python爬取各类文档方法归类汇总

### Reading TXT doc ###
from urllib.request import urlopen
from urllib.error import URLError,HTTPError
import re

try:
 textPage = urlopen("http://www.pythonscraping.com/pages/warandpeace/chapter1.txt")
except (URLError,HTTPError) as e:
 print("Errors:\n")
 print(e)
#print(textPage.read())
text = str(textPage.read())

#下面方法用正则匹配含1805的句子
pattern = re.compile("\..*1805(\w|,|\s|-)*(\.)")#不完美，简单示例
match = pattern.search(text)
if match is not None:
 print(match.group())

#下面方法不用正则。先用.将句集分片，之后就可遍历了。
ss = text.split('.')
key_words = "1805"
words_list = [x.lower() for x in key_words.split()]
for item in ss:
 if all([word in item.lower() and True or False for word in words_list]):
  print(item)

from urllib.request import urlopen
from urllib.error import URLError,HTTPError
from bs4 import BeautifulSoup
try:
 html = urlopen("https://en.wikipedia.org/wiki/Python_(programming_language)")
except (URLError,HTTPError) as e:
 print(e)
try:
 bsObj = BeautifulSoup(html,"html.parser")
 content = bsObj.find("div",{"id":"mw-content-text"}).get_text()
except AttributeError as e:
 print(e)

meta = bsObj.find("meta")
#print(bsObj)
if meta.attrs['charset'] == 'UTF-8':
 content = bytes(content,"UTF-8")
 print("-----------------UTF-8--------------")
 print(content.decode("UTF-8"))
if meta.attrs['charset'] == 'iso-8859-1':
 content = bytes(content,"iso-8859-1")
 print("--------------iso-8859-1------------")
 print(content.decode("iso-8859-1"))

#csv远程获取，内存加载读取
from urllib.request import urlopen
import csv
from io import StringIO#在内存中读写str，如果要操作二进制数据，就需要使用BytesIO

try:
 data = urlopen("http://pythonscraping.com/files/MontyPythonAlbums.csv").read().decode("ascii","ignore")
except (URLError,HTTPError) as e:
 print("Errors:\n")
 print(e)

dataFile = StringIO(data)
csvReader = csv.reader(dataFile)
count = 0
for row in csvReader:
 if count < 10:
  print(row)
 else:
  print("...\n...")
  break
 count += 1 

#将数据写入本地csv文件
with open("./localtmp.csv","wt",newline='',encoding='utf-8') as localcsvfile:
 writer = csv.writer(localcsvfile)
 count = 0 
 try:
  for row in csvReader:
   if count < 10:
    writer.writerow(row)
   else:
    break
   count += 1
 finally:
  localcsvfile.close()

#csv.DictReader读取csv文件，可以有效处理标题行等问题
from urllib.request import urlopen
import csv
from io import StringIO#在内存中读写str，如果要操作二进制数据，就需要使用BytesIO

try:
 data = urlopen("http://pythonscraping.com/files/MontyPythonAlbums.csv").read().decode("ascii","ignore")
except (URLError,HTTPError) as e:
 print("Errors:\n")
 print(e)

dataFile = StringIO(data)
csvReader = csv.reader(dataFile)
dictReader = csv.DictReader(dataFile)
print(dictReader.fieldnames)
count = 0
for row in dictReader:
 if count < 10:
  print(row)
 else:
  print("...\n...")
  break
 count += 1 

#抓取并操作pdf
#pdf READ operation
from urllib.request import urlopen
from pdfminer.pdfinterp import PDFResourceManager,process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO,open

def readPDF(filename):
 resmgr = PDFResourceManager()#STEP 1
 retstr = StringIO()#STEP 2
 laparams = LAParams()#STEP 3
 device = TextConverter(resmgr,retstr,laparams=laparams)#STEP 4

 process_pdf(resmgr,device,filename)#STEP 5
 device.close()#STEP 6

 content = retstr.getvalue()
 retstr.close()
 return content

try:
 pdffile = urlopen("http://www.fit.vutbr.cz/research/groups/speech/servite/2010/rnnlm_mikolov.pdf")

except (URLError,HTTPError) as e:
 print("Errors:\n")
 print(e)

outputString = readPDF(pdffile)#也可以读取由pdffile=open("../../readme.pdf")语句打开的本地文件。
print(outputString)
pdffile.close()

#读取word docx文档内容
from zipfile import ZipFile
from urllib.request import urlopen
from io import BytesIO
from bs4 import BeautifulSoup

wordFile = urlopen("http://pythonscraping.com/pages/AWordDocument.docx").read()
wordFile = BytesIO(wordFile)
document = ZipFile(wordFile)#
xml_content = document.read("word/document.xml")
#print(xml_content.decode("utf-8"))

wordObj = BeautifulSoup(xml_content.decode("utf-8"),"lxml")
textStrings = wordObj.findAll("w:t")
for textElem in textStrings:
 print(textElem.text)