# -*- coding: utf-8 -*-
# 031904138-王绮雯
# 爬取http://www.weather.com.cn/
# 8页138张图片（18*7+12=138）
import sqlite3
from urllib import request

import pandas as pd
from bs4 import BeautifulSoup, UnicodeDammit
import urllib.request
import requests
import re

# 使用urllib.request爬取网页
def getHTMLText(url):
	try:
		headers = {
			"user-agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36"
		}
		req = urllib.request.Request(url=url,headers=headers)
		data = urllib.request.urlopen(req)
		data = data.read()
		dammit = UnicodeDammit(data, ["utf-8", "gbk"])
		data=dammit.unicode_markup
		return data
	except Exception as err:
		print(err)

def parsePage(html,num):    # num表示每页爬取的商品数量
	list=[]
	try:
		soup = BeautifulSoup(html, 'html.parser')
		imgs = soup.select('img')
		imgs = str(imgs)
		p_picture = re.compile('src="(.*?)"')		#观察html文件内容后提取出关键字
		pictures = re.findall(p_picture, imgs)		#查找图片链接

		for i in range(num):						#按照指定数量得到列表
			list.append(pictures[i])
		return list
	except:
		return ""


# 输出图片链接列表
def printGoodsList(list):
	tply="{0:^4}\t{1:^30}"
	print(tply.format("序号","图片链接",chr(12288)))
	count=1
	for img in list:
		print(tply.format(count,img,chr(12288)))
		count = count + 1

#将每张图片写到本地
def save2file(img_url_list,path):
	i=1
	for img in img_url_list:
		img_url = img
		new_path = path + str(i) + ".jpg"
		urllib.request.urlretrieve(img_url, new_path)		#定义存取本地图片路径
		i += 1

# 用于找到图片数量足够多的页面
def pagelinks(html):
	soup = BeautifulSoup(html, 'html.parser')
	link = soup.select('a')  # 找到页面链接
	p_link = re.compile('href="(.*?)"')
	link = str(link)
	links = re.findall(p_link, link)

	pagelinks = []  # 找到图片数量足够的页面链接
	num = 0
	for i in range(len(links)):
		if (num <= 10):
			try:
				html = getHTMLText(links[i])
				soup = BeautifulSoup(html, 'html.parser')
				imgs = soup.select('img')
				p_picture = re.compile('src="(.*?)"')  # 观察html文件内容后提取出关键字
				imgs = str(imgs)
				# print(imgs)
				picture = re.findall(p_picture, imgs)
				if (len(picture) >= 20):
					pagelinks.append(links[i])
					num += 1
			except:
				pass
	return pagelinks

if __name__ == "__main__":
	url = 'http://www.weather.com.cn/'
	picture_list = []			#用于记录得到的图片链接

	html = getHTMLText(url)
	pagelink = pagelinks(html)	# 找到其他页面跳转链接

	page = 8  # 学号031904138 爬取页数为8，图片数量为138
	for i in range(page):			#138=7*18+1*12  最后一页爬取12项
		url = pagelink[i]
		html = getHTMLText(url)		#爬取指定网页
		if(i==page-1):
			list = parsePage(html,12)	# 解析网页提取需要的数据，最后一页提取12项
		else:
			list = parsePage(html, 18)  # 解析网页提取需要的数据,提取前18项
		picture_list.extend(list)

	printGoodsList(picture_list)  # 打印得到的数据

	path = r"D:/wqwDownload/PyCharm Community Edition 2021.2.2/PycharmProjects/wqwcodes/爬虫实践课/第三次作业/picture/"	#图片保存路径
	save2file(picture_list,path)			#将图片保存到本地文件