Python爬取读者并制作成PDF

yipeiwu_com5年前Python爬虫

学了下beautifulsoup后,做个个网络爬虫,爬取读者杂志并用reportlab制作成pdf..

crawler.py

复制代码 代码如下:

#!/usr/bin/env python
#coding=utf-8
"""
    Author:         Anemone
    Filename:       getmain.py
    Last modified:  2015-02-19 16:47
    E-mail:         anemone@82flex.com
"""
import urllib2
from bs4 import BeautifulSoup
import re
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
def getEachArticle(url):
#    response = urllib2.urlopen('http://www.52duzhe.com/2015_01/duzh20150104.html')
    response = urllib2.urlopen(url)
    html = response.read()
    soup = BeautifulSoup(html)#.decode("utf-8").encode("gbk"))
    #for i in soup.find_all('div'):
    #    print i,1
    title=soup.find("h1").string
    writer=soup.find(id="pub_date").string.strip()
    _from=soup.find(id="media_name").string.strip()
    text=soup.get_text()#.encode("utf-8")
    main=re.split("BAIDU_CLB.*;",text)
    result={"title":title,"writer":writer,"from":_from,"context":main[1]}
    return result
    #new=open("new.txt","w")
    #new.write(result["title"]+"\n\n")
    #new.write(result["writer"]+"  "+result["from"])
    #new.write(result["context"])
    #new.close()
def getCatalog(issue):
    url="http://www.52duzhe.com/"+issue[:4]+"_"+issue[-2:]+"/"
    firstUrl=url+"duzh"+issue+"01.html"
    firstUrl=url+"index.html"
    duzhe=dict()
    response = urllib2.urlopen(firstUrl)
    html = response.read()
    soup=BeautifulSoup(html)
    firstUrl=url+soup.table.a.get("href")
    response = urllib2.urlopen(firstUrl)
    html = response.read()
    soup = BeautifulSoup(html)
    all=soup.find_all("h2")
    for i in all:
        print i.string
        duzhe[i.string]=list()
        for link in i.parent.find_all("a"):
            href=url+link.get("href")
            print href
            while 1:
                try:
                    article=getEachArticle(href)
                    break
                except:
                    continue
            duzhe[i.string].append(article)
    return duzhe
def readDuZhe(duzhe):
    for eachColumn in duzhe:
        for eachArticle in duzhe[eachColumn]:
            print eachArticle["title"]
if __name__ == '__main__':
#    issue=raw_input("issue(201501):")
    readDuZhe(getCatalog("201424"))

getpdf.py

复制代码 代码如下:

#!/usr/bin/env python
#coding=utf-8
"""
    Author:         Anemone
    Filename:       writetopdf.py
    Last modified:  2015-02-20 19:19
    E-mail:         anemone@82flex.com
"""
#coding=utf-8
import reportlab.rl_config
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.lib import fonts
import copy
from reportlab.platypus import Paragraph, SimpleDocTemplate,flowables
from reportlab.lib.styles import getSampleStyleSheet
import crawler
def writePDF(issue,duzhe):
    reportlab.rl_config.warnOnMissingFontGlyphs = 0
    pdfmetrics.registerFont(TTFont('song',"simsun.ttc"))
    pdfmetrics.registerFont(TTFont('hei',"msyh.ttc"))
    fonts.addMapping('song', 0, 0, 'song')
    fonts.addMapping('song', 0, 1, 'song')
    fonts.addMapping('song', 1, 0, 'hei')
    fonts.addMapping('song', 1, 1, 'hei')
    stylesheet=getSampleStyleSheet()
    normalStyle = copy.deepcopy(stylesheet['Normal'])
    normalStyle.fontName ='song'
    normalStyle.fontSize = 11
    normalStyle.leading = 11
    normalStyle.firstLineIndent = 20
    titleStyle = copy.deepcopy(stylesheet['Normal'])
    titleStyle.fontName ='song'
    titleStyle.fontSize = 15
    titleStyle.leading = 20
    firstTitleStyle = copy.deepcopy(stylesheet['Normal'])
    firstTitleStyle.fontName ='song'
    firstTitleStyle.fontSize = 20
    firstTitleStyle.leading = 20
    firstTitleStyle.firstLineIndent = 50
    smallStyle = copy.deepcopy(stylesheet['Normal'])
    smallStyle.fontName ='song'
    smallStyle.fontSize = 8
    smallStyle.leading = 8
    story = []
    story.append(Paragraph("<b>读者{0}期</b>".format(issue), firstTitleStyle))
    for eachColumn in duzhe:
        story.append(Paragraph('__'*28, titleStyle))
        story.append(Paragraph('<b>{0}</b>'.format(eachColumn), titleStyle))
        for eachArticle in duzhe[eachColumn]:
            story.append(Paragraph(eachArticle["title"],normalStyle))
    story.append(flowables.PageBreak())
    for eachColumn in duzhe:
        for eachArticle in duzhe[eachColumn]:
            story.append(Paragraph("<b>{0}</b>".format(eachArticle["title"]),titleStyle))
            story.append(Paragraph(" {0}  {1}".format(eachArticle["writer"],eachArticle["from"]),smallStyle))
            para=eachArticle["context"].split("  ")
            for eachPara in para:
                story.append(Paragraph(eachPara,normalStyle))
            story.append(flowables.PageBreak())
    #story.append(Paragraph("context",normalStyle))
    doc = SimpleDocTemplate("duzhe"+issue+".pdf")
    print "Writing PDF..."
    doc.build(story)
def main(issue):
    duzhe=crawler.getCatalog(issue)
    writePDF(issue,duzhe)
if __name__ == '__main__':
    issue=raw_input("Enter issue(201501):")
    main(issue)

以上就是本文的全部内容了,希望大家能够喜欢。

相关文章

使用PyV8在Python爬虫中执行js代码

前言 可能很多人会觉得这是一个奇葩的需求,爬虫去好好的爬数据不就行了,解析js干嘛?吃饱了撑的? 搜索一下互联网上关于这个问题还真不少,但是大多数童鞋是因为自己的js基础太烂,要么是HT...

python面向对象多线程爬虫爬取搜狐页面的实例代码

python面向对象多线程爬虫爬取搜狐页面的实例代码

首先我们需要几个包:requests, lxml, bs4, pymongo, redis 1. 创建爬虫对象,具有的几个行为:抓取页面,解析页面,抽取页面,储存页面 class S...

Python爬取APP下载链接的实现方法

Python爬取APP下载链接的实现方法

首先是准备工作 Python 2.7.11:下载python Pycharm:下载Pycharm 其中python2和python3目前同步发行,我这里使用的是python2作为环境。P...

python爬取淘宝商品详情页数据

python爬取淘宝商品详情页数据

在讲爬取淘宝详情页数据之前,先来介绍一款 Chrome 插件:Toggle JavaScript (它可以选择让网页是否显示 js 动态加载的内容),如下图所示: 当这个插件处于关闭状...

Python3爬虫学习入门教程

Python3爬虫学习入门教程

本文实例讲述了Python3爬虫相关入门知识。分享给大家供大家参考,具体如下: 在网上看到大多数爬虫教程都是Python2的,但Python3才是未来的趋势,许多初学者看了Python2...