Using Python+selenium to crawl the most popular books in watercress reading, sorted by rating

Grab watercress Reading (http://book.douban.com/) Themost popular books, sorted by rating, and saved to TXT file, need to crawl the name of the book, author, rating, genre and a comment on the sentence

#coding =utf-8from selenium import webdriverfrom time import sleepclass  Doubanpopularbook:    def __init__ (self):         self.dr = webdriver. Chrome ()         self.popular_books_list = self.get_douban_ Popular_books ()     def get_douban_popular_books (self):         self.dr.get (' https://book.douban.com/')         sleep (3)         popular_books_list = [] # Define an empty list to hold the acquired book information         i = 0         while i < 10:             book_info = self.dr.find_elements_by_css_selector ("[class= ' List-col list-col2  List-summary s ']>li ") [i].text  #通过css用class属性和标签li组合来获取书籍所有文本信息              popular_books_list.append (book_info.split (' \ n '))  # Append book information to an empty list separated by a newline character             i += 1          #popular_books_list. Sort (key=lambda x:float (x[1][0:2)),  reverse=true)   #用sort中key方法根据书籍评分从高到低进行排序         sorted ( Popular_books_list, key=lambda book: book[1], reverse=true)          return popular_books_list    def get_popular_books_rank_file ( Self):        self.file_title =  ' watercress list of top rated books '          self.file = open (self.file_title +  '. txt ',  ' WB ')         for item in self.popular_books_list:             separate_line =  ' ~~~~~~~~~~~~~~~~~~~~~~~~\n '              self.file.write (Separate_line.encode (' Utf-8 '))              self.file.write (' Book Name: ' +item[0]+ ' \ n '). Encode (' Utf-8 '))             self.file.write (' Score: ' +item[1]+ ' \ n '). Encode (' Utf-8 '))             self.file.write ((item[ 2]+ ' \ n '). Encode (' Utf-8 '))              Self.file.write (' Genre: ' +item[3]+ ' \ n '). Encode (' Utf-8 '))              if item[4] ==  ' have ebook ':                &nbSp;self.file.write (' A remark: ' +item[5]+ ' \ n '). Encode (' Utf-8 '))              else:                 self.file.write (' A remark: ' +item[4]+ ' \ n '). Encode (' Utf-8 '))          self.file.close ()     def quit (self):         self.dr.quit () if __name__ ==  ' __main__ ':    popular_books  = doubanpopularbook ()     popular_books.get_popular_books_rank_file ()      popular_books.quit ()

The page is as follows:

650) this.width=650; "Src=" http://images2015.cnblogs.com/blog/942023/201612/942023-20161214221546354-484427625. PNG "alt=" 942023-20161214221546354-484427625.png "/>

650) this.width=650; "Src=" http://images2015.cnblogs.com/blog/942023/201612/942023-20161214221630354-618661845. PNG "alt=" 942023-20161214221630354-618661845.png "/>

The resulting TXT effect is as follows:

650) this.width=650; "Src=" http://images2015.cnblogs.com/blog/942023/201612/942023-20161214221818979-249351042. PNG "alt=" 942023-20161214221818979-249351042.png "/>

650) this.width=650; "Src=" http://images2015.cnblogs.com/blog/942023/201612/942023-20161214221854620-1577556429. PNG "alt=" 942023-20161214221854620-1577556429.png "/>

This article comes from "No idea, no achievement!" "Blog, be sure to keep this provenance http://kemixing.blog.51cto.com/10774787/1882846

Using Python+selenium to crawl the most popular books in watercress reading, sorted by rating