBeautifulSoup4 ImportOS5  fromSeleniumImportWebdriver6 7 8 9 #parse each comic page and download comicsTen defmanhua (URL): One  A  - browser.get (URL) -  the     #get the page source of the simulated access -Html=Browser.page_source -  -  +HTML =etree. HTML (HTML) -Img_url = Html.xpath ('//img[@id = "Mangafile"]/@src') [0] +alt = Html.xpath ('/html/body/div[2]/div[2]/h1/a/text ()') [0] Atitle = Html.xpath ('/html/body/div[2]/div[2]/h2/text ()') [0] at     Print(Img_url,alt,title) -  -  -     #print (HTML) -  -  inPath='./Comics/'+alt+'/'+title+'/' -     if  notos.path.exists (path): to os.makedirs (path) +Fname=img_url.split ('/') [-1] -     #print (fname) the  *  $     Print(Os.path.join (path,fname))Panax Notoginseng  -     #Request.urlretrieve (Img_url,os.path.join (path,fname)) the  +     #Request Picture Address AResponse =requests.get (Img_url) the     #Binary decoding +Data=response.content -     #Save File $With open (Path+fname,'WB') as F: $ f.write (data) - #Parse Get comic page link - defmanhua_url (URL): theResponse =requests.get (URL) -Response.encoding =response.apparent_encodingWuyiHTML =Response.text theHTML =etree. HTML (HTML) -     #print (HTML) Wu     #I for comic pages -i = Html.xpath ('/html/body/div[2]/div[2]/span/text ()') [1][1:-1] AboutI=Int (i) $     #print (i) -     #find the rule of pagination -     #Splicing page links, choosing the Format function -url = url +'/index.html?p={}' A     #print (URL) +      forNinchRange (1,i+1): theFullUrl =Url.format (n) -         Print(FullUrl) $         #Time.sleep (2) the         #FullUrl for all pagination comics links the manhua (FullUrl) the  the #Parse List page - deflist (Lb_url): inResponse =requests.get (Lb_url) theResponse.encoding =response.apparent_encoding theHTML =Response.text AboutHTML = beautifulsoup (HTML,'lxml') the     #match all chapter links theUrl_list = Html.select ('Div.subbooklist ul Li') the      forUrlinchurl_list: +url = url.select ('a') [0].get ('href'). Split ('/') [-2] -  the         #print (URL)BayiFullUrl =Os.path.join (Lb_url,url) the         Print(FullUrl) the         #Chapter Links - Manhua_url (FullUrl) -  the     #print (url_list) the     #print (HTML) the  the #Parse Home - defShouye (): the     #Home Link theBase_url ='http://www.omanhua.com/' the     #initiating a request94Response =requests.get (Base_url) the     #decoding theResponse.encoding =response.apparent_encoding the     #Gets the page returned98HTML =Response.text About     #print (HTML) -     #parsing101HTML =beautifulsoup (HTML,'lxml')102     #Match Hottest Comics links103Url_list = Html.select ('Ul#cartoon_image_show1 Li')104      forUrlinchurl_list: the         #print (URL)106url = url.select ('a') [0].get ('href') [1:]107         #alt = Url.select (' a ')108         #Print (ALT)109         #Splicing Links theFullUrl =Os.path.join (Base_url,url)111         Print(FullUrl) the 113 list (fullurl) the if __name__=='__main__': the     #use the automatic test module selenium to simulate the browser access, here with Google image loading get no image link the     #The following path is the Chorm drive path117Browser = Webdriver. Chrome (executable_path=r'C:\Users\zhaozhi\Desktop\chromedriver.exe')118Shouye ()

The first self-study crawler soon, the code may be a bit cumbersome to write, I hope to work with you to learn progress

Python Crawl Oh comics