# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(http\S+\.pdf)"
test_str = ("Name|COL\n"
"San Diego|'https://foo.com/energy_docs/tyv/2004/019787_S30_gasTOC.cfm https://foo.com/energy_docs/tyv/99/19787s022_gas.pdf https://foo.com/energy_docs/tyv/2000/19787s021_gas.pdf https://foo.com/energy_docs/tyv/2000/19787-s017_report.pdf https://foo.com/energy_docs/tyv/99/293-_9302SDFS 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/99/19787-s018_gas.pdf https://foo.com/energy_docs/tyv/2000/19787-s017_report.pdf https://foo.com/energy_docs/tyv/98/019787-S16_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/019787-S15_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/019787-S14_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/19787-S013_gas.pdf https://foo.com/energy_docs/tyv/96/019787-S12_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/019787-S11_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/019787-S10_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S9_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S8_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/19-787s007_Amlodipine.cfm https://foo.com/energy_docs/tyv/pre96/019787-S6_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S5_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S4_gas GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S3_gas_toc.cfm https://foo.com/energy_docs/tyv/pre96/019787-S2_gas GAS_TPC.cfm'\n"
"Washington|'https://foo.com/energy_docs/a32/2007/022136.cfm'\n"
"Texas|'https://foo.com/energy/29380/no_ant/USA/2/2007.pdf'")
matches = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html