python The reptile crawls for the bean Top250 The book information , And save to file

import requests
from bs4 import BeautifulSoup
resp = requests.get('https://book.douban.com/top250?start=0')
soup = BeautifulSoup(resp.text, 'lxml')
# Request for HTML Function of source code
def get_html(url):
# Masquerading as a browser access
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'}
resp = requests.get(url, headers=headers).text
return resp
# Get functions for all pages
def all_page():
base_url = 'https://book.douban.com/top250?start='
urllist = []
# from 0 To 225, interval 25 Array of
for page in range(0, 250, 25):
allurl = base_url + str(page)
urllist.append(allurl)
return urllist
# Parsing the page , Get data information
def html_parse():
# Call function ,for Loop through all pages
for url in all_page():
# BeautifulSoup Parsing
soup = BeautifulSoup(get_html(url), 'lxml')
# Title
alldiv = soup.find_all('div', class_='pl2')
names = [a.find('a')['title'] for a in alldiv]
# author
allp = soup.find_all('p', class_='pl')
authors = [p.get_text() for p in allp]
# score
starspan = soup.find_all('span', class_='rating_nums')
scores = [s.get_text() for s in starspan]
# brief introduction
sumspan = soup.find_all('span', class_='inq')
sums = [i.get_text() for i in sumspan]
for name, author, score, sum in zip(names, authors, scores, sums):
name = ' Title ：' + str(name) + '\n'
author = ' author ：' + str(author) + '\n'
score = ' score ：' + str(score) + '\n'
sum = ' brief introduction ：' + str(sum) + '\n'
data = name + author + score + sum
# Save the data
f.writelines(data + '=======================' + '\n')
# file name
filename = ' Douban books Top250.txt'
# Save file operation
f = open(filename, 'w', encoding='utf-8')
# Call function
html_parse()
f.close()
print(' Saved successfully .')
# find_all() Method ,
# Be careful class yes Python key word , Then underline it _：
# alldiv = soup.find_all('div', class_='pl2')
# for a in alldiv:
# names = a.find('a')['title']
# print('find_all():', names)
# find() Method ：
# alldiv2 = soup.find('div', class_='pl2')
# names2 = alldiv2.find('a')['title']
# print('find():', names2 )

Xiaobai's crawler road , The first water test .