问将regex与html标记组合在一起

EN

page = 
"""
<font style="DISPLAY: inline; FONT-FAMILY: Times New Roman; FONT-SIZE: 10pt; FONT-WEIGHT: bold">Item 1. Business/</font> Unless otherwise indicated by the context, we use the terms “GE” and “GECC” on the basis of consolidation described in Note 1 to the consolidated financial statements in Part II, Item 8. “Financial Statements and Supplementary Data” of this Form 10-K Report. Also, unless otherwise indicated by the context, “General Electric” means the parent company, General Electric Company (the Company).

General Electric’s address is 1 River Road, Schenectady, NY 12345-6999; we also maintain executive offices at 3135 Easton Turnpike, Fairfield, CT 06828-0001.

<font style="DISPLAY: inline; FONT-FAMILY: Times New Roman; FONT-SIZE: 10pt; FONT-WEIGHT: bold">Item 1A. Risk Factors</font>"""

regexs = ('bold;\">\s*Item 1\.(.+?)bold;\">\s*Item 1A\.',   #<===pattern 1: with an attribute bold before the item subtitle
              'b>\s*Item 1\.(.+?)b>\s*Item 1A\.',               #<===pattern 2: with a tag <b> before the item subtitle
              'Item 1\.\s*<\/b>(.+?)Item 1A\.\s*<\/b>',         #<===pattern 3: with a tag <\b> after the item subtitle          
              'Item 1\.\s*Business\.\s*<\/b(.+?)Item 1A\.\s*Risk Factors\.\s*<\/b') #<===pattern 4: with a tag <\b> after the item+description subtitle 

for regex in regexs:
    match = re.search(regex, page, flags=re.IGNORECASE|re.DOTALL)  #<===search for the pattern in HTML using re.search from the re package. Ignore cases.
    if match:
        soup = BeautifulSoup(match.group(1), "html.parser") #<=== match.group(1) returns the texts inside the parentheses (.*?) 

            #soup.text removes the html tags and only keep the texts
            #rawText = soup.text.encode('utf8') #<=== you have to change the encoding the unicodes
        rawText = soup.text
        print(rawText)
        break

Unless otherwise indicated by the context, we use the terms “GE” and “GECC” on the basis of consolidation described in Note 1 to the consolidated financial statements in Part II, Item 8. “Financial Statements and Supplementary Data” of this Form 10-K Report. Also, unless otherwise indicated by the context, “General Electric” means the parent company, General Electric Company (the Company).

General Electric’s address is 1 River Road, Schenectady, NY 12345-6999; we also maintain executive offices at 3135 Easton Turnpike, Fairfield, CT 06828-0001.

# Import the libraries
import requests
from bs4 import BeautifulSoup
import re
url = "https://www.sec.gov/Archives/edgar/data/40545/000004054513000036/geform10k2012.htm"
HEADERS = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"}
response = requests.get(url, headers=HEADERS)
print(response.status_code)

page = response.text
#Pre-processing the html content by removing extra white space and combining then into one line.
page = page.strip()  #<=== remove white space at the beginning and end
page = page.replace('\n', ' ') #<===replace the \n (new line) character with space
page = page.replace('\r', '') #<===replace the \r (carriage returns -if you're on windows) with space
page = page.replace('&nbsp;', ' ') #<===replace "&nbsp;" (a special character for space in HTML) with space. 
page = page.replace('&#160;', ' ') #<===replace "&#160;" (a special character for space in HTML) with space.
page = page.replace(u'\xa0', ' ') #<===replace "&#160;" (a special character for space in HTML) with space.
page = page.replace(u'/s/', ' ') #<===replace "&#160;" (a special character for space in HTML) with space.
while '  ' in page:
    page = page.replace('  ', ' ') #<===remove extra space